Rank #9 of 9 in AI Assistants
Microsoft Copilot
Built-in AI assistantMicrosoft · commercial
vs ChatGPT
vs Claude
vs Gemini
vs Perplexity
vs Grok
vs Muse
vs Poke
vs MartinProducts
Microsoft, product by product →Microsoft ships more than one product — each judged line competes in its own arena on the same stories as everyone else.
| Line | Arena | Rank | PA Score | Agent-ready |
|---|---|---|---|---|
| Microsoft Copilotthis page | AI Assistants | #9/9 | 4/100 | 0/100 |
| Windows | Desktop OS | #3/5 | 9/100 | 15/100 |
| Microsoft Teams | Team Chat | #5/5 | 21/100 | 32/100 |
| AutoGen | Agent Frameworks & SDKs | #9/9 | 26/100 | 31/100 |
Not yet judged (1 — no arena where they compete): Visual Studio Code
Verified integrations
No integration evidence found in our corpus for this product yet — that means none was found, never that it doesn’t integrate.
By theme — the product's score on each story themeBy theme
Agenticness — how well agents can access and operate the productAgenticnessevidence →
How well agents can access and operate the product
Agents tasks — stories about agents tasks in this arenaAgents tasksevidence →
Stories about agents tasks in this arena
Apps devices — stories about apps devices in this arenaApps devicesevidence →
Stories about apps devices in this arena
Automation depth — how much of the product can run unattendedAutomation depthevidence →
How much of the product can run unattended
Connectors apps — stories about connectors apps in this arenaConnectors appsevidence →
Stories about connectors apps in this arena
Files analysis — stories about files analysis in this arenaFiles analysisevidence →
Stories about files analysis in this arena
Memory context — stories about memory context in this arenaMemory contextevidence →
Stories about memory context in this arena
Multimodal — stories about multimodal in this arenaMultimodalevidence →
Stories about multimodal in this arena
Openness — open source, data portability, and self-hosting storiesOpennessevidence →
Open source, data portability, and self-hosting stories
Privacy posture — data-handling and privacy storiesPrivacy postureevidence →
Data-handling and privacy stories
Research answers — stories about research answers in this arenaResearch answersevidence →
Stories about research answers in this arena
Trust controls — stories about trust controls in this arenaTrust controlsevidence →
Stories about trust controls in this arena
Story verdicts — every judged story with its evidenceStory verdicts
Follow the green: where the map greys out is where Microsoft Copilot stops today. ✓ full · ~ partial · ! disputed · — none · n/a not applicable.
Agenticness — how well agents can access and operate the productAgenticness
How well agents can access and operate the product
API surface
Drive the product through a documented public API
—0/10
Subscribe to events via webhooks
—0/10
Build against official SDKs
—0/10
Issue scoped/least-privilege API credentials for an agent
—–
Connect an agent via an official MCP server
n/an/a
Download a machine-readable API spec (OpenAPI or equivalent)
—0/10
Rely on versioned APIs with a documented deprecation policy
—0/10
Test against a sandbox environment without touching production data
n/an/a
Explore an interactive API reference with runnable examples
n/an/a
Docs for agents
Point an agent at llms.txt or agent-oriented docs
—0/10
Agentic features
Delegate tasks to a built-in AI assistant inside the product
~6/10
unlocks → NL commands · MCP client · AI insights
Operate the product with natural-language commands
!5/10
Plug MCP servers into this product so it can use their tools
—0/10
Get AI-generated insights and suggestions from my data inside the product
!5/10
Set up automations that run autonomously in the background
~4/10
Agents tasks — stories about agents tasks in this arenaAgents tasks
Stories about agents tasks in this arena
Apps devices — stories about apps devices in this arenaApps devices
Stories about apps devices in this arena
Automation depth — how much of the product can run unattendedAutomation depth
How much of the product can run unattended
Connectors apps — stories about connectors apps in this arenaConnectors apps
Stories about connectors apps in this arena
Files analysis — stories about files analysis in this arenaFiles analysis
Stories about files analysis in this arena
Have the assistant write and run code on my data to produce charts, computed answers, and downloadable files
~6/10
Have the assistant create and iteratively edit documents, presentations, and other files I can export
!4/10
Upload documents, spreadsheets, and PDFs and get accurate analysis of their contents
~6/10
Memory context — stories about memory context in this arenaMemory context
Stories about memory context in this arena
Multimodal — stories about multimodal in this arenaMultimodal
Stories about multimodal in this arena
Openness — open source, data portability, and self-hosting storiesOpenness
Open source, data portability, and self-hosting stories
Privacy posture — data-handling and privacy storiesPrivacy posture
Data-handling and privacy stories
Research answers — stories about research answers in this arenaResearch answers
Stories about research answers in this arena
Trust controls — stories about trust controls in this arenaTrust controls
Stories about trust controls in this arena
Sorted by importance (agentic first) (high → low) · 52/52 stories · click a row’s chevron for the rationale and evidence
Delegate tasks to a built-in AI assistant inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | partial | 6/10 | Xcommunity | |
Connect an agent via an official MCP server G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | n/a | 0/10 | ||
Drive the product through a documented public API G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | none | 0/10 | ||
Plug MCP servers into this product so it can use their tools G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | none | 0/10 | ||
Get AI-generated insights and suggestions from my data inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | disputed | 5/10 | Dcontradicted | |
Operate the product with natural-language commands G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | disputed | 5/10 | Dcontradicted | |
Set up automations that run autonomously in the background G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 4/10 | Cclaimed | |
Build against official SDKs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Download a machine-readable API spec (OpenAPI or equivalent) G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Point an agent at llms.txt or agent-oriented docs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Rely on versioned APIs with a documented deprecation policy G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Subscribe to events via webhooks G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Use an official CLI G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Explore an interactive API reference with runnable examples G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | n/a | untested | none yet | |
Issue scoped/least-privilege API credentials for an agent G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | untested | none yet | |
Run the product headlessly / in CI for automation G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | n/a | untested | none yet | |
Test against a sandbox environment without touching production data G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 1 | n/a | untested | none yet | |
Connect my cloud drive, email, and calendar so the assistant can search and use them in answers C Connectors | knowledge-worker | Connectors apps — stories about connectors apps in this arenaConnectors apps | 3 | full | 8/10 | Xcommunity | |
Control whether my conversations are used to train models C Data controls | knowledge-worker | Trust controls — stories about trust controls in this arenaTrust controls | 3 | partial | 6/10 | Xcommunity | |
Have the assistant operate a web browser on my behalf to research and complete tasks on websites C Agent mode | power-user | Agents tasks — stories about agents tasks in this arenaAgents tasks | 3 | partial | 6/10 | Cclaimed | |
Have the assistant remember relevant context from previous chats and apply it in new conversations C Memory | power-user | Memory context — stories about memory context in this arenaMemory context | 3 | partial | 6/10 | Cclaimed | |
Have the assistant write and run code on my data to produce charts, computed answers, and downloadable files C Analysis | power-user | Files analysis — stories about files analysis in this arenaFiles analysis | 3 | partial | 6/10 | Cclaimed | |
Prevent my data from being used to train AI models G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 3 | partial | 6/10 | Xcommunity | |
Upload documents, spreadsheets, and PDFs and get accurate analysis of their contents C Files | knowledge-worker | Files analysis — stories about files analysis in this arenaFiles analysis | 3 | partial | 6/10 | Xcommunity | |
Delegate a multi-step task that the assistant works on autonomously in the background and returns for my review C Agent mode | power-user | Agents tasks — stories about agents tasks in this arenaAgents tasks | 3 | partial | 5/10 | Cclaimed | |
Launch a deep research run that autonomously searches many sources and returns a cited report C Research | knowledge-worker | Research answers — stories about research answers in this arenaResearch answers | 3 | partial | 5/10 | Cclaimed | |
Export all of my data in open formats and leave G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | none | 0/10 | ||
Define rules that trigger actions automatically on events G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 3 | none | untested | none yet | |
Self-host the core product G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | none | untested | none yet | |
Get answers grounded in current web results with citations back to the sources C Research | knowledge-worker | Research answers — stories about research answers in this arenaResearch answers | 2 | full | 8/10 | Cclaimed | |
Control data retention and deletion G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | partial | 6/10 | Xcommunity | |
Have a natural, real-time voice conversation with the assistant C Voice | knowledge-worker | Multimodal — stories about multimodal in this arenaMultimodal | 2 | full | 6/10 | Cclaimed | |
Let the assistant see and operate applications on my computer to complete work C Agent mode | power-user | Agents tasks — stories about agents tasks in this arenaAgents tasks | 2 | partial | 6/10 | Xcommunity | |
Use full-featured official mobile apps for iOS and Android C Apps | knowledge-worker | Apps devices — stories about apps devices in this arenaApps devices | 2 | partial | 6/10 | Cclaimed | |
Opt out of telemetry and usage tracking G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | disputed | 5/10 | Dcontradicted | |
Share screenshots and photos and have the assistant accurately interpret what is in them C Images | knowledge-worker | Multimodal — stories about multimodal in this arenaMultimodal | 2 | partial | 5/10 | Cclaimed | |
Browse a directory of third-party apps and connectors and add them to the assistant C Connectors | power-user | Connectors apps — stories about connectors apps in this arenaConnectors apps | 2 | partial | 4/10 | Cclaimed | |
Have the assistant create and iteratively edit documents, presentations, and other files I can export G Artifacts | knowledge-worker | Files analysis — stories about files analysis in this arenaFiles analysis | 2 | disputed | 4/10 | Dcontradicted | |
Perform bulk operations across many items at once G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | partial | 3/10 | Xcommunity | |
Do everything through the API that I can do in the UI G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | none | 0/10 | ||
Generate and edit images from natural-language prompts C Images | knowledge-worker | Multimodal — stories about multimodal in this arenaMultimodal | 2 | none | 0/10 | ||
Organize related chats and files into a project or space that shares context and instructions C Projects | knowledge-worker | Memory context — stories about memory context in this arenaMemory context | 2 | none | 0/10 | ||
Read the product's source under an open license G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | none | 0/10 | ||
Schedule recurring or one-off tasks that run automatically and come back to me with results C Tasks | power-user | Agents tasks — stories about agents tasks in this arenaAgents tasks | 2 | none | 0/10 | ||
Use an official desktop app with OS-level shortcuts and access to what is on my screen C Apps | power-user | Apps devices — stories about apps devices in this arenaApps devices | 2 | none | 0/10 | ||
Build and share custom assistants with their own instructions and knowledge C Custom bots | power-user | Apps devices — stories about apps devices in this arenaApps devices | 2 | none | untested | none yet | |
Choose where my data is stored (region/residency) G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Manage members, permissions, and data policies for my organization's workspace C Admin | team-admin | Trust controls — stories about trust controls in this arenaTrust controls | 2 | none | untested | none yet | |
Schedule recurring jobs or workflows G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | none | untested | none yet | |
Set persistent custom instructions and preferences that shape every response C Memory | power-user | Memory context — stories about memory context in this arenaMemory context | 1 | partial | 5/10 | Cclaimed | |
Export my complete chat history and account data G Data controls | knowledge-worker | Trust controls — stories about trust controls in this arenaTrust controls | 1 | none | 0/10 | ||
Version, review, and roll back my automations G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 1 | none | untested | none yet |
Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 41 stories with headroom
What would move Microsoft Copilot’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.
Agenticness — how well agents can access and operate the productPlug MCP servers into this product so it can use their tools
nonemoves agent-readyimpact 45
The evidence pack describes Copilot connecting to first-party consumer services (OneDrive, Outlook.com, Google Drive/Gmail) via 'Copilot connectors,' but there is no mention of MCP (Model Context Protocol) server support or an ability for users to plug in arbitrary MCP tool servers.
Agenticness — how well agents can access and operate the productDrive the product through a documented public API
nonemoves agent-readyimpact 45
Missing: any public API documentation, SDK, or endpoint spec that lets developers programmatically invoke Copilot's capabilities.
Automation depth — how much of the product can run unattendedDefine rules that trigger actions automatically on events
nonemoves PA Scoreimpact 30
The evidence describes Copilot responding to prompts, browsing, summarizing, and connecting to services, but there is no mention of user-defined rules or triggers that fire actions automatically on events (e.g., 'when email arrives, do X' style automation).
Openness — open source, data portability, and self-hosting storiesExport all of my data in open formats and leave
nonemoves PA Scoreimpact 30
No evidence of a data export/portability feature or open-format export mechanism; docs only mention deleting conversation history, not exporting it, and probes for machine-readable docs/APIs 404.
Openness — open source, data portability, and self-hosting storiesSelf-host the core product
nonemoves PA Scoreimpact 30
Microsoft Copilot is a cloud-hosted SaaS product with no evidence of any self-hosted or on-premises deployment option; all documentation describes it as a hosted service (Copilot.com, Microsoft 365 cloud integration, Edge browser actions) with no self-hosting mechanism mentioned.
Agenticness — how well agents can access and operate the productPoint an agent at llms.txt or agent-oriented docs
nonemoves agent-readyimpact 30
Probes show no llms.txt, no markdown docs endpoint, and no OpenAPI spec for Microsoft Copilot's support site, and no evidence anywhere in the pack of agent-oriented documentation formats being offered.
Agenticness — how well agents can access and operate the productUse an official CLI
nonemoves agent-readyimpact 30
No evidence of an official CLI for Microsoft Copilot; all evidence covers chat, browser, and Office app integrations, with probes confirming no machine-readable API/CLI artifacts.
Agenticness — how well agents can access and operate the productIssue scoped/least-privilege API credentials for an agent
nonemoves agent-readyimpact 30
Missing: any mention of API keys, scoped tokens, permission scoping, or credential management for agent access.
Showing the top 8 of 41 — every none/partial verdict in the story verdicts table is headroom.
Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.
Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map3 surfaces · 24 covered stories
Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.
En us docs23 stories
- Get AI-generated insights and suggestions from my data inside the product
- Set up automations that run autonomously in the background
- Delegate tasks to a built-in AI assistant inside the product
- Operate the product with natural-language commands
- Delegate a multi-step task that the assistant works on autonomously in the background and returns for my review
- Have the assistant operate a web browser on my behalf to research and complete tasks on websites
- Let the assistant see and operate applications on my computer to complete work
- Use full-featured official mobile apps for iOS and Android
- Perform bulk operations across many items at once
- Browse a directory of third-party apps and connectors and add them to the assistant
- Connect my cloud drive, email, and calendar so the assistant can search and use them in answers
- Have the assistant write and run code on my data to produce charts, computed answers, and downloadable files
- Upload documents, spreadsheets, and PDFs and get accurate analysis of their contents
- Have the assistant remember relevant context from previous chats and apply it in new conversations
- Set persistent custom instructions and preferences that shape every response
- Share screenshots and photos and have the assistant accurately interpret what is in them
- Have a natural, real-time voice conversation with the assistant
- Prevent my data from being used to train AI models
- Control data retention and deletion
- Opt out of telemetry and usage tracking
- Launch a deep research run that autonomously searches many sources and returns a cited report
- Get answers grounded in current web results with citations back to the sources
- Control whether my conversations are used to train models
Hacker News12 stories
- Get AI-generated insights and suggestions from my data inside the product
- Delegate tasks to a built-in AI assistant inside the product
- Operate the product with natural-language commands
- Let the assistant see and operate applications on my computer to complete work
- Perform bulk operations across many items at once
- Connect my cloud drive, email, and calendar so the assistant can search and use them in answers
- Have the assistant create and iteratively edit documents, presentations, and other files I can export
- Upload documents, spreadsheets, and PDFs and get accurate analysis of their contents
- Prevent my data from being used to train AI models
- Control data retention and deletion
- Opt out of telemetry and usage tracking
- Control whether my conversations are used to train models
En us docs10 stories
- Get AI-generated insights and suggestions from my data inside the product
- Set up automations that run autonomously in the background
- Delegate tasks to a built-in AI assistant inside the product
- Operate the product with natural-language commands
- Perform bulk operations across many items at once
- Have the assistant write and run code on my data to produce charts, computed answers, and downloadable files
- Have the assistant create and iteratively edit documents, presentations, and other files I can export
- Upload documents, spreadsheets, and PDFs and get accurate analysis of their contents
- Launch a deep research run that autonomously searches many sources and returns a cited report
- Get answers grounded in current web results with citations back to the sources
Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence
2 of 16 testable claims verified · 3 contradicted → integrity 0/100
25 distinct capability claims found in Microsoft Copilot’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.
2
Verified
11
Unverified
3
Contradicted
7
Undersold
Verified (6)
“Copilot connects to OneDrive, Outlook.com, Google Drive, Gmail, Calendar and Contacts”
Connect my cloud drive, email, and calendar so the assistant can search and use them in answersfullproof ↗
“Users can find files with natural-language requests like 'find my budget spreadsheet'”
Connect my cloud drive, email, and calendar so the assistant can search and use them in answersfullproof ↗
“Users can search for specific file types like 'show me all PDFs' or Word docs on a topic”
Connect my cloud drive, email, and calendar so the assistant can search and use them in answersfullproof ↗
“Users can find specific emails via natural-language queries like 'show me emails from Sarah'”
Connect my cloud drive, email, and calendar so the assistant can search and use them in answersfullproof ↗
“Users can query their calendar with natural language, e.g. 'what's on my calendar for tomorrow'”
Connect my cloud drive, email, and calendar so the assistant can search and use them in answersfullproof ↗
“Users can opt out of having their conversation activity used for model training”
Control whether my conversations are used to train modelspartialproof ↗
Unverified (15)
“Copilot in Excel turns raw data into insights by analyzing attached spreadsheets via chat”
Have the assistant write and run code on my data to produce charts, computed answers, and downloadable filespartialproof ↗
“Researcher feature finds, synthesizes, and explains information faster”
Launch a deep research run that autonomously searches many sources and returns a cited reportpartialproof ↗
“Analyst feature helps turn raw numbers into insight through data analysis”
Have the assistant write and run code on my data to produce charts, computed answers, and downloadable filespartialproof ↗
“Browse with Copilot lets it perform actions directly in Microsoft Edge, like clicking, typing, and navigating tabs”
Have the assistant operate a web browser on my behalf to research and complete tasks on websitespartialproof ↗
“Cowork mode lets Copilot handle bigger multi-step tasks and deliver completed to-dos”
Delegate a multi-step task that the assistant works on autonomously in the background and returns for my reviewpartialproof ↗
“Browser actions run step-by-step visibly, letting users watch and take control at any time”
Have the assistant operate a web browser on my behalf to research and complete tasks on websitespartialproof ↗
“A copilot can automate repetitive tasks without requiring any coding”
Set up automations that run autonomously in the backgroundpartialproof ↗
“Copilot grounds responses in high-ranking web content with hyperlinked citations”
Get answers grounded in current web results with citations back to the sourcesfullproof ↗
“Copilot Voice mode lets users speak prompts and receive spoken audio responses”
Have a natural, real-time voice conversation with the assistantfullproof ↗
“Vision feature analyzes images, extracts insights from photos, and supports visual search”
Share screenshots and photos and have the assistant accurately interpret what is in thempartialproof ↗
“Copilot can run code to perform complex calculations and generate graphs”
Have the assistant write and run code on my data to produce charts, computed answers, and downloadable filespartialproof ↗
“Copilot can store specific facts users ask it to remember and use them in future responses”
Have the assistant remember relevant context from previous chats and apply it in new conversationspartialproof ↗
“Copilot pauses to ask for user approval before sensitive actions like purchases, bookings, or sending email”
Delegate a multi-step task that the assistant works on autonomously in the background and returns for my reviewpartialproof ↗
“Copilot connectors are available on Copilot.com and on Copilot Mobile apps for iOS and Android”
Browse a directory of third-party apps and connectors and add them to the assistantpartialproof ↗
“Copilot connectors are available on Copilot.com and on Copilot Mobile apps for iOS and Android”
Use full-featured official mobile apps for iOS and Androidpartialproof ↗
Contradicted (5)
“Copilot in Word can draft and iteratively edit documents from a prompt and uploaded notes”
Have the assistant create and iteratively edit documents, presentations, and other files I can exportdisputedproof ↗
“Copilot in PowerPoint can generate a full presentation from a prompt, outlining flow and visuals”
Have the assistant create and iteratively edit documents, presentations, and other files I can exportdisputedproof ↗
“Copilot in Outlook generates summaries of emails to help users stay organized”
Get AI-generated insights and suggestions from my data inside the productdisputedproof ↗
“Users can find files with natural-language requests like 'find my budget spreadsheet'”
Operate the product with natural-language commandsdisputedproof ↗
“Copilot can proactively suggest research topics based on past queries and stored memory”
Get AI-generated insights and suggestions from my data inside the productdisputedproof ↗
Undersold (7)
Delegate tasks to a built-in AI assistant inside the productpartialproof ↗
Let the assistant see and operate applications on my computer to complete workpartialproof ↗
Perform bulk operations across many items at oncepartialproof ↗
Upload documents, spreadsheets, and PDFs and get accurate analysis of their contentspartialproof ↗
Set persistent custom instructions and preferences that shape every responsepartialproof ↗
Prevent my data from being used to train AI modelspartialproof ↗
Claims outside our story set (1)
Real capability claims found in Microsoft Copilot’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.
“Users can choose between different leading AI models for different kinds of work”
source ↗
Business model
Free to use with a Microsoft account; Copilot Pro is a flat monthly subscription that adds priority model access and Copilot in Microsoft 365 apps.
pricing ↗Score trend
How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.
Flag
⚑ Flag a verdictThink a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.
For agents