|
22295
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
LLM API Pricing Comparison & Cost Guide (May 2026)
LLM API Pricing Comparison & Cost Guide (May 2026)
Close tab
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
AI Chat settings
Close
WORK, Google Account: [EMAIL]
Main menu
New Chat
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected. Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
You said
I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected.
Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
Expand
Listen
Show thinking
Gemini said
Gemini said
Here is a summary of the changes in the provided code diff:
AI Call Scoring Additions
AI Call Scoring Additions
Pre-computed Scores:
Added strict instructions to treat the
ai_call_score
as pre-computed data. The system must interpret and summarize the provided scores rather than inventing or recalculating them.
Context Breakdown:
*
Short Context:
Now displays the
AI Scorecard
name and the overall
AI Score
(the average of per-rule scores).
Full Context:
Details the
ai_call_score
object, breaking down individual rules. Each rule includes a title, prompt, a 1–5 score, a brief justification, and up to three timestamped speaker references (MM:SS).
Application Rules:
Instructs the system to use these scores for coaching summaries, trends, and comparisons, but dictates that it must still rely on the actual transcript for direct quotes.
Grammar and Formatting Cleanup
Grammar and Formatting Cleanup
Typo Corrections:
Fixed minor grammatical errors, such as changing "contexts" to "context" and "utlizes" to "utilizes".
String Formatting:
Cleaned up the markdown link instructions by removing trailing newline and quotation artifacts (
\n"
) from the text strings.
Good response
Bad response...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22295
|
|
22294
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
LLM API Pricing Comparison & Cost Guide (May 2026)
LLM API Pricing Comparison & Cost Guide (May 2026)
Close tab
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
AI Chat settings
Close
WORK, Google Account: [EMAIL]
Main menu
New Chat
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected. Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
You said
I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected.
Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
Expand
Listen
Show thinking
Gemini said
Gemini said
Here is a summary of the changes in the provided code diff:
AI Call Scoring Additions
AI Call Scoring Additions
Pre-computed Scores:
Added strict instructions to treat the
ai_call_score
as pre-computed data. The system must interpret and summarize the provided scores rather than inventing or recalculating them.
Context Breakdown:
*
Short Context:
Now displays the
AI Scorecard
name and the overall
AI Score
(the average of per-rule scores).
Full Context:
Details the
ai_call_score
object, breaking down individual rules. Each rule includes a title, prompt, a 1–5 score, a brief justification, and up to three timestamped speaker references (MM:SS).
Application Rules:
Instructs the system to use these scores for coaching summaries, trends, and comparisons, but dictates that it must still rely on the actual transcript for direct quotes.
Grammar and Formatting Cleanup
Grammar and Formatting Cleanup
Typo Corrections:
Fixed minor grammatical errors, such as changing "contexts" to "context" and "utlizes" to "utilizes".
String Formatting:
Cleaned up the markdown link instructions by removing trailing newline and quotation artifacts (
\n"
) from the text strings.
Good response
Bad response
Share & export
Copy
Show more options
Copy prompt
Edit
You said are there some issues and bottlenecks
You said
are there some issues and bottlenecks
Listen
Show thinking
Gemini said
Gemini said
Looking closely at the system instructions in the diff, there are definitely a few potential prompt engineering issues and bottlenecks introduced by these additions. When you ask a Large Language Model (LLM) to juggle large transcripts alongside complex JSON scoring objects, it creates specific friction points.
Here is a breakdown of the potential issues and bottlenecks based on the changes:
1. Token Consumption and Context Bloat (Bottleneck)
1. Token Consumption and Context Bloat (Bottleneck)
Massive Payload Size:
By injecting the full
ai_call_score
object into the context (which includes rule names, prompts, scores, text justifications, and up to three timestamps
per rule
), the token count per call will skyrocket.
Context Window Limits:
The prompt states:
"The full call context includes all calls data available..."
If a user filters for 5 or 10 calls, injecting the transcripts
plus
these extensive AI scoring arrays could easily hit the model's maximum context window, leading to truncated data or degraded recall (the "lost in the middle" effect).
2. LLM Instruction Conflicts (Issue)
2. LLM Instruction Conflicts (Issue)
Pre-computed vs. Raw Transcript:
The prompt explicitly instructs the model:
"
Do not
invent, override, or recalculate scores"
but later says,
"For
what was actually said
, still rely on the
transcript
."
This creates a cognitive conflict for the LLM. If the raw transcript contradicts the pre-computed
justification
, the LLM might struggle with which source of truth to prioritize, potentially leading to hallucinations or contradictory summaries.
Prompt Complexity:
The more rules you add about
how
to read JSON formatting and
what
not to do, the less attention the model pays to the actual user query. This is a common bottleneck in prompt engineering known as instruction bloat.
3. Edge Cases in Formatting (Issue)
3. Edge Cases in Formatting (Issue)
Timestamp Limitations:
The instructions strictly define timestamps as
MM:SS
. This works fine for standard calls, but for longer meetings (over an hour), it either forces an awkward format (e.g.,
85:30
) or breaks if the system outputs
HH:MM:SS
.
Decimal vs. Whole Numbers:
The prompt specifies that the overall AI Score might be a decimal (average), but the individual rule score is a "Whole number
1–5
". If the upstream pipeline accidentally passes a decimal for a rule score, the LLM might get confused based on these rigid instructions.
How are you currently handling pagination or chunking for these calls—are you limiting the number of calls that can be passed into the full context at once to avoid token limits?
Good response
Bad response
Redo
Share & export
Copy
Show more options
Enter a prompt for Gemini
encrypted
Enter a prompt for Gemini
encrypted
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22294
|
|
22293
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
LLM API Pricing Comparison & Cost Guide (May 2026)
LLM API Pricing Comparison & Cost Guide (May 2026)
Close tab
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
AI Chat settings
Close
WORK, Google Account: [EMAIL]
Main menu
New Chat
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected. Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
You said
I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected.
Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
Expand
Listen
Show thinking
Gemini said
Gemini said
Here is a summary of the changes in the provided code diff:
AI Call Scoring Additions
AI Call Scoring Additions
Pre-computed Scores:
Added strict instructions to treat the
ai_call_score
as pre-computed data. The system must interpret and summarize the provided scores rather than inventing or recalculating them.
Context Breakdown:
*
Short Context:
Now displays the
AI Scorecard
name and the overall
AI Score
(the average of per-rule scores).
Full Context:
Details the
ai_call_score
object, breaking down individual rules. Each rule includes a title, prompt, a 1–5 score, a brief justification, and up to three timestamped speaker references (MM:SS).
Application Rules:
Instructs the system to use these scores for coaching summaries, trends, and comparisons, but dictates that it must still rely on the actual transcript for direct quotes.
Grammar and Formatting Cleanup
Grammar and Formatting Cleanup...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22293
|
|
22292
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
LLM API Pricing Comparison & Cost Guide (May 2026)
LLM API Pricing Comparison & Cost Guide (May 2026)
Close tab
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
AI Chat settings
Close
WORK, Google Account: [EMAIL]
Main menu
New Chat
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected. Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
You said
I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected.
Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy....
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22292
|
|
22291
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
LLM API Pricing Comparison & Cost Guide (May 2026)
LLM API Pricing Comparison & Cost Guide (May 2026)
Close tab
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
AI Chat settings
Close
WORK, Google Account: [EMAIL]
Main menu
New Chat
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected. Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
You said
I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected.
Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
Expand
Listen
Show thinking...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22291
|
|
22290
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
LLM API Pricing Comparison & Cost Guide (May 2026)
LLM API Pricing Comparison & Cost Guide (May 2026)
Close tab
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
AI Chat settings
Close
WORK, Google Account: [EMAIL]
Main menu
New Chat
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected. Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
You said
I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected.
Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
Expand
Listen
Show thinking
Gemini said
Gemini said
Here is a summary of the changes in the provided code diff:
AI Call Scoring Additions
AI Call Scoring Additions
Pre-computed Scores:
Added strict instructions to treat the
ai_call_score
as pre-computed data. The system must interpret and summarize the provided scores rather than inventing or recalculating them.
Context Breakdown:
*
Short Context:
Now displays the
AI Scorecard
name and the overall
AI Score
(the average of per-rule scores).
Full Context:
Details the
ai_call_score
object, breaking down individual rules. Each rule includes a title, prompt, a 1–5 score, a brief justification, and up to three timestamped speaker references (MM:SS).
Application Rules:
Instructs the system to use these scores for coaching summaries, trends, and comparisons, but dictates that it must still rely on the actual transcript for direct quotes....
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22290
|
|
22289
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22289
|
|
22288
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
LLM API Pricing Comparison & Cost Guide (May 2026)
LLM API Pricing Comparison & Cost Guide (May 2026)
Close tab
New Tab
Customize sidebar...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22288
|
|
22287
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
LLM API Pricing Comparison & Cost Guide (May 2026)
LLM API Pricing Comparison & Cost Guide (May 2026)
Close tab
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
AI Chat settings
Close...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22287
|
|
22286
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
LLM API Pricing Comparison & Cost Guide (May 2026)
LLM API Pricing Comparison & Cost Guide (May 2026)
Close tab
New Tab
Customize sidebar...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22286
|
|
22285
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22285
|
|
22284
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
LLM API Pricing Comparison & Cost Guide (May 2026)
LLM API Pricing Comparison & Cost Guide (May 2026)
Close tab
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
AI Chat settings
Close
WORK, Google Account: [EMAIL]
Main menu
New Chat
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected. Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
You said
I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected.
Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
Expand
Listen
Show thinking
Gemini said
Gemini said
Here is a summary of the changes in the provided code diff:
AI Call Scoring Additions
AI Call Scoring Additions
Pre-computed Scores:
Added strict instructions to treat the
ai_call_score
as pre-computed data. The system must interpret and summarize the provided scores rather than inventing or recalculating them.
Context Breakdown:
*
Short Context:
Now displays the
AI Scorecard
name and the overall
AI Score
(the average of per-rule scores).
Full Context:
Details the
ai_call_score
object, breaking down individual rules. Each rule includes a title, prompt, a 1–5 score, a brief justification, and up to three timestamped speaker references (MM:SS).
Application Rules:
Instructs the system to use these scores for coaching summaries, trends, and comparisons, but dictates that it must still rely on the actual transcript for direct quotes.
Grammar and Formatting Cleanup
Grammar and Formatting Cleanup
Typo Corrections:
Fixed minor grammatical errors, such as changing "contexts" to "context" and "utlizes" to "utilizes".
String Formatting:
Cleaned up the markdown link instructions by removing trailing newline and quotation artifacts (
\n"
) from the text strings.
Good response
Bad response
Share & export
Copy
Show more options
Copy prompt
Edit
You said are there some issues and bottlenecks
You said
are there some issues and bottlenecks
Listen
Show thinking
Gemini said
Gemini said
Looking closely at the system instructions in the diff, there are definitely a few potential prompt engineering issues and bottlenecks introduced by these additions. When you ask a Large Language Model (LLM) to juggle large transcripts alongside complex JSON scoring objects, it creates specific friction points.
Here is a breakdown of the potential issues and bottlenecks based on the changes:
1. Token Consumption and Context Bloat (Bottleneck)
1. Token Consumption and Context Bloat (Bottleneck)
Massive Payload Size:
By injecting the full
ai_call_score
object into the context (which includes rule names, prompts, scores, text justifications, and up to three timestamps
per rule
), the token count per call will skyrocket.
Context Window Limits:
The prompt states:
"The full call context includes all calls data available..."
If a user filters for 5 or 10 calls, injecting the transcripts
plus
these extensive AI scoring arrays could easily hit the model's maximum context window, leading to truncated data or degraded recall (the "lost in the middle" effect).
2. LLM Instruction Conflicts (Issue)
2. LLM Instruction Conflicts (Issue)
Pre-computed vs. Raw Transcript:
The prompt explicitly instructs the model:
"
Do not
invent, override, or recalculate scores"
but later says,
"For
what was actually said
, still rely on the
transcript
."
This creates a cognitive conflict for the LLM. If the raw transcript contradicts the pre-computed
justification
, the LLM might struggle with which source of truth to prioritize, potentially leading to hallucinations or contradictory summaries.
Prompt Complexity:
The more rules you add about
how
to read JSON formatting and
what
not to do, the less attention the model pays to the actual user query. This is a common bottleneck in prompt engineering known as instruction bloat.
3. Edge Cases in Formatting (Issue)
3. Edge Cases in Formatting (Issue)
Timestamp Limitations:
The instructions strictly define timestamps as
MM:SS
. This works fine for standard calls, but for longer meetings (over an hour), it either forces an awkward format (e.g.,
85:30
) or breaks if the system outputs
HH:MM:SS
.
Decimal vs. Whole Numbers:
The prompt specifies that the overall AI Score might be a decimal (average), but the individual rule score is a "Whole number
1–5
". If the upstream pipeline accidentally passes a decimal for a rule score, the LLM might get confused based on these rigid instructions.
How are you currently handling pagination or chunking for these calls—are you limiting the number of calls that can be passed into the full context at once to avoid token limits?
Good response
Bad response
Redo
Share & export
Copy
Show more options
Enter a prompt for Gemini
encrypted
Enter a prompt for Gemini
encrypted
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Your Jiminny chats aren’t used to improve our models. Gemini is AI. It can make mistakes, so double check it.
Your privacy & Gemini Opens in a new window
Your privacy & Gemini
Opens in a new window
Summarize page
Summarize page
NEW:
Real-Time Usage Tracking for AI Agents — track Claude Code, Kimi, Codex & more.
Try it free →
Try it free →
CostGoat Logo CostGoat...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22284
|
|
22283
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
LLM API Pricing Comparison & Cost Guide (May 2026)
LLM API Pricing Comparison & Cost Guide (May 2026)
Close tab
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
AI Chat settings
Close
WORK, Google Account: [EMAIL]
Main menu
New Chat
Open menu for conversation actions....
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22283
|
|
22282
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
LLM API Pricing Comparison & Cost Guide (May 2026)
LLM API Pricing Comparison & Cost Guide (May 2026)
Close tab
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
AI Chat settings
Close
WORK, Google Account: [EMAIL]
Main menu
New Chat
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected. Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
You said
I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected.
Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
Expand
Listen
Show thinking
Gemini said
Gemini said
Here is a summary of the changes in the provided code diff:
AI Call Scoring Additions
AI Call Scoring Additions
Pre-computed Scores:
Added strict instructions to treat the
ai_call_score
as pre-computed data. The system must interpret and summarize the provided scores rather than inventing or recalculating them.
Context Breakdown:
*
Short Context:
Now displays the
AI Scorecard
name and the overall
AI Score
(the average of per-rule scores).
Full Context:
Details the
ai_call_score
object, breaking down individual rules. Each rule includes a title, prompt, a 1–5 score, a brief justification, and up to three timestamped speaker references (MM:SS)....
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22282
|
|
22281
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22281
|
|
22280
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
LLM API Pricing Comparison & Cost Guide (May 2026)
LLM API Pricing Comparison & Cost Guide (May 2026)
Close tab
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
AI Chat settings
Close
WORK, Google Account: [EMAIL]
Main menu
New Chat
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected. Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
You said
I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected.
Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
Expand
Listen
Show thinking
Gemini said
Gemini said
Here is a summary of the changes in the provided code diff:
AI Call Scoring Additions
AI Call Scoring Additions
Pre-computed Scores:
Added strict instructions to treat the
ai_call_score
as pre-computed data. The system must interpret and summarize the provided scores rather than inventing or recalculating them.
Context Breakdown:
*
Short Context:
Now displays the
AI Scorecard
name and the overall
AI Score
(the average of per-rule scores).
Full Context:
Details the
ai_call_score
object, breaking down individual rules. Each rule includes a title, prompt, a 1–5 score, a brief justification, and up to three timestamped speaker references (MM:SS)....
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22280
|
|
22279
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
LLM API Pricing Comparison & Cost Guide (May 2026)
LLM API Pricing Comparison & Cost Guide (May 2026)
Close tab
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
AI Chat settings
Close
WORK, Google Account: [EMAIL]
Main menu
New Chat
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22279
|
|
22278
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22278
|
|
22277
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
LLM API Pricing Comparison & Cost Guide (May 2026)...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22277
|
|
22276
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22276
|
|
22275
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
LLM API Pricing Comparison & Cost Guide (May 2026)
LLM API Pricing Comparison & Cost Guide (May 2026)
Close tab
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
AI Chat settings
Close
WORK, Google Account: [EMAIL]
Main menu
New Chat
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected. Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
You said
I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected.
Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
Expand
Listen
Show thinking
Gemini said
Gemini said
Here is a summary of the changes in the provided code diff:
AI Call Scoring Additions
AI Call Scoring Additions
Pre-computed Scores:
Added strict instructions to treat the
ai_call_score
as pre-computed data. The system must interpret and summarize the provided scores rather than inventing or recalculating them.
Context Breakdown:
*
Short Context:
Now displays the
AI Scorecard
name and the overall
AI Score
(the average of per-rule scores).
Full Context:
Details the
ai_call_score
object, breaking down individual rules. Each rule includes a title, prompt, a 1–5 score, a brief justification, and up to three timestamped speaker references (MM:SS).
Application Rules:
Instructs the system to use these scores for coaching summaries, trends, and comparisons, but dictates that it must still rely on the actual transcript for direct quotes.
Grammar and Formatting Cleanup
Grammar and Formatting Cleanup...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22275
|
|
22274
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
LLM API Pricing Comparison & Cost Guide (May 2026)
LLM API Pricing Comparison & Cost Guide (May 2026)
Close tab
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
AI Chat settings...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22274
|
|
22273
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
LLM API Pricing Comparison & Cost Guide (May 2026)
LLM API Pricing Comparison & Cost Guide (May 2026)
Close tab
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
AI Chat settings
Close
WORK, Google Account: [EMAIL]
Main menu
New Chat
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22273
|
|
22272
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
LLM API Pricing Comparison & Cost Guide (May 2026)
LLM API Pricing Comparison & Cost Guide (May 2026)
Close tab
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
AI Chat settings
Close
WORK, Google Account: [EMAIL]...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22272
|
|
22271
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
LLM API Pricing Comparison & Cost Guide (May 2026)
LLM API Pricing Comparison & Cost Guide (May 2026)
Close tab
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
AI Chat settings
Close
WORK, Google Account: [EMAIL]...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22271
|
|
22270
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22270
|
|
22269
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22269
|
|
22268
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22268
|
|
22267
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22267
|
|
22266
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22266
|
|
22265
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22265
|
|
22264
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22264
|
|
22263
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22263
|
|
22262
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
LLM API Pricing Comparison & Cost Guide (May 2026)
LLM API Pricing Comparison & Cost Guide (May 2026)
Close tab
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
AI Chat settings
Close
WORK, Google Account: [EMAIL]
Main menu
New Chat
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected. Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
You said
I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected.
Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
Expand...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22262
|
|
22261
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22261
|
|
22260
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
LLM API Pricing Comparison & Cost Guide (May 2026)
LLM API Pricing Comparison & Cost Guide (May 2026)
Close tab
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
AI Chat settings
Close
WORK, Google Account: [EMAIL]
Main menu
New Chat
Open menu for conversation actions....
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22260
|
|
22259
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22259
|
|
22258
|
New Tab
New Tab
FirefoxFileEditViewHistoryBookmark New Tab
New Tab
FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp(allDaily - Platform • 8 m left)100% <28•Tue 12 May 9:57:46meet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.com9Nikolay Yankov (Presenting, annotating)ChromeFileViewHistoryTabWindowHelp1 SeX PrNnnyCo4 At:https://jiminny.atlassian.net/jira/software/c/projects/JY/boards/37?selectedlssue=JY-20625E::© AWS|X) SSH Home | Salesforce |Platform TeamQ SearJy-20739 / Q JY-20625READY FI(POC)Jiminny MCP ConnectorDescriptionCustomers are starting to use Al tool (like Claude and GPT) to connect the information from all f their platform into one place.Which they then use to interrogate and perform different analysis on their data. We want to create a Jiminny MCP which will|enable them to connect their Jiminny data to Claude/GPT.• create a POC to demonstrate the approach• determine form where the data needs to be fotched - long term we want to fetch everything from Elastic Search but inorder to release it faster we can consider a tem brary mixed approach with the DB• we will use php/laravel for the implementation• determine what the authentication needs to be (keep in mind requirement 1 and 7)• outline any issues/blockers that we need to address• the approach/findings should be confirmed with Stefka and Galya• product requirements -https://imanny.atfassian.net/wiki/spaces/PROD/pages/37282447371Jiminry+MCP-Connectorот1Subtasks33% DoneWorkPriorityStory R..Assig...9:57 AM | Daily - Platform*8 Jin*ClC м | E3 мDatadog* Claude |•Jir8 Jin3 CircleciA Sentry8• Tue 12 May 9:57A(л|+D All BookmarksGalya DimitrovaStefka Stoyanovain Prootess4• DetailsAssigneeNikolay NIkolovAssign to meReporter2 Galya DimitrovaComponentsPiattormSub-ProductAdd optionsLabelsNoneStory point estimateNoneStory PointsXE Improve Spike4 othersNikolay Nikolov:meet.google.comNikolay Yankov (You, presenti..+7Lukas Kovalik11:53...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22258
|
|
22257
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app...
|
Firefox
|
LLM API Pricing Comparison & Cost Guide (May 2 LLM API Pricing Comparison & Cost Guide (May 2026) — Work...
|
costgoat.com/compare/llm-api
|
22257
|
|
22256
|
HomeActivityFllesLaterMoreFirefoxMIStoMJiminny... HomeActivityFllesLaterMoreFirefoxMIStoMJiminny... ~# curiosity lab# engineering# general# jiminny-bg# platform-tickets# product launches# random# releases# sofia-office# support# thank-yous# the_people_of jimi...^? Direct messages. Galya Dimitrova MA. Aneliya Angelova @f Petko Kashinski@ Stefka Stoyanova€. Vasil VasilevCP. Nikolay Ivanov(3) Aneliva Angelova…Stoyan Tanev. Vese. Lukas Kovali... M o::: Apps& Toast4" Jira Cloud(m) Google Cale...© BadKeywordsQueryExcer( ConfiqurationExceotion.o© CrmException.php-crmUndateSycention.ohr© DatabaseException.phpE DealRisksEycention.nhn© DomainException.phpC EmailActivitvimnortEycen© ErrorDownloadingEmptyF) ErrorDownloadina Sile Syci© FileNotFoundException.pl© FileSystemException.php© Handler.php(@ HttnRodDoauoctEycontinA HttnRaNDebookmarksProtllesToolsWindow& # engineering• Messages©Canvas20260507)Help8 24e FilesMoreatecfix/npm-circlec APP 9-10 ANO 2 PRs with v Pnerability fixes are ready forreviewPlease take a look at the code and confirmthat everything works properly on yourlocal machine or on a planet environmentPull requests (jiminny/app)• 412049 hx cecurimv: comnoserdependency updates - 2026-05-07(secfix/composer-20260507)• #12048 fix(security): npm dependencyupdates - 2026-05-07 (secfix/npm-20260507)llan Kvuchukov 9.50AMClaude's limits are getang ridiculous. whatare you using from OpenAI? GPT-5.3Codey?e A 5 replies Last reply todayat 9-5...Message #engineering+ Aatroller.onpSautomatNew Tabe Jy 20820 es reindex stream mode[UY-20725] [HubSpot] Optimise CF@ JY-20725 add HS rate limit handlilO'Pipelines - jiminny/app• Pull requests • jiminny/appWY-207731 User Pilot not receivin@JY-20773 fix user pilot tracking ofrNY-20776 Automated report - seTypeError: LeaguelFlysystem|FilesA TypeError: League\Flysystem|FilesPlatform Sprint 3 02 - Platform TeJY-20361: Add call scores in P. Xsimonw/lim-prices: Prices of va X+ New Tab© github.com/simc~ Google Geminiintroduced by these additions. When you ask aLarge Language Model (LLM) to juggle largetranscripts alongside complex JsON scoringobjects, it creates specific friction points.Here is a breakdown of the potential issues andbottlenecks based on the changes:1. Token Consumption and Context Bloat(Bottleneck)• Massive Payload Size: By injecting thefull ai_call_score object into thecontext (which includes rule names,prompts, scores, text justifications, andup to three timestamps per rule), thetoken count per call will skyrocket.• Context Window Limits: The promptstates: "The full call context includes allcalls data available..." If a user filters for 5or 10 calls, injecting the transcripts plusthese extensive Al scoring arrays couldeasily hit the model's maximum contextwindow, leading to truncated data ordegraded recall (the "lost in the middle"effect).? 11 M Inctruction Conflicte (Iccme)• Pre-computed vs. Raw Transcript: Theprompt explicitly instructs the model: "Donot invent, override, or recalculatescores" but later says, "For what was• Enter a prompt for GeminiPro vYour Jiminny chats aren't used to improveJlrcan mite micnkes colcolliale chocktYottr orivaevdoSummarize pagea<40 hil © I Daily - Platform - 8mleft A 100% C/7 &• Tue 12 May 9:57:42OO READMEExample:"orices":"id": "amazon-nova-lite","vendor":amazon","name": "Amazon Nova Lite","input": 0.06,"output":0.24,"input_cached": null,"from_date": null,"to_date": null"id": "amazon-nova-micro","Amazon Nova Micro","1ndut": 0.035."output": 0.14,"input_cached": null,"from_date": null,"to date": nuluHow the data files workThe pricing data is maintained in individual JSON files in the data/ directory, with one file per vendor (e.g., data/anthropic.json, data/openal.json )•Each vendor file has the following structure:"vendor": "anthropic","id": "claude-3.7-sonnet","name": "Claude 3.7 Sonnet","orice history"."input": 3,"output": 15,"inout cachedi: null."from_date": null,"to_date": null...
|
Firefox
|
simonw/llm-prices: Prices of various LLMs — Work
|
NULL
|
22256
|
|
22255
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp(allDaily - Platform • 8 m left)100% <2Tue 12 May 9:57:42meet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comNikolay Yankov (Presenting, annotating)ChromeFileViewHistory1 SeProfilesTabWindowHelpPrNnry4 AtAt:https://jiminny.atlassian.net/jira/software/c/projects/JY/boards/37© AWS|X) SSH• Home | Salesforce |Platform TeamQ Search board•.Epic vType vQuick filters vREADY FOR DEVINDEV 3CODE REVIEW 2BLOCKEDUpgrade to PHP 8.5PHP 8.5 UPGRADEIn Dev3 П •••=AJ Panorama forCall Scoring in ODAUTOMATED AI SCORINGCode Review2.5 1 =E JY-18091|[ JY-20361|SAI Review - Q1 -Summary/Actionitems/Key PointsGROWTH - MAINTAIN OU...In Dev20.000=(HubSpot] OptimiseCRM rematching ondelete hubspot….PLATFORM STABILITYCode Review[ JY-20566XỐ JY-20725[POC)Jiminny MCPConnectorJIMINNY MCP CONNECTORIn Progress+ Create10 1 •.••=@JY-20625*JinClС мс3 мс$8• Tue 12 May 9:57Jin8 Jie1[л|+Datadog* Claude|3 CircleciSentryD All BookmarksComplete sprintGroup: Queries|QA 2PO ACCEPTANCEDEPLOY 9Smart Instant|Nudge Pre-filteringCOST-EFFECTIVE AND FA...Ready for QA|15 П =AI Reports > Emptypage design andpromotionAJ REPORTSDeployed1 П [PASSWORD_DOTS]=[ JY-20493|Д JY-20372Sync opportunitieswithout a localowner (user_id is..PLATFORM STABILITYIn QAn9 JY-20352Grok via AzureMAINTENANCEDeployed• •••.=Д JY-20726:meet.google.comNikolay Yankov (You, presenti..+7Galya DimitrovaNikolay Nikolov9Stefka Stoyanova4 others9:57 AM | Daily - PlatformLukas Kovalik11:49...
|
Firefox
|
simonw/llm-prices: Prices of various LLMs — Work
|
NULL
|
22255
|
|
22254
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
simonw/llm-prices: Prices of various LLMs
simonw/llm-prices: Prices of various LLMs
Close tab
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
AI Chat settings
Close
WORK, Google Account: [EMAIL]...
|
Firefox
|
simonw/llm-prices: Prices of various LLMs — Work
|
github.com/simonw/llm-prices
|
22254
|
|
22253
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
simonw/llm-prices: Prices of various LLMs
simonw/llm-prices: Prices of various LLMs
Close tab
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
AI Chat settings
Close
WORK, Google Account: [EMAIL]
Main menu
New Chat
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected. Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
You said
I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected.
Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
Expand
Listen
Show thinking
Gemini said
Gemini said
Here is a summary of the changes in the provided code diff:
AI Call Scoring Additions
AI Call Scoring Additions
Pre-computed Scores:
Added strict instructions to treat the
ai_call_score
as pre-computed data. The system must interpret and summarize the provided scores rather than inventing or recalculating them.
Context Breakdown:
*
Short Context:
Now displays the
AI Scorecard
name and the overall
AI Score
(the average of per-rule scores).
Full Context:
Details the
ai_call_score
object, breaking down individual rules. Each rule includes a title, prompt, a 1–5 score, a brief justification, and up to three timestamped speaker references (MM:SS).
Application Rules:
Instructs the system to use these scores for coaching summaries, trends, and comparisons, but dictates that it must still rely on the actual transcript for direct quotes....
|
Firefox
|
simonw/llm-prices: Prices of various LLMs — Work
|
github.com/simonw/llm-prices
|
22253
|
|
22252
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
simonw/llm-prices: Prices of various LLMs
simonw/llm-prices: Prices of various LLMs
Close tab
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
AI Chat settings
Close
WORK, Google Account: [EMAIL]
Main menu
New Chat
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected. Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
You said
I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected.
Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
Expand...
|
Firefox
|
simonw/llm-prices: Prices of various LLMs — Work
|
github.com/simonw/llm-prices
|
22252
|
|
22251
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
JY-20773 fix user pilot tracking ofr automated report generated by LakyLak · Pull Request #12024 · jiminny/app
[JY-20776] Automated report - sentry - Jira
[JY-20776] Automated report - sentry - Jira
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 3 Q2 - Platform Team - Scrum Board - Jira
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
JY-20361: Add call scores in Panorama by steliyan-g · Pull Request #507 · jiminny/prophet
simonw/llm-prices: Prices of various LLMs
simonw/llm-prices: Prices of various LLMs
Close tab
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
AI Chat settings
Close
WORK, Google Account: [EMAIL]
Main menu
New Chat
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected. Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
You said
I’m on page “<tabTitle>JY-20361: Add call scores in Panorama by steliyan-</tabTitle>” with “<selection>@@ -4,7 +4,7 @@ Today is {date_today}.445System instructions:5System instructions:6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.6- You must answer using markdown. Do not use html tags in your response even if requested by the user's question.7-- The contexts includes data for call shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.7+- The context includes data for calls shortlisted through user-applied filters. Note that the calls might not relate to the same deal or not even be by the same sales rep.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.8 - The full call context includes all calls data available while the short call context contains only an overview of the calls that are analysed. Refer to the short call context for quick reference and to see the overall picture.9- The calls are ordered in chronological order. 9- The calls are ordered in chronological order. 10- Here’s how to use the call context:10- Here’s how to use the call context:@@ -16,6 +16,15 @@ System instructions:16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.16 - Frame answers with awareness of the company’s ICP, deal cycle, and sales motion.17 - Evaluate statements or objections based on how the team operates and what success looks like.17 - Evaluate statements or objections based on how the team operates and what success looks like.18 - Position responses in light of known competitors and market dynamics.18 - Position responses in light of known competitors and market dynamics.19+ - AI call score (`ai_call_score` in the full call JSON): When present, treat it as **pre-computed** output from your team’s AI call-scoring pipeline (the same kind of scoring as the `/call/ai-call-scoring` endpoint). **Do not** invent, override, or recalculate scores; interpret and summarize what is given.20+ - **Short call context:** **AI Scorecard** is the name of the scorecard applied to that call; **AI Score** is the **overall** score for that scorecard (the average of its per-rule scores, possibly shown as a decimal).21+ - **Full call context:** The `ai_call_score` object may include `ai_scorecard_name`, `score` (overall for that scorecard), and `ai_scorecard_rules`. For each rule when listed:22+ - `rule_name`: Title of the criterion.23+ - `rule_prompt`: The criterion text that was evaluated.24+ - `score`: Whole number **1–5** measuring how well the call satisfied that criterion against `rule_prompt` (1 = no evidence / not discussed or contrary; 5 = strong, clear evidence on the call).25+ - `justification`: Short rationale grounded in what happened on the call.26+ - `justification_timestamps`: Up to three entries with speaker **name** and **timestamp** (MM:SS in the recording) highlighting where the justification is supported.27+ - Use scores for coaching summaries, trends across calls, or quick comparisons when relevant. For **what was actually said**, still rely on the **transcript** (you may cross-reference rule timestamps when helpful).19- Use the Message History to:28- Use the Message History to:20 - Maintain continuity if the current question refers to previous exchanges.29 - Maintain continuity if the current question refers to previous exchanges.21 - Clarify or resolve ambiguities if the question depends on prior messages.30 - Clarify or resolve ambiguities if the question depends on prior messages.@@ -28,10 +37,10 @@ System instructions:28 - All factual claims must be supported by one or more references to relevant calls.37 - All factual claims must be supported by one or more references to relevant calls.29 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.38 - Use Markdown link syntax ([link text](URL)) and place links inline within sentences. Do not use footnotes, reference sections, or bare URLs. Integrate the reference links directly within the relevant parts of your response, rather than in a separate section.30 - Use markdown links in the format [link text](/playback/{{call_id}})39 - Use markdown links in the format [link text](/playback/{{call_id}})31- - Use descriptive link that utlizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.\n"40+ - Use descriptive link text that utilizes the call name. Do not use call time stamps in the link text even if the link itself contains a time stamp, e.g. use 'Call Name' instead of 'Call Name at 10:00'. Never use call ids as link text.32- - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)\n"41+ - Good example of link text: [Call Name](/playback/1234567890?apFrom=123)33- - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)\n"42+ - Bad example of link text: [Call Name at 12:34](/playback/1234567890?apFrom=123) (do not use call time stamps in the link text)34- - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)\n\n"43+ - Bad example of links: [Call Name on November 12, 2025](/playback/1234567890?apFrom=123) (do not use dates in the link text)35 - You might back your statements with examples from the provided call transcripts in addition to the reference links.44 - You might back your statements with examples from the provided call transcripts in addition to the reference links.36- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.45- Be specific. Use names of accounts, clients and persons involved. Don't just say "one client" or "a client"! If no account is available, use the call title as a reference.37- If the question or context is unclear, request clarification or highlight ambiguities.46- If the question or context is unclear, request clarification or highlight ambiguities.</selection>” selected.
Please summarize the selection using precise and concise language. Use headers and bulleted lists in the summary, to make it scannable. Maintain the meaning and factual accuracy.
Expand
Listen
Show thinking
Gemini said
Gemini said
Here is a summary of the changes in the provided code diff:
AI Call Scoring Additions
AI Call Scoring Additions
Pre-computed Scores:
Added strict instructions to treat the
ai_call_score
as pre-computed data. The system must interpret and summarize the provided scores rather than inventing or recalculating them.
Context Breakdown:
*
Short Context:
Now displays the
AI Scorecard
name and the overall
AI Score
(the average of per-rule scores).
Full Context:
Details the
ai_call_score
object, breaking down individual rules. Each rule includes a title, prompt, a 1–5 score, a brief justification, and up to three timestamped speaker references (MM:SS).
Application Rules:
Instructs the system to use these scores for coaching summaries, trends, and comparisons, but dictates that it must still rely on the actual transcript for direct quotes.
Grammar and Formatting Cleanup
Grammar and Formatting Cleanup
Typo Corrections:
Fixed minor grammatical errors, such as changing "contexts" to "context" and "utlizes" to "utilizes".
String Formatting:
Cleaned up the markdown link instructions by removing trailing newline and quotation artifacts (
\n"
) from the text strings.
Good response
Bad response
Share & export
Copy
Show more options
Copy prompt
Edit
You said are there some issues and bottlenecks
You said
are there some issues and bottlenecks...
|
Firefox
|
simonw/llm-prices: Prices of various LLMs — Work
|
github.com/simonw/llm-prices
|
22251
|
|
22250
|
FirefoxFileEditViewHistoryBookmarksProfilesToolsWi FirefoxFileEditViewHistoryBookmarksProfilesToolsWindowHelp(allDaily - Platform • 8 m left)100% <2Tue 12 May 9:57:27meet.google.com/mie-gawc-dsi?authuser=lukas.kovalik%40jiminny.comNikolay Yankov (Presenting, annotating)ChromeFileViewHistory19 SeTabWindowHelpNnry4 AtAt:https://jiminny.atlassian.net/jira/software/c/projects/JY/boards/37© AWS|X) SSH• Home | Salesforce |Platform TeamQ Search board03Epic vType vQuick filters vREADY FOR DEVINDEV 3CODE REVIEW 2BLOCKEDUpgrade to PHP 8.5PHP 8.5 UPGRADEIn Dev3 П •••=AJ Panorama forCall Scoring in ODAUTOMATED AI SCORINGCode Review2.5 1 =E JY-18091|[ JY-20361|SAI Review - Q1 -Summary/Actionitems/Key PointsGROWTH - MAINTAIN OU...In Dev(HubSpot] OptimiseCRM rematching ondelete hubspot…PLATFORM STABILITYCode Review2 @ .00=.[ JY-20566X* JY-20725[POC)Jiminny MCPConnectorJIMINNY MCP CONNECTORIn Progress+ Create10 1 •.••=*@JY-20625*8• Tue 12 May 9:57• Jin * ClС мс.8 мсJir8 Jirlai|+Datadog* Claude|3 CircleciSentry0 All Bookmarks |Complete sprintGroup: Queries|QA 2PO ACCEPTANCEDEPLOY 9Smart InstantNudge Pre-filteringCOST-EFFECTIVE AND FA...Ready for QA|15 П =AI Reports > Emptypage design andpromotionAJ REPORTSDeployed1 1 [PASSWORD_DOTS]=[ JY-20493|Д JY-20372Sync opportunitieswithout a localowner (user_id is…PLATFORM STABILITYIn QAGrok via AzureMAINTENANCEDeployed••00=.Д JY-207269 JY-20352t:meet.google.comNikolay Yankov (You, presenti..0+7Galya DimitrovaNikolay Nikolov9Stefka Stoyanova4 others9:57 AM | Daily - PlatformLukas Kovalik11:34...
|
Firefox
|
LLM pricing overview with the most actual prices - LLM pricing overview with the most actual prices - Google Search — Work...
|
NULL
|
22250
|
|
22249
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app...
|
Firefox
|
LLM pricing overview with the most actual prices - LLM pricing overview with the most actual prices - Google Search — Work...
|
NULL
|
22249
|
|
22248
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app
Pull requests · jiminny/app
[JY-20773] User Pilot not receiving events on report generated - Jira...
|
Firefox
|
LLM pricing overview with the most actual prices - LLM pricing overview with the most actual prices - Google Search — Work...
|
NULL
|
22248
|
|
22247
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
JY-20725 add HS rate limit handling on activities rematching by LakyLak · Pull Request #12066 · jiminny/app
Pipelines - jiminny/app
Pipelines - jiminny/app
Pull requests · jiminny/app...
|
Firefox
|
LLM API Pricing Comparison 2026: Every Major Model LLM API Pricing Comparison 2026: Every Major Model, Ranked by Cost | BenchLM.ai — Work...
|
NULL
|
22247
|
|
22246
|
New Tab
New Tab
Jy 20820 es reindex stream model h New Tab
New Tab
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
Jy 20820 es reindex stream model hydration by Vasil-Jiminny · Pull Request #12059 · jiminny/app
[JY-20725] [HubSpot] Optimise CRM rematching on delete hubspot accounts/contacts - Jira...
|
Firefox
|
LLM API Pricing Comparison 2026: Every Major Model LLM API Pricing Comparison 2026: Every Major Model, Ranked by Cost | BenchLM.ai — Work...
|
NULL
|
22246
|