Cursor vs GitHub Copilot

Agent access

1. ai-native userPoint an agent at llms.txt or agent-oriented docs

   weight 2 · round to GitHub Copilot
   Cursor—none0/10

   No evidence pack item mentions llms.txt, agent-oriented documentation ingestion, or a mechanism to point Cursor's agent at such files; only generic doc/MCP/tooling references are present. missing for 10: any mention of llms.txt support, crawling agent-oriented doc formats, or a documented feature for feeding external agent docs to Cursor's agent.

   ⚑ flag

   GitHub Copilot~partialprobed6/10

   Probes confirm docs.github.com serves an llms.txt file and a .md-formatted docs page, meaning an agent pointed at docs.github.com could consume agent-oriented docs directly; GitHub also documents MCP server usage for structured context. However, there's no evidence Copilot itself is documented to consume llms.txt as part of its own context-gathering workflow, nor first-party guidance recommending llms.txt for agent use. missing for 10: explicit product documentation instructing users/agents to point Copilot at llms.txt, and independent confirmation this integration is actually used in practice.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.github.com/llms.txt # GitHub Docs > GitHub is a developer platform for building, shipping, and mai…”
   • [probe] “PROBE docs-md: HTTP 200 at https://docs.github.com/copilot.md # GitHub Copilot documentation You can use GitHub Copilot to enhance your pro…”
   • [claimed-docs] “Connect MCP servers to Copilot Chat to share context from other applications.”
   • [claimed-docs] “Learn how to use the GitHub Model Context Protocol (MCP) server to interact with repositories, issues, pull requests, and other GitHub featu…”

   proof ↗⚑ flag

2. ai-native userRun the product headlessly / in CI for automation

   weight 2 · round to GitHub Copilot
   Cursor~partialprobed6/10

   Cursor ships an official CLI (cursor.com/cli, curl installer) and background/cloud agents that run 'on schedules or triggers' to build and fix software autonomously, which implies non-interactive/headless automation. However, there is no explicit documentation of CI pipeline integration, exit codes, or scripting examples for pipelines. Missing for 10: explicit CI/CD integration docs (e.g., GitHub Actions example), documented headless flags/exit-code behavior, and independent confirmation of CLI use in automated pipelines.

   • [probe] “official CLI documented at https://cursor.com/cli”
   • [claimed-docs] “curl https://cursor.com/install -fsS | bash”
   • [claimed-docs] “Set up always-on agents that run on schedules or triggers to build, maintain, and fix your software.”
   • [claimed-docs] “Agents use their own computers to build, test, and demo features end to end for you to review.”

   proof ↗⚑ flag

   GitHub Copilot~partialprobed7/10

   GitHub Copilot ships a CLI for terminal/headless use and a 'cloud agent' with 'automations' that can run on a schedule or in response to repo events (e.g., issue opened), plus isolated cloud/local sandboxes for execution — all of which enable non-interactive, CI-like automation. However, evidence doesn't show explicit CI pipeline (e.g., GitHub Actions) integration steps or a documented non-interactive/scriptable flag set for true headless scripting. Missing for 10: documented CI/Actions integration examples, explicit non-interactive/headless CLI flags, and independent hands-on confirmation of automation running unattended in CI.

   • [claimed-docs] “The command-line interface (CLI) for GitHub Copilot allows you to use Copilot directly from your terminal.”
   • [claimed-docs] “Automations let you run Copilot cloud agent automatically, on a schedule or in response to events in a repository.”
   • [claimed-docs] “Set up an automation to run Copilot automatically, on a schedule or in response to events such as an issue being opened.”
   • [claimed-docs] “Cloud and local sandboxes provide isolated execution environments that let Copilot safely interact with code, tools, filesystem, and network…”
   • [claimed-docs] “With Copilot cloud agent, GitHub Copilot can work independently in the background to complete tasks, just like a human developer.”
   • [probe] “official CLI documented at https://docs.github.com/en/copilot/how-tos/copilot-cli/set-up-copilot-cli/install-copilot-cli”

   proof ↗⚑ flag

3. ai-native userPlug MCP servers into this product so it can use their tools

   weight 3 · round to GitHub Copilot
   Cursor✓fullclaimed8/10

   Cursor's docs explicitly describe MCP support: connecting to external tools/data sources, marketplace one-click install with OAuth, custom JSON server configuration, toggling servers, and enterprise admin controls over allowed servers. This directly matches the story of plugging in MCP servers so the agent can use their tools. Missing for 10: independent hands-on verification of MCP tool usage in practice and no community corroboration of the feature's reliability.

   • [claimed-docs] “Model Context Protocol (MCP) enables Cursor to connect to external tools and data sources.”
   • [claimed-docs] “Click "Add to Cursor" on a marketplace entry to install it and authenticate with OAuth.”
   • [claimed-docs] “Configure custom MCP servers with a JSON file”
   • [claimed-docs] “Enterprise admins can control which MCP servers users may run from the Cursor dashboard.”
   • [claimed-docs] “Toggle servers on/off without removing them”

   proof ↗⚑ flag

   GitHub Copilot✓fullclaimed9/10

   GitHub Copilot documents direct MCP server integration: connecting MCP servers to Copilot Chat to extend context/tools, creating custom MCP servers, using the official GitHub MCP server, and admin controls (allow lists) for which MCP servers developers can access. This is well-documented first-party capability across IDE and chat surfaces. missing for 10: independent hands-on community verification of MCP tool usage in practice (community evidence pack is mostly about code suggestion quality/licensing, not MCP specifically).

   • [claimed-docs] “Connect MCP servers to Copilot Chat to share context from other applications.”
   • [claimed-docs] “You can create a new MCP server to fulfill your specific needs, and then integrate it with Copilot Chat.”
   • [claimed-docs] “Learn how to use the GitHub Model Context Protocol (MCP) server to interact with repositories, issues, pull requests, and other GitHub featu…”
   • [claimed-docs] “Control which MCP servers developers can access from their IDEs, and use allow lists to prevent unauthorized access.”
   • [claimed-docs] “Copilot works where you do—in GitHub, your IDE, the CLI, project tools, chat apps, and custom MCP servers.”

   proof ↗⚑ flag

4. ai-native userUse an official CLI

   weight 2 · round drawn
   Cursor✓fullprobed8/10

   Cursor documents an official CLI with an install command (curl https://cursor.com/install) and a dedicated CLI docs page (cursor.com/cli), confirming a first-party terminal tool for AI-native workflows. Missing for 10: independent/hands-on corroboration of CLI capabilities and depth of documentation beyond install instructions.

   • [claimed-docs] “curl https://cursor.com/install -fsS | bash”
   • [claimed-docs] “Cursor runs in your terminal, collaborates in Slack, and reviews PRs in GitHub.”
   • [probe] “official CLI documented at https://cursor.com/cli”

   proof ↗⚑ flag

   GitHub Copilot✓fullprobed8/10

   GitHub Copilot ships an official CLI documented at docs.github.com, letting users invoke Copilot directly from the terminal with prompt/voice input, corroborated by a dedicated install guide probe. missing for 10: independent hands-on community review of the CLI itself (community evidence only covers older chat/agent features, not the CLI), and no detail on CLI feature parity with IDE agent mode.

   • [claimed-docs] “The command-line interface (CLI) for GitHub Copilot allows you to use Copilot directly from your terminal.”
   • [claimed-docs] “As an alternative to typing, you can speak your prompt.”
   • [probe] “official CLI documented at https://docs.github.com/en/copilot/how-tos/copilot-cli/set-up-copilot-cli/install-copilot-cli”
   • [claimed-docs] “GitHub Copilot is also supported in terminals through GitHub CLI and as a chat integration in Windows Terminal Canary.”

   proof ↗⚑ flag

5. ai-native userDrive the product through a documented public API

   weight 3 · round drawn
   Cursor~partialprobed3/10

   Evidence shows an official CLI (cursor.com/cli) that lets users invoke Cursor from scripts, which partially satisfies 'driving the product programmatically,' but there is no documented public REST/SDK API, authentication scheme, or endpoint reference — MCP docs describe Cursor consuming external tools, not exposing itself as an API. Missing for 10: documented REST/GraphQL API, SDK/client libraries, API authentication and rate-limit docs, independent corroboration of programmatic usage.

   • [probe] “official CLI documented at https://cursor.com/cli”
   • [claimed-docs] “curl https://cursor.com/install -fsS | bash”

   proof ↗⚑ flag

   GitHub Copilot~partialprobed3/10

   GitHub Copilot ships a documented CLI (docs-26, probe-4) that lets scripts/agents invoke Copilot from a terminal, and Copilot Chat can be extended via MCP servers (docs-20/21/25), giving some programmatic hooks. However, an explicit probe for a standard OpenAPI/public API spec returned 404s (probe-3), and no REST/GraphQL API for driving Copilot itself is documented in the evidence. Missing for 10: a dedicated, versioned public API (REST/GraphQL/OpenAPI) for programmatically controlling Copilot beyond CLI/MCP, and independent confirmation of its stability/coverage.

   • [claimed-docs] “The command-line interface (CLI) for GitHub Copilot allows you to use Copilot directly from your terminal.”
   • [probe] “official CLI documented at https://docs.github.com/en/copilot/how-tos/copilot-cli/set-up-copilot-cli/install-copilot-cli”
   • [claimed-docs] “Connect MCP servers to Copilot Chat to share context from other applications.”
   • [claimed-docs] “You can create a new MCP server to fulfill your specific needs, and then integrate it with Copilot Chat.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.github.com/openapi.json, https://docs.github.com/swagger.json, https://docs.github.com/…”

   proof ↗⚑ flag

6. ai-native userIssue scoped/least-privilege API credentials for an agent

   weight 2 · round to GitHub Copilot
   Cursor—none0/10

   No evidence Cursor lets users mint scoped or least-privilege API credentials for agents; docs cover MCP server toggling and enterprise admin control of which servers can run, but nothing about issuing scoped/limited API keys or credentials specifically for agent use.

   ⚑ flag

   GitHub Copilot~partialclaimed3/10

   Evidence shows governance-adjacent controls like MCP server allow lists and a central control plane with audit logs for managing agents (docs-10, docs-23), but there is no explicit documentation of issuing scoped or least-privilege API credentials/tokens specifically for an agent's actions. Missing for 10: explicit scoped API credential/token issuance mechanism for agents, fine-grained permission scoping documentation, and independent verification that these controls limit agent API access at a credential level rather than just access-list level.

   • [claimed-docs] “Control which MCP servers developers can access from their IDEs, and use allow lists to prevent unauthorized access.”
   • [claimed-docs] “Track activity with detailed audit logs and enforce governance by managing agents from a single control plane.”
   • [claimed-docs] “Cloud and local sandboxes provide isolated execution environments that let Copilot safely interact with code, tools, filesystem, and network…”

   proof ↗⚑ flag

7. ai-native userBuild against official SDKs

   weight 2 · round to GitHub Copilot
   Cursor—none0/10

   Evidence shows Cursor offers a CLI, MCP integration, and marketplace extensions, but there is no mention of any official SDK (e.g., a documented library/API package) for developers to build against Cursor itself.

   ⚑ flag

   GitHub Copilot~partialclaimed4/10

   Evidence shows extensibility surfaces (MCP server integration, custom agents, partner 'agent apps') that let developers build on top of Copilot, but there is no dedicated official SDK (e.g., language client libraries or API SDK docs) described in the pack. missing for 10: explicit official SDK/client-library docs, code samples for building third-party apps against a Copilot API, independent developer confirmation of SDK usage.

   • [claimed-docs] “Agent apps let you use partner-built agents directly in your workflows on GitHub, powered by your Copilot subscription.”
   • [claimed-docs] “Connect MCP servers to Copilot Chat to share context from other applications.”
   • [claimed-docs] “You can create a new MCP server to fulfill your specific needs, and then integrate it with Copilot Chat.”
   • [claimed-docs] “Custom agents allow you to tailor Copilot's expertise for specific tasks.”

   proof ↗⚑ flag

8. ai-native userSubscribe to events via webhooks

   weight 2 · round drawn
   Cursor—none0/10

   Evidence covers MCP integration, background agents, and IDE integrations, but there is no mention of a webhook subscription mechanism for external event notifications.

   ⚑ flag

   GitHub Copilot—none0/10

   Evidence shows Copilot 'automations' can be triggered by repository events (e.g., issue opened) [docs-33, docs-15], but this is Copilot reacting to GitHub events, not an API/webhook mechanism for an external AI-native user to subscribe to Copilot's own events. No documentation describes a webhook subscription endpoint or event payload schema for consuming Copilot activity.

   • [claimed-docs] “Automations let you run Copilot cloud agent automatically, on a schedule or in response to events in a repository.”
   • [claimed-docs] “Set up an automation to run Copilot automatically, on a schedule or in response to events such as an issue being opened.”

   proof ↗⚑ flag

Agentic features

1. ai-native userGet AI-generated insights and suggestions from my data inside the product

   weight 2 · round to GitHub Copilot
   Cursor✓fullclaimed7/10

   Cursor's core value proposition is analyzing the user's codebase to surface AI-generated insights (tracing repo structure, finding root causes, reviewing diffs) and suggestions for next actions, as documented across multiple first-party docs. Missing for 10: independent/hands-on evidence validating the accuracy or depth of these insights, and no detail on insight types beyond code-centric suggestions (e.g., data analytics or business data outside code).

   • [claimed-docs] “Trace how a repo fits together and find the right places to start”
   • [claimed-docs] “Scope changes, use Plan Mode, and ship bigger work with confidence”
   • [claimed-docs] “Reproduce issues, narrow the root cause, and verify the fix”
   • [claimed-docs] “Inspect diffs, run checks, and catch problems before you merge”

   proof ↗⚑ flag

   GitHub Copilot✓fullcommunity8/10

   Copilot generates AI insights/suggestions from the user's own code and repository data via code completion, chat with repo/doc context, code review with severity-labeled comments, and Autofix vulnerability suggestions, and can pull context from GitHub issues/PRs/docs via MCP. Community anecdotes (comm-1, comm-6, comm-7) corroborate real productivity gains from these suggestions, though some criticize suggestion quality on edge cases (comm-2, comm-10). Missing for 10: independent benchmark data quantifying insight accuracy/usefulness and no first-party analytics-style 'insights dashboard' beyond code review/Autofix.

   • [claimed-docs] “Scale knowledge and keep teams consistent by creating a shared source of truth that includes context from your docs and repositories.”
   • [claimed-docs] “GitHub Copilot Autofix provides contextual explanations and code suggestions to help developers fix vulnerabilities in code”
   • [claimed-docs] “Connect MCP servers to Copilot Chat to share context from other applications.”
   • [claimed-docs] “Learn how to use the GitHub Model Context Protocol (MCP) server to interact with repositories, issues, pull requests, and other GitHub featu…”
   • [claimed-docs] “GitHub Copilot can review your code and provide feedback. Where possible, Copilot's feedback includes suggested changes which you can apply …”
   • [claimed-docs] “Copilot labels each comment with a severity level of "High," "Medium," or "Low" to help you prioritize the issues it finds based on their im…”
   • [community] “I've been using the alpha for the past 2 weeks, and I'm blown away. Copilot guesses the exact code I want about one in ten times... when it …”
   • [community] “I have absolutely loved copilot so far. I especially love how fast it handles indexing complex n-dimensional arrays... I'd estimate a 10% ve…”
   • [community] “Yesterday, Copilot could not write a program with SymPy... Today it uses SymPy as well as it uses NumPy (occasional mistakes, but overall it…”

   proof ↗⚑ flag

2. ai-native userSet up automations that run autonomously in the background

   weight 2 · round drawn
   Cursor✓fullclaimed8/10

   Cursor explicitly documents 'always-on agents that run on schedules or triggers to build, maintain, and fix your software' and 'fleets of agents that work in parallel for hours or days,' directly matching autonomous background automation. This is first-party vendor documentation without independent hands-on corroboration of scheduling/triggers working reliably. Missing for 10: independent/community verification that scheduled/triggered background agents work reliably in practice, and more detail on trigger configuration options.

   • [claimed-docs] “Launch fleets of agents that work in parallel on ambitious tasks for hours or days.”
   • [claimed-docs] “Set up always-on agents that run on schedules or triggers to build, maintain, and fix your software.”
   • [claimed-docs] “Agents use their own computers to build, test, and demo features end to end for you to review.”

   proof ↗⚑ flag

   GitHub Copilot✓fullclaimed8/10

   GitHub Copilot's cloud agent explicitly supports background automation: docs describe running Copilot 'automatically, on a schedule or in response to events in a repository' and working 'independently in the background to complete tasks, just like a human developer,' with a control plane to track multiple agent sessions. This directly matches the story of autonomous background automations for an AI-native user. Missing for 10: independent/community hands-on validation specifically of the scheduled/event-triggered automation feature (most community evidence is about code completion quality, not the cloud-agent automation flow).

   • [claimed-docs] “Automations let you run Copilot cloud agent automatically, on a schedule or in response to events in a repository.”
   • [claimed-docs] “With Copilot cloud agent, GitHub Copilot can work independently in the background to complete tasks, just like a human developer.”
   • [claimed-docs] “Set up an automation to run Copilot automatically, on a schedule or in response to events such as an issue being opened.”
   • [claimed-docs] “Assign tasks to agents like Copilot, Claude by Anthropic, and OpenAI Codex, and let them plan, explore, and execute work autonomously in the…”
   • [claimed-docs] “Use one centralized control page to jump between agent sessions, check progress, and stay in control without losing your place.”
   • [claimed-docs] “Launch work from GitHub, track progress across multiple agents, review changes, and merge completed work—all from one desktop workspace buil…”

   proof ↗⚑ flag

3. ai-native userDelegate tasks to a built-in AI assistant inside the product

   weight 3 · round drawn
   Cursor✓fullclaimed9/10

   Cursor's docs clearly describe delegating tasks to built-in agents that plan, code, test, and demo work end-to-end while the user focuses on review/decisions, including background/parallel agents and always-on scheduled agents. This is a core, heavily documented capability of the product, though independent hands-on validation of agent task quality is thin (only general community commentary, some critical, exists). Missing for 10: deeper independent verification of agent task success rates beyond vendor docs.

   • [claimed-docs] “Launch fleets of agents that work in parallel on ambitious tasks for hours or days.”
   • [claimed-docs] “Set up always-on agents that run on schedules or triggers to build, maintain, and fix your software.”
   • [claimed-docs] “Accelerate development by handing off tasks to Cursor, while you focus on making decisions.”
   • [claimed-docs] “Agents use their own computers to build, test, and demo features end to end for you to review.”
   • [claimed-docs] “Scope changes, use Plan Mode, and ship bigger work with confidence”

   proof ↗⚑ flag

   GitHub Copilot✓fullcommunity9/10

   GitHub Copilot ships extensive built-in agentic capabilities: agent mode in editors, cloud/background agents that plan-explore-execute autonomously, @copilot mentions on PRs, automations, custom agents, and a CLI, all documented first-party. Community evidence corroborates hands-on usage of the assistant delivering real productivity gains, supporting the delegation story. Missing for 10: independent hands-on validation specifically of the newer autonomous cloud-agent/background task delegation (most community evidence predates these agentic features).

   • [claimed-docs] “Edit files in your workspace in agent mode”
   • [claimed-docs] “Assign tasks to agents like Copilot, Claude by Anthropic, and OpenAI Codex, and let them plan, explore, and execute work autonomously in the…”
   • [claimed-docs] “Launch work from GitHub, track progress across multiple agents, review changes, and merge completed work—all from one desktop workspace buil…”
   • [claimed-docs] “With Copilot cloud agent, GitHub Copilot can work independently in the background to complete tasks, just like a human developer.”
   • [claimed-docs] “Mention `@copilot` in a comment on an existing pull request to ask it to make changes.”
   • [claimed-docs] “Set up an automation to run Copilot automatically, on a schedule or in response to events such as an issue being opened.”
   • [community] “I have absolutely loved copilot so far. I especially love how fast it handles indexing complex n-dimensional arrays... I'd estimate a 10% ve…”
   • [community] “Yesterday, Copilot could not write a program with SymPy... Today it uses SymPy as well as it uses NumPy (occasional mistakes, but overall it…”

   proof ↗⚑ flag

4. ai-native userOperate the product with natural-language commands

   weight 2 · round drawn
   Cursor✓fullclaimed8/10

   Cursor's core interaction model is natural-language driven agents that plan, code, test, and operate across terminal/Slack/GitHub (cursor-docs-2, cursor-docs-8, cursor-docs-9, cursor-docs-10, cursor-docs-11), consistent with an AI-native product. Missing for 10: independent hands-on evidence specifically validating natural-language command reliability/accuracy (community evidence focuses on bugginess/pricing complaints unrelated to NL command capability itself).

   • [claimed-docs] “Scope changes, use Plan Mode, and ship bigger work with confidence”
   • [claimed-docs] “Launch fleets of agents that work in parallel on ambitious tasks for hours or days.”
   • [claimed-docs] “Set up always-on agents that run on schedules or triggers to build, maintain, and fix your software.”
   • [claimed-docs] “Cursor runs in your terminal, collaborates in Slack, and reviews PRs in GitHub.”
   • [claimed-docs] “Accelerate development by handing off tasks to Cursor, while you focus on making decisions.”
   • [claimed-docs] “Agents use their own computers to build, test, and demo features end to end for you to review.”

   proof ↗⚑ flag

   GitHub Copilot✓fullcommunity8/10

   GitHub Copilot offers natural-language interaction across chat, agent mode, CLI, and even voice input, letting users direct edits, reviews, and autonomous tasks conversationally (docs-2, docs-22, docs-26, docs-27). Community evidence corroborates real usage of chat/agent workflows, though some report chat availability limited to specific IDEs and mixed quality of autonomous 'fix the bug' style commands. Missing for 10: independent hands-on validation of natural-language command robustness across all surfaces (mobile, terminal) and no rigorous benchmark of command success rate.

   • [claimed-docs] “Edit files in your workspace in agent mode”
   • [claimed-docs] “chat functionality is currently available only in Visual Studio Code, JetBrains, and Visual Studio”
   • [claimed-docs] “Copilot in your editor does it all, from explaining concepts and completing code, to proposing edits and validating files with agent mode.”
   • [claimed-docs] “The command-line interface (CLI) for GitHub Copilot allows you to use Copilot directly from your terminal.”
   • [claimed-docs] “As an alternative to typing, you can speak your prompt.”
   • [community] “The first video in this post is a perfect example of the problems I see in this space. First the programmer asks the AI to nebulously 'fix t…”

   proof ↗⚑ flag

Api quality

1. ai-native userExplore an interactive API reference with runnable examples

   weight 2 · round drawn
   Cursor—none0/10

   No evidence of an interactive API reference with runnable examples for Cursor; docs entries describe product features and MCP setup but nothing about an API reference or executable code samples.

   ⚑ flag

   GitHub Copilot—none0/10

   The evidence pack shows no interactive API reference or runnable-example explorer for GitHub Copilot; a direct probe for OpenAPI/Swagger specs returned 404s on all candidate paths, and docs are plain markdown/text pages rather than an interactive API console.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.github.com/openapi.json, https://docs.github.com/swagger.json, https://docs.github.com/…”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.github.com/llms.txt # GitHub Docs > GitHub is a developer platform for building, shipping, and mai…”
   • [probe] “PROBE docs-md: HTTP 200 at https://docs.github.com/copilot.md # GitHub Copilot documentation You can use GitHub Copilot to enhance your pro…”

   proof ↗⚑ flag

2. ai-native userDownload a machine-readable API spec (OpenAPI or equivalent)

   weight 2 · round drawn
   Cursor—none0/10

   No evidence of Cursor publishing a downloadable OpenAPI or equivalent machine-readable API spec; docs reference MCP config and CLI but not an API spec.

   ⚑ flag

   GitHub Copilot—none0/10

   The evidence pack shows explicit probe attempts to find an OpenAPI/machine-readable spec for GitHub Copilot's docs (openapi.json, swagger.json, etc.) all returning 404, and no other citation mentions a downloadable API spec for Copilot. No documentation or community evidence confirms a machine-readable spec exists.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.github.com/openapi.json, https://docs.github.com/swagger.json, https://docs.github.com/…”

   proof ↗⚑ flag

3. ai-native userRely on versioned APIs with a documented deprecation policy

   weight 2 · round drawn
   Cursor—none0/10

   No evidence in the pack mentions API versioning or a deprecation policy for Cursor's APIs (CLI, extensions, or MCP config); docs cover features like MCP setup, agents, and integrations but nothing about version stability guarantees or deprecation timelines.

   ⚑ flag

   GitHub Copilot—none0/10

   The evidence pack contains no documentation of a versioned API or deprecation policy for GitHub Copilot; the OpenAPI probe explicitly found all candidate spec paths returning 404, and no other citation addresses API versioning/deprecation commitments.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.github.com/openapi.json, https://docs.github.com/swagger.json, https://docs.github.com/…”

   proof ↗⚑ flag

1. ai-native userPerform bulk operations across many items at once

   weight 2 · round drawn
   Cursor~partialclaimed5/10

   Cursor supports launching 'fleets of agents' in parallel and always-on scheduled/triggered agents, which enables some multi-item automation, but there's no direct evidence of bulk operations across many discrete items (e.g., bulk file edits, batch refactors, or multi-repo operations) as a first-class feature. missing for 10: explicit documentation or hands-on evidence of bulk/batch operations across many items (files, tickets, repos), user-facing UI for selecting many items at once, and independent corroboration of this working in practice.

   • [claimed-docs] “Launch fleets of agents that work in parallel on ambitious tasks for hours or days.”
   • [claimed-docs] “Set up always-on agents that run on schedules or triggers to build, maintain, and fix your software.”

   proof ↗⚑ flag

   GitHub Copilot~partialclaimed5/10

   Docs show Copilot can run multiple background cloud-agent sessions in parallel, track them from one control page, and trigger automations on repo events/schedules (docs-8, docs-14, docs-15, docs-33), which supports scaling to many tasks, but there's no explicit evidence of a single bulk command/batch operation (e.g., 'review 50 PRs at once' or 'fix all issues matching X') as a discrete feature. Missing for 10: an explicit bulk-action UI/API (e.g., batch PR review, batch issue triage) and independent confirmation that many items can be processed in one invocation rather than via separate parallel agent sessions.

   • [claimed-docs] “Launch work from GitHub, track progress across multiple agents, review changes, and merge completed work—all from one desktop workspace buil…”
   • [claimed-docs] “Use one centralized control page to jump between agent sessions, check progress, and stay in control without losing your place.”
   • [claimed-docs] “Automations let you run Copilot cloud agent automatically, on a schedule or in response to events in a repository.”
   • [claimed-docs] “Set up an automation to run Copilot automatically, on a schedule or in response to events such as an issue being opened.”
   • [claimed-docs] “Track activity with detailed audit logs and enforce governance by managing agents from a single control plane.”

   proof ↗⚑ flag

2. ai-native userDefine rules that trigger actions automatically on events

   weight 3 · round to GitHub Copilot
   Cursor~partialclaimed6/10

   Cursor docs describe 'always-on agents that run on schedules or triggers' and a way to 'add rules' from one place, matching the idea of rule-based automation triggered by events. However the evidence pack doesn't detail how rules are authored/scoped to specific events beyond the marketing blurb, and there's no independent/hands-on confirmation of this automation working as described. Missing for 10: concrete rule-definition syntax/examples, independent verification that scheduled/triggered agents reliably fire on events, and detail on event types supported.

   • [claimed-docs] “Set up always-on agents that run on schedules or triggers to build, maintain, and fix your software.”
   • [claimed-docs] “Add plugins, skills, MCPs, and rules from one place”

   proof ↗⚑ flag

   GitHub Copilot✓fullclaimed8/10

   GitHub Copilot documents event/schedule-triggered automations for its cloud agent ('run Copilot cloud agent automatically, on a schedule or in response to events in a repository', 'in response to events such as an issue being opened'), plus @mention-triggered PR actions, matching the story's rule-based automatic action pattern. Missing for 10: no independent/hands-on validation of the automation reliability or examples of complex rule chains beyond schedule/issue triggers.

   • [claimed-docs] “Automations let you run Copilot cloud agent automatically, on a schedule or in response to events in a repository.”
   • [claimed-docs] “Set up an automation to run Copilot automatically, on a schedule or in response to events such as an issue being opened.”
   • [claimed-docs] “Mention `@copilot` in a comment on an existing pull request to ask it to make changes.”
   • [claimed-docs] “With Copilot cloud agent, GitHub Copilot can work independently in the background to complete tasks, just like a human developer.”

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round drawn
   Cursor✓fullclaimed7/10

   Cursor documents 'always-on agents that run on schedules or triggers to build, maintain, and fix your software,' directly matching recurring scheduled workflow automation, alongside parallel agent fleets for ambitious tasks. Missing for 10: independent hands-on verification of scheduling reliability, details on trigger configuration options, and any community corroboration of this specific feature working in practice.

   • [claimed-docs] “Set up always-on agents that run on schedules or triggers to build, maintain, and fix your software.”
   • [claimed-docs] “Launch fleets of agents that work in parallel on ambitious tasks for hours or days.”

   proof ↗⚑ flag

   GitHub Copilot✓fullclaimed7/10

   GitHub Copilot docs explicitly describe 'Automations' that run the cloud agent on a schedule or in response to repository events, allowing recurring/scheduled agent workflows, plus a control page to track multiple scheduled agent sessions. This directly matches the story of scheduling recurring jobs/workflows. Missing for 10: independent/hands-on corroboration of scheduling reliability, and more detail on cron-like configuration options or failure handling.

   • [claimed-docs] “Automations let you run Copilot cloud agent automatically, on a schedule or in response to events in a repository.”
   • [claimed-docs] “Set up an automation to run Copilot automatically, on a schedule or in response to events such as an issue being opened.”
   • [claimed-docs] “Use one centralized control page to jump between agent sessions, check progress, and stay in control without losing your place.”
   • [claimed-docs] “With Copilot cloud agent, GitHub Copilot can work independently in the background to complete tasks, just like a human developer.”

   proof ↗⚑ flag

4. ai-native userVersion, review, and roll back my automations

   weight 1 · round to GitHub Copilot
   Cursor—none0/10

   Evidence shows Cursor can inspect diffs and review changes before merge, but there is no documented capability to version, review, or roll back the automations themselves (e.g., scheduled/always-on agents, rules, MCP configs) as distinct artifacts with history/rollback support.

   ⚑ flag

   GitHub Copilot~partialclaimed5/10

   Copilot's cloud-agent automations produce PRs that can be reviewed (code review feature, docs-28/29) and tracked via audit logs and a central control plane (docs-23), and since output flows through Git, changes are inherently versioned and revertible via standard PR/commit mechanics. However, there is no direct evidence of a dedicated versioning or rollback mechanism for the automation definitions/schedules themselves (e.g., automation history, revert-to-previous-config). missing for 10: explicit versioning/rollback UI for automation configs, evidence of rolling back an automation run itself (not just its code output), independent confirmation of this workflow in practice.

   • [claimed-docs] “Automations let you run Copilot cloud agent automatically, on a schedule or in response to events in a repository.”
   • [claimed-docs] “GitHub Copilot can review your code and provide feedback. Where possible, Copilot's feedback includes suggested changes which you can apply …”
   • [claimed-docs] “Copilot labels each comment with a severity level of "High," "Medium," or "Low" to help you prioritize the issues it finds based on their im…”
   • [claimed-docs] “Track activity with detailed audit logs and enforce governance by managing agents from a single control plane.”
   • [claimed-docs] “Set up an automation to run Copilot automatically, on a schedule or in response to events such as an issue being opened.”

   proof ↗⚑ flag

Background execution

1. ai-native userHave a cloud agent build, test, and demo a feature end-to-end for my review

   weight 2 · round to Cursor
   Cursor✓fullclaimed7/10

   Cursor's docs explicitly describe cloud/background agents that 'use their own computers to build, test, and demo features end to end for you to review,' plus the ability to launch fleets of agents working in parallel for hours/days, and always-on scheduled agents — directly matching the story. Corroboration is entirely first-party marketing/docs rather than independent hands-on verification of an actual demo workflow. Missing for 10: independent/hands-on evidence confirming the build-test-demo loop works reliably end-to-end, and detail on what 'demo' concretely produces (e.g., preview links, recordings).

   • [claimed-docs] “Launch fleets of agents that work in parallel on ambitious tasks for hours or days.”
   • [claimed-docs] “Set up always-on agents that run on schedules or triggers to build, maintain, and fix your software.”
   • [claimed-docs] “Accelerate development by handing off tasks to Cursor, while you focus on making decisions.”
   • [claimed-docs] “Agents use their own computers to build, test, and demo features end to end for you to review.”

   proof ↗⚑ flag

   GitHub Copilot~partialclaimed7/10

   Docs describe a genuine cloud agent that works independently in the background (assign tasks, plan/explore/execute), runs in isolated cloud sandboxes to interact with code/tools/filesystem, and produces PRs for review with automated code review and severity-labeled feedback — covering build, execute, and review end-to-end. However, 'testing' and 'demo' are only implied (sandbox execution, PR review) rather than explicitly documented as a testing/demo step, and there is no independent/hands-on corroboration of the cloud agent specifically completing a full feature end-to-end (community evidence predates/doesn't cover the cloud agent feature). Missing for 10: explicit test-running/verification evidence, a documented demo/preview mechanism, and independent hands-on validation of cloud agent outcomes.

   • [claimed-docs] “Assign tasks to agents like Copilot, Claude by Anthropic, and OpenAI Codex, and let them plan, explore, and execute work autonomously in the…”
   • [claimed-docs] “Access to Cloud agent and code review”
   • [claimed-docs] “Launch work from GitHub, track progress across multiple agents, review changes, and merge completed work—all from one desktop workspace buil…”
   • [claimed-docs] “Use one centralized control page to jump between agent sessions, check progress, and stay in control without losing your place.”
   • [claimed-docs] “Automations let you run Copilot cloud agent automatically, on a schedule or in response to events in a repository.”
   • [claimed-docs] “Cloud and local sandboxes provide isolated execution environments that let Copilot safely interact with code, tools, filesystem, and network…”
   • [claimed-docs] “GitHub Copilot can review your code and provide feedback. Where possible, Copilot's feedback includes suggested changes which you can apply …”
   • [claimed-docs] “Copilot labels each comment with a severity level of "High," "Medium," or "Low" to help you prioritize the issues it finds based on their im…”
   • [claimed-docs] “With Copilot cloud agent, GitHub Copilot can work independently in the background to complete tasks, just like a human developer.”
   • [claimed-docs] “Mention `@copilot` in a comment on an existing pull request to ask it to make changes.”
   • [claimed-docs] “Set up an automation to run Copilot automatically, on a schedule or in response to events such as an issue being opened.”

   proof ↗⚑ flag

2. developerDelegate longer-running coding tasks to run in the background in an isolated cloud environment

   weight 3 · round drawn
   Cursor✓fullclaimed8/10

   Cursor documents cloud/background agents ('Agents use their own computers to build, test, and demo features end to end', 'Launch fleets of agents that work in parallel on ambitious tasks for hours or days', and hand-off delegation while the developer focuses elsewhere), matching the isolated cloud-background-task story. Missing for 10: independent hands-on verification of the background agent's isolation/reliability and details on session duration limits or failure modes.

   • [claimed-docs] “Launch fleets of agents that work in parallel on ambitious tasks for hours or days.”
   • [claimed-docs] “Accelerate development by handing off tasks to Cursor, while you focus on making decisions.”
   • [claimed-docs] “Agents use their own computers to build, test, and demo features end to end for you to review.”
   • [claimed-docs] “Set up always-on agents that run on schedules or triggers to build, maintain, and fix your software.”

   proof ↗⚑ flag

   GitHub Copilot✓fullclaimed8/10

   Copilot cloud agent is well documented as delegating tasks to run autonomously in an isolated cloud sandbox, working independently in the background like a human developer, with scheduling/automations, a control page to track multiple sessions, and audit logs for governance. missing for 10: independent hands-on community verification of cloud agent reliability/performance (community evidence pack predates cloud agent feature and doesn't corroborate this specific capability).

   • [claimed-docs] “Assign tasks to agents like Copilot, Claude by Anthropic, and OpenAI Codex, and let them plan, explore, and execute work autonomously in the…”
   • [claimed-docs] “Access to Cloud agent and code review”
   • [claimed-docs] “Launch work from GitHub, track progress across multiple agents, review changes, and merge completed work—all from one desktop workspace buil…”
   • [claimed-docs] “Use one centralized control page to jump between agent sessions, check progress, and stay in control without losing your place.”
   • [claimed-docs] “Automations let you run Copilot cloud agent automatically, on a schedule or in response to events in a repository.”
   • [claimed-docs] “Cloud and local sandboxes provide isolated execution environments that let Copilot safely interact with code, tools, filesystem, and network…”
   • [claimed-docs] “With Copilot cloud agent, GitHub Copilot can work independently in the background to complete tasks, just like a human developer.”
   • [claimed-docs] “Set up an automation to run Copilot automatically, on a schedule or in response to events such as an issue being opened.”
   • [claimed-docs] “Track activity with detailed audit logs and enforce governance by managing agents from a single control plane.”

   proof ↗⚑ flag

3. developerConfigure a reproducible cloud environment with the dependencies and setup steps my repository needs

   weight 2 · round drawn
   Cursor~partialclaimed4/10

   Cursor's docs mention cloud/background agents that 'use their own computers to build, test, and demo features' and can be launched in fleets or run on schedules, implying some cloud execution environment, but there's no evidence pack detail on how a developer configures dependencies, install scripts, or a reproducible environment spec (e.g. Dockerfile/environment.json) for these agents. Missing for 10: explicit documentation of environment configuration format, dependency/setup step definition, and evidence of reproducibility across runs.

   • [claimed-docs] “Launch fleets of agents that work in parallel on ambitious tasks for hours or days.”
   • [claimed-docs] “Set up always-on agents that run on schedules or triggers to build, maintain, and fix your software.”
   • [claimed-docs] “Agents use their own computers to build, test, and demo features end to end for you to review.”

   proof ↗⚑ flag

   GitHub Copilot~partialclaimed4/10

   Docs mention 'Cloud and local sandboxes provide isolated execution environments' for Copilot cloud agent and background task automation, implying some environment abstraction, but there is no explicit evidence of a mechanism (e.g., a setup-steps config, devcontainer, or dependency manifest) for developers to define reproducible cloud environment setup steps. Missing for 10: explicit documentation of a configuration file/workflow for specifying dependencies/setup steps, independent confirmation of reproducibility across runs.

   • [claimed-docs] “Cloud and local sandboxes provide isolated execution environments that let Copilot safely interact with code, tools, filesystem, and network…”
   • [claimed-docs] “With Copilot cloud agent, GitHub Copilot can work independently in the background to complete tasks, just like a human developer.”
   • [claimed-docs] “Set up an automation to run Copilot automatically, on a schedule or in response to events such as an issue being opened.”

   proof ↗⚑ flag

Parallel agents

1. ai-native userLaunch fleets of autonomous agents that work in parallel on different tasks for hours or days

   weight 2 · round to Cursor
   Cursor✓fullclaimed8/10

   First-party marketing/docs explicitly state the exact capability: "Launch fleets of agents that work in parallel on ambitious tasks for hours or days," plus supporting evidence of background/always-on agents and agents using their own compute to build/test/demo. No independent hands-on verification of multi-day parallel fleet execution is present, and no community corroboration confirms this specific feature works at scale. Missing for 10: independent/hands-on validation of parallel agent fleets running for hours/days, details on concurrency limits or reliability over long runs.

   • [claimed-docs] “Launch fleets of agents that work in parallel on ambitious tasks for hours or days.”
   • [claimed-docs] “Set up always-on agents that run on schedules or triggers to build, maintain, and fix your software.”
   • [claimed-docs] “Agents use their own computers to build, test, and demo features end to end for you to review.”
   • [claimed-docs] “Accelerate development by handing off tasks to Cursor, while you focus on making decisions.”

   proof ↗⚑ flag

   GitHub Copilot~partialclaimed6/10

   GitHub Copilot's cloud agent supports background autonomous work, scheduled/event-triggered automations, and a control page to track and manage multiple agent sessions in parallel (docs-8, docs-14, docs-15, docs-31, docs-33), which covers the 'fleets working in parallel' concept. However, evidence doesn't confirm true multi-hour/multi-day persistent autonomous runs at scale or independent hands-on validation of large fleets; most evidence is vendor docs rather than field reports. missing for 10: independent/hands-on confirmation of long-running (hours/days) parallel agent fleets, concrete scale limits or examples of many simultaneous agents, and community verification of duration/reliability at scale.

   • [claimed-docs] “Launch work from GitHub, track progress across multiple agents, review changes, and merge completed work—all from one desktop workspace buil…”
   • [claimed-docs] “Use one centralized control page to jump between agent sessions, check progress, and stay in control without losing your place.”
   • [claimed-docs] “Automations let you run Copilot cloud agent automatically, on a schedule or in response to events in a repository.”
   • [claimed-docs] “With Copilot cloud agent, GitHub Copilot can work independently in the background to complete tasks, just like a human developer.”
   • [claimed-docs] “Set up an automation to run Copilot automatically, on a schedule or in response to events such as an issue being opened.”
   • [claimed-docs] “Track activity with detailed audit logs and enforce governance by managing agents from a single control plane.”

   proof ↗⚑ flag

2. developerRun several task attempts in parallel and compare results before choosing one

   weight 1 · round to Cursor
   Cursor~partialclaimed6/10

   Cursor's docs describe launching 'fleets of agents that work in parallel on ambitious tasks for hours or days,' directly supporting parallel task execution, and agents run in isolated environments for review before merging changes. However, there is no explicit documentation of a UI/workflow for comparing multiple parallel attempts side-by-side before choosing one, and no independent/hands-on evidence corroborating this specific comparison workflow. Missing for 10: dedicated compare/diff-across-attempts feature documentation, independent verification of parallel-agent comparison in practice.

   • [claimed-docs] “Launch fleets of agents that work in parallel on ambitious tasks for hours or days.”
   • [claimed-docs] “Agents use their own computers to build, test, and demo features end to end for you to review.”

   proof ↗⚑ flag

   GitHub Copilot~partialclaimed5/10

   Copilot's cloud/background agents support launching and tracking multiple agent sessions in parallel from a single control page and desktop workspace (docs-8, docs-14, docs-31), which enables running concurrent tasks. However, there's no explicit documentation of running multiple attempts of the *same* task and comparing outputs before selecting one—the evidence describes managing distinct tasks/agents, not competing solutions to a single task. Missing for 10: explicit multi-attempt-per-task workflow, UI for side-by-side comparison of alternative solutions, and any hands-on/community confirmation of this specific parallel-attempt-and-choose pattern.

   • [claimed-docs] “Launch work from GitHub, track progress across multiple agents, review changes, and merge completed work—all from one desktop workspace buil…”
   • [claimed-docs] “Use one centralized control page to jump between agent sessions, check progress, and stay in control without losing your place.”
   • [claimed-docs] “With Copilot cloud agent, GitHub Copilot can work independently in the background to complete tasks, just like a human developer.”
   • [claimed-docs] “Track activity with detailed audit logs and enforce governance by managing agents from a single control plane.”

   proof ↗⚑ flag

Scheduled automation

1. ai-native userSet up always-on agents that run on schedules or triggers to maintain and fix my software autonomously

   weight 2 · round drawn
   Cursor✓fullclaimed8/10

   Cursor's own site directly states the capability: "Set up always-on agents that run on schedules or triggers to build, maintain, and fix your software," plus related background-agent features (parallel fleets, agents running on their own machines) that support this workflow. Missing for 10: independent/hands-on confirmation of scheduled/triggered agents actually running reliably in practice, and more detail on trigger types/configuration.

   • [claimed-docs] “Set up always-on agents that run on schedules or triggers to build, maintain, and fix your software.”
   • [claimed-docs] “Launch fleets of agents that work in parallel on ambitious tasks for hours or days.”
   • [claimed-docs] “Agents use their own computers to build, test, and demo features end to end for you to review.”

   proof ↗⚑ flag

   GitHub Copilot✓fullclaimed8/10

   GitHub Copilot explicitly documents scheduled/event-triggered cloud agents ('Automations let you run Copilot cloud agent automatically, on a schedule or in response to events in a repository') that work independently in the background, plus a control plane to track/manage multiple agent sessions and sandboxed execution environments. This directly matches the always-on, autonomous, schedule/trigger-driven maintenance story. Missing for 10: independent/hands-on verification of scheduled agent runs actually fixing software autonomously in production, and more detail on trigger types beyond issue-opened examples.

   • [claimed-docs] “Automations let you run Copilot cloud agent automatically, on a schedule or in response to events in a repository.”
   • [claimed-docs] “With Copilot cloud agent, GitHub Copilot can work independently in the background to complete tasks, just like a human developer.”
   • [claimed-docs] “Set up an automation to run Copilot automatically, on a schedule or in response to events such as an issue being opened.”
   • [claimed-docs] “Use one centralized control page to jump between agent sessions, check progress, and stay in control without losing your place.”
   • [claimed-docs] “Cloud and local sandboxes provide isolated execution environments that let Copilot safely interact with code, tools, filesystem, and network…”
   • [claimed-docs] “Track activity with detailed audit logs and enforce governance by managing agents from a single control plane.”

   proof ↗⚑ flag

Code completion

1. developerReceive inline code completions and next-edit suggestions as I type

   weight 3 · round to GitHub Copilot
   Cursor—none0/10

   The evidence pack contains no first-party documentation or hands-on account describing Cursor's own inline code completion or next-edit suggestion feature; only tangential community references compare competitors' tab-completion tools (e.g., Continue, SuperMaven) without confirming or detailing Cursor's implementation. Missing for 10: any first-party doc on Cursor's Tab/inline completion feature, hands-on confirmation it works as typed, and mention of 'next-edit' suggestion behavior.

   ⚑ flag

   GitHub Copilot✓fullcommunity9/10

   Docs explicitly claim 'unlimited code completion and next edit suggestions' and inline editor functionality (explaining, completing code, proposing edits), and community reports from real usage confirm inline completions work well in practice (e.g., 'Copilot guesses the exact code I want,' 'occasional mistakes but overall it has the right idea'). Missing for 10: no first-party benchmark or independent quantitative study specifically isolating next-edit-suggestion accuracy separate from general completion quality.

   • [claimed-docs] “Unlimited code completion and next edit suggestions”
   • [claimed-docs] “Copilot in your editor does it all, from explaining concepts and completing code, to proposing edits and validating files with agent mode.”
   • [community] “I've been using the alpha for the past 2 weeks, and I'm blown away. Copilot guesses the exact code I want about one in ten times... when it …”
   • [community] “Yesterday, Copilot could not write a program with SymPy... Today it uses SymPy as well as it uses NumPy (occasional mistakes, but overall it…”

   proof ↗⚑ flag

Debugging

1. developerDebug a live running web application directly from my coding assistant

   weight 1 · round drawn
   Cursor—none0/10

   No evidence pack item describes attaching a debugger, inspecting runtime state, or interacting with a live running web app from Cursor; docs mention reproducing issues and root-causing bugs conceptually, but not live-app debugging integration (e.g., breakpoints, browser dev tools, runtime inspection). missing for 10: evidence of live debugger attach/breakpoints, browser/runtime inspection tooling, or integration with running app state.

   • [claimed-docs] “Reproduce issues, narrow the root cause, and verify the fix”
   • [claimed-docs] “Inspect diffs, run checks, and catch problems before you merge”

   proof ↗⚑ flag

   GitHub Copilot—none0/10

   Evidence covers code completion, chat, agent mode file edits, cloud agents, code review, and MCP integrations, but nothing about attaching to or debugging a live running web application (e.g., runtime inspection, breakpoints, log/trace analysis of a running process). No evidence supports this capability.

   ⚑ flag

2. developerDebug issues and troubleshoot using natural-language queries

   weight 2 · round to GitHub Copilot
   Cursor~partialcommunity6/10

   cursor-docs-3 directly claims support for reproducing issues, narrowing root cause, and verifying fixes via natural-language-driven agent workflows, and docs-1 supports tracing how a repo fits together to find bug locations. However, there's no independent/hands-on evidence corroborating debugging quality, and community evidence highlights buginess and unreliability concerns (cursor-comm-2, cursor-comm-8) that add caveats without directly contradicting the specific debugging workflow claim. Missing for 10: independent verification of debugging accuracy, concrete examples of NL-driven troubleshooting sessions, and resolution of buggy-product complaints.

   • [claimed-docs] “Trace how a repo fits together and find the right places to start”
   • [claimed-docs] “Reproduce issues, narrow the root cause, and verify the fix”
   • [community] “"Cursor is weird. They have a basically unused GitHub with a thousand unanswered Issues. It's so buggy in ways that VSCode isn't. I hate it.…”
   • [community] “"That's a lot of money for a buggy product that is at best slightly better than its competitors."”

   proof ↗⚑ flag

   GitHub Copilot✓fullclaimed7/10

   Copilot Chat explicitly supports natural-language interaction for explaining concepts, code review with prioritized issue severity, and agent mode for autonomous exploration and fixing—core debugging/troubleshooting workflows (docs-4, docs-22, docs-28, docs-29). Autofix also provides contextual explanations for vulnerabilities (docs-13), reinforcing NL-driven troubleshooting. missing for 10: a dedicated 'debug' feature description, independent hands-on evidence specifically validating debugging accuracy/success (community evidence focuses on completion quality and licensing concerns, not debugging).

   • [claimed-docs] “chat functionality is currently available only in Visual Studio Code, JetBrains, and Visual Studio”
   • [claimed-docs] “Copilot in your editor does it all, from explaining concepts and completing code, to proposing edits and validating files with agent mode.”
   • [claimed-docs] “GitHub Copilot can review your code and provide feedback. Where possible, Copilot's feedback includes suggested changes which you can apply …”
   • [claimed-docs] “Copilot labels each comment with a severity level of "High," "Medium," or "Low" to help you prioritize the issues it finds based on their im…”
   • [claimed-docs] “GitHub Copilot Autofix provides contextual explanations and code suggestions to help developers fix vulnerabilities in code”

   proof ↗⚑ flag

Feature implementation

1. developerTurn a tracked issue into a complete pull request end-to-end

   weight 3 · round to GitHub Copilot
   Cursor~partialclaimed7/10

   Cursor's docs describe agents that trace repos, plan changes, reproduce issues, inspect diffs/run checks, and integrate with issue trackers (GitHub, Linear) and PR review, which together support a full issue-to-PR workflow (cursor-docs-1 through cursor-docs-4, cursor-docs-6, cursor-docs-8–cursor-docs-12). However, there's no explicit first-party or independent case study showing a single tracked issue being turned into a merged PR end-to-end without manual intervention, and community evidence focuses on unrelated bugs/pricing complaints rather than this workflow. Missing for 10: a concrete end-to-end example/case study of issue→PR automation and independent verification that the full pipeline works reliably.

   • [claimed-docs] “Trace how a repo fits together and find the right places to start”
   • [claimed-docs] “Scope changes, use Plan Mode, and ship bigger work with confidence”
   • [claimed-docs] “Reproduce issues, narrow the root cause, and verify the fix”
   • [claimed-docs] “Inspect diffs, run checks, and catch problems before you merge”
   • [claimed-docs] “Work with GitHub, GitLab, Azure DevOps, Bitbucket, JetBrains, Slack, Linear, and more”
   • [claimed-docs] “Launch fleets of agents that work in parallel on ambitious tasks for hours or days.”
   • [claimed-docs] “Set up always-on agents that run on schedules or triggers to build, maintain, and fix your software.”
   • [claimed-docs] “Cursor runs in your terminal, collaborates in Slack, and reviews PRs in GitHub.”
   • [claimed-docs] “Accelerate development by handing off tasks to Cursor, while you focus on making decisions.”
   • [claimed-docs] “Agents use their own computers to build, test, and demo features end to end for you to review.”

   proof ↗⚑ flag

   GitHub Copilot✓fullclaimed8/10

   GitHub Copilot's cloud agent can be assigned directly from an issue or via @copilot mentions, working autonomously to plan, explore, execute changes, and open a pull request, with automations to trigger this on issue events; the desktop workspace lets developers track, review, and merge the resulting PR end-to-end. missing for 10: independent hands-on verification of the full issue-to-merged-PR flow (community evidence covers earlier code-completion/chat era, not cloud agent specifically) and concrete success-rate data on autonomous PR quality.

   • [claimed-docs] “Assign tasks to agents like Copilot, Claude by Anthropic, and OpenAI Codex, and let them plan, explore, and execute work autonomously in the…”
   • [claimed-docs] “Launch work from GitHub, track progress across multiple agents, review changes, and merge completed work—all from one desktop workspace buil…”
   • [claimed-docs] “Use one centralized control page to jump between agent sessions, check progress, and stay in control without losing your place.”
   • [claimed-docs] “Automations let you run Copilot cloud agent automatically, on a schedule or in response to events in a repository.”
   • [claimed-docs] “With Copilot cloud agent, GitHub Copilot can work independently in the background to complete tasks, just like a human developer.”
   • [claimed-docs] “Mention `@copilot` in a comment on an existing pull request to ask it to make changes.”
   • [claimed-docs] “Set up an automation to run Copilot automatically, on a schedule or in response to events such as an issue being opened.”

   proof ↗⚑ flag

2. developerDescribe a feature or bug in plain language and have the agent implement or fix it across multiple files

   weight 3 · round drawn
   Cursor✓fullcommunity8/10

   Cursor's docs describe an agent that traces repo structure, plans and scopes multi-file changes, implements features/fixes end-to-end, runs checks, and produces diffs for review — directly matching plain-language feature/bug requests across multiple files. Community evidence corroborates the product is used daily for this purpose (albeit with complaints about bugginess), without disputing the core multi-file agentic editing capability. Missing for 10: independent hands-on benchmarks showing successful multi-file fixes, and no first-party demo/case study detailing a concrete before/after example.

   • [claimed-docs] “Trace how a repo fits together and find the right places to start”
   • [claimed-docs] “Scope changes, use Plan Mode, and ship bigger work with confidence”
   • [claimed-docs] “Reproduce issues, narrow the root cause, and verify the fix”
   • [claimed-docs] “Inspect diffs, run checks, and catch problems before you merge”
   • [claimed-docs] “Accelerate development by handing off tasks to Cursor, while you focus on making decisions.”
   • [claimed-docs] “Agents use their own computers to build, test, and demo features end to end for you to review.”
   • [community] “"Cursor is weird. They have a basically unused GitHub with a thousand unanswered Issues. It's so buggy in ways that VSCode isn't. I hate it.…”
   • [community] “"That's a lot of money for a buggy product that is at best slightly better than its competitors."”

   proof ↗⚑ flag

   GitHub Copilot✓fullcommunity8/10

   Docs describe Copilot agent mode editing files across the workspace, cloud agents that plan/explore/execute tasks autonomously (including from plain-language issue/PR descriptions via @copilot mentions), and code review/autofix capabilities, directly matching the story of describing a feature/bug and having it implemented across multiple files. Community evidence corroborates real usage of the agent for multi-file/complex code tasks, though some hands-on reports note quality limitations on nuanced 'fix the bug' requests. Missing for 10: rigorous independent benchmarking of multi-file correctness and more first-hand accounts specifically of cross-file feature implementation success/failure rates.

   • [claimed-docs] “Edit files in your workspace in agent mode”
   • [claimed-docs] “Assign tasks to agents like Copilot, Claude by Anthropic, and OpenAI Codex, and let them plan, explore, and execute work autonomously in the…”
   • [claimed-docs] “With Copilot cloud agent, GitHub Copilot can work independently in the background to complete tasks, just like a human developer.”
   • [claimed-docs] “Mention `@copilot` in a comment on an existing pull request to ask it to make changes.”
   • [claimed-docs] “Copilot in your editor does it all, from explaining concepts and completing code, to proposing edits and validating files with agent mode.”
   • [community] “The first video in this post is a perfect example of the problems I see in this space. First the programmer asks the AI to nebulously 'fix t…”

   proof ↗⚑ flag

Maintenance automation

1. developerHave the agent write tests, fix lint errors, resolve merge conflicts, and update dependencies for me

   weight 3 · round to GitHub Copilot
   Cursor~partialclaimed6/10

   Cursor's docs describe agents that write code, run tests/checks, and 'build, maintain, and fix' software autonomously (cursor-docs-3, cursor-docs-4, cursor-docs-9, cursor-docs-12), which implies test-writing and general maintenance tasks, but there is no explicit documentation of lint-error fixing, merge-conflict resolution, or dependency-update workflows specifically. missing for 10: explicit lint-fixing examples, explicit merge-conflict-resolution examples, explicit dependency-update examples, independent hands-on verification of these specific tasks.

   • [claimed-docs] “Reproduce issues, narrow the root cause, and verify the fix”
   • [claimed-docs] “Inspect diffs, run checks, and catch problems before you merge”
   • [claimed-docs] “Set up always-on agents that run on schedules or triggers to build, maintain, and fix your software.”
   • [claimed-docs] “Agents use their own computers to build, test, and demo features end to end for you to review.”

   proof ↗⚑ flag

   GitHub Copilot✓fullclaimed8/10

   Copilot's agent mode edits files, validates changes, and can autonomously plan/execute tasks (docs-2,3,22,31), code review with severity-labeled feedback and suggested fixes covers lint/quality issues (docs-28,29), and @copilot on PRs plus cloud agent covers merge conflict resolution and general code changes (docs-32). Dependency updates and explicit test-writing aren't separately documented as named features, so this is inferred from general-purpose agent code editing rather than a dedicated capability. missing for 10: explicit documented examples of writing tests, resolving merge conflicts, and updating dependencies as named use cases, and independent hands-on confirmation of these specific tasks.

   • [claimed-docs] “Edit files in your workspace in agent mode”
   • [claimed-docs] “Assign tasks to agents like Copilot, Claude by Anthropic, and OpenAI Codex, and let them plan, explore, and execute work autonomously in the…”
   • [claimed-docs] “Copilot in your editor does it all, from explaining concepts and completing code, to proposing edits and validating files with agent mode.”
   • [claimed-docs] “GitHub Copilot can review your code and provide feedback. Where possible, Copilot's feedback includes suggested changes which you can apply …”
   • [claimed-docs] “Copilot labels each comment with a severity level of "High," "Medium," or "Low" to help you prioritize the issues it finds based on their im…”
   • [claimed-docs] “With Copilot cloud agent, GitHub Copilot can work independently in the background to complete tasks, just like a human developer.”
   • [claimed-docs] “Mention `@copilot` in a comment on an existing pull request to ask it to make changes.”

   proof ↗⚑ flag

Multimodal generation

1. ai-native userGenerate a working app from a sketch, image, or PDF design

   weight 2 · round drawn
   Cursor—none0/10

   No evidence in the pack describes image/sketch/PDF-to-app generation, multimodal design input, or any UI-from-design workflow; the docs snippets cover repo navigation, plan mode, agents, MCP, and integrations but nothing about visual design inputs.

   ⚑ flag

   GitHub Copilot—none0/10

   No evidence that Copilot can take a sketch, image, or PDF design and generate a working app from it; documentation focuses on code completion, chat, agent mode, cloud agents, and MCP integration, with no mention of image/PDF-to-code or multimodal design-to-app generation.

   ⚑ flag

Codebase mapping

1. developerUnderstand how a codebase fits together to find where to start making changes

   weight 3 · round to Cursor
   Cursor~partialclaimed6/10

   Cursor's docs explicitly claim the ability to 'trace how a repo fits together and find the right places to start,' directly matching the story, but this is a single marketing-style doc line with no detailed walkthrough, feature docs (e.g., codebase indexing/@codebase chat), or independent corroboration of how it actually surfaces architecture understanding. Missing for 10: detailed documentation of the codebase-mapping/indexing feature itself, concrete examples of it locating relevant code, and independent/hands-on validation of accuracy.

   • [claimed-docs] “Trace how a repo fits together and find the right places to start”

   proof ↗⚑ flag

   GitHub Copilot~partialclaimed5/10

   Copilot Chat in the editor is documented to explain concepts and provide context-aware help (docs-22), and enterprise features let teams build a 'shared source of truth' from docs and repos (docs-9) plus MCP integrations that pull in repo/issue/PR context (docs-20, docs-21, docs-25), all of which support exploring an unfamiliar codebase. However, there is no explicit feature description of codebase-wide indexing, dependency/architecture mapping, or a dedicated 'explain this repo' capability, and no hands-on community evidence confirming it helps developers orient in large codebases. Missing for 10: dedicated codebase-mapping/semantic search feature docs, explicit onboarding/architecture-understanding use case, and independent corroboration of effectiveness.

   • [claimed-docs] “Copilot in your editor does it all, from explaining concepts and completing code, to proposing edits and validating files with agent mode.”
   • [claimed-docs] “Scale knowledge and keep teams consistent by creating a shared source of truth that includes context from your docs and repositories.”
   • [claimed-docs] “Connect MCP servers to Copilot Chat to share context from other applications.”
   • [claimed-docs] “You can create a new MCP server to fulfill your specific needs, and then integrate it with Copilot Chat.”
   • [claimed-docs] “Learn how to use the GitHub Model Context Protocol (MCP) server to interact with repositories, issues, pull requests, and other GitHub featu…”

   proof ↗⚑ flag

2. developerHave the agent map and explain an entire unfamiliar codebase without manually selecting context files

   weight 3 · round to GitHub Copilot
   Cursor~partialclaimed4/10

   First-party docs claim Cursor can 'trace how a repo fits together and find the right places to start' (cursor-docs-1), implying automatic codebase mapping, but there's no detail on how context is auto-gathered (e.g., codebase indexing/@codebase) nor any independent/hands-on confirmation that it explains an unfamiliar codebase without manual file selection. Missing for 10: technical explanation of automatic context retrieval, independent user validation of whole-codebase explanation, and comparison to manual context selection workflows.

   • [claimed-docs] “Trace how a repo fits together and find the right places to start”

   proof ↗⚑ flag

   GitHub Copilot~partialclaimed5/10

   Copilot's agent mode and cloud agent are documented to 'plan, explore, and execute work autonomously' across a repo, and 'skills' let it perform specialized tasks, implying some autonomous codebase exploration without hand-picked files, but there's no explicit doc describing a whole-codebase 'map and explain' capability. missing for 10: dedicated codebase-mapping/explanation feature docs, evidence of automatic whole-repo context gathering without manual file selection, and independent hands-on confirmation of this specific workflow.

   • [claimed-docs] “Assign tasks to agents like Copilot, Claude by Anthropic, and OpenAI Codex, and let them plan, explore, and execute work autonomously in the…”
   • [claimed-docs] “Scale knowledge and keep teams consistent by creating a shared source of truth that includes context from your docs and repositories.”
   • [claimed-docs] “Copilot in your editor does it all, from explaining concepts and completing code, to proposing edits and validating files with agent mode.”
   • [claimed-docs] “With Copilot cloud agent, GitHub Copilot can work independently in the background to complete tasks, just like a human developer.”

   proof ↗⚑ flag

Context management

1. developerHave the agent build and recall memory automatically across sessions

   weight 2 · round drawn
   Cursor—none0/10

   No evidence describes persistent memory that automatically builds and recalls context across sessions; docs mention repo tracing, plan mode, and MCP integrations but nothing about cross-session memory recall.

   ⚑ flag

   GitHub Copilot—none0/10

   The evidence pack describes agent mode, cloud agents, MCP context, and code review, but nothing about persistent memory that is automatically built and recalled across sessions—closest is a static 'shared source of truth' repository doc feature, not agent-built memory.

   • [claimed-docs] “Scale knowledge and keep teams consistent by creating a shared source of truth that includes context from your docs and repositories.”

   proof ↗⚑ flag

2. developerInclude multiple project directories in a single session for broader context

   weight 2 · round drawn
   Cursor—none0/10

   No evidence in the pack mentions multi-root workspaces or including multiple project directories in a single Cursor session; docs cover repo navigation, MCP, agents, and integrations but not multi-directory context.

   ⚑ flag

   GitHub Copilot—none0/10

   The evidence pack describes agent mode, chat, MCP integrations, and cloud agents, but contains no mention of including multiple project directories/folders in a single Copilot session for broader context. Missing for 10: any documentation of multi-root workspace support, cross-directory indexing, or explicit multi-project context sharing in one session.

   ⚑ flag

3. developerAdd a project instructions file to set coding standards and conventions the agent follows

   weight 3 · round to GitHub Copilot
   Cursor~partialclaimed3/10

   Cursor's docs mention adding 'rules' as one of its features (alongside plugins, skills, MCPs) which aligns with the project-instructions concept, but the evidence pack gives no detail on how project rule files work, their scope, or how the agent applies them to enforce coding standards. missing for 10: documentation of the rules file format/location, examples of coding standards enforcement, independent confirmation the agent actually follows these instructions consistently.

   • [claimed-docs] “Add plugins, skills, MCPs, and rules from one place”

   proof ↗⚑ flag

   GitHub Copilot~partialclaimed4/10

   Docs mention 'creating a shared source of truth that includes context from your docs and repositories' to keep teams consistent (github-copilot-docs-9), which gestures at instructions/knowledge-context features, but the evidence pack never explicitly describes a project instructions file (e.g., copilot-instructions.md) or how coding standards/conventions are set and enforced. Missing for 10: explicit documentation of an instructions file mechanism, its scope/format, and confirmation the agent follows it during edits/completions.

   • [claimed-docs] “Scale knowledge and keep teams consistent by creating a shared source of truth that includes context from your docs and repositories.”

   proof ↗⚑ flag

Issue diagnosis

1. developerReproduce issues, narrow down root causes, and verify fixes

   weight 3 · round to Cursor
   Cursor~partialclaimed6/10

   cursor-docs-3 directly claims the exact capability ('Reproduce issues, narrow the root cause, and verify the fix'), and supporting docs on codebase tracing, diffs/checks, and agents running their own environments (cursor-docs-1, cursor-docs-4, cursor-docs-12) plausibly back this workflow. However, this is a first-party marketing/docs claim only, with no independent or hands-on corroboration of actual debugging workflows, and community evidence highlights general bugginess/quality concerns rather than validating this specific capability. Missing for 10: independent verification or hands-on case studies of reproduce/root-cause/verify-fix workflows, more detail on how reproduction (e.g., test running, log inspection) is concretely supported.

   • [claimed-docs] “Reproduce issues, narrow the root cause, and verify the fix”
   • [claimed-docs] “Trace how a repo fits together and find the right places to start”
   • [claimed-docs] “Inspect diffs, run checks, and catch problems before you merge”
   • [claimed-docs] “Agents use their own computers to build, test, and demo features end to end for you to review.”

   proof ↗⚑ flag

   GitHub Copilot~partialclaimed5/10

   Copilot's agent mode and chat can propose edits and 'validate files' (docs-22), Autofix explains and suggests fixes for vulnerabilities (docs-13), and code review flags issues with severity (docs-28/29), which together support parts of root-cause analysis and fix verification, but there is no explicit documentation of reproducing bugs, running/debugging tests, or a dedicated root-cause investigation workflow. missing for 10: explicit reproduction-of-issue workflow, test-execution/debugging tooling, and independent hands-on evidence of root-cause narrowing.

   • [claimed-docs] “GitHub Copilot Autofix provides contextual explanations and code suggestions to help developers fix vulnerabilities in code”
   • [claimed-docs] “Copilot in your editor does it all, from explaining concepts and completing code, to proposing edits and validating files with agent mode.”
   • [claimed-docs] “GitHub Copilot can review your code and provide feedback. Where possible, Copilot's feedback includes suggested changes which you can apply …”
   • [claimed-docs] “Copilot labels each comment with a severity level of "High," "Medium," or "Low" to help you prioritize the issues it finds based on their im…”
   • [claimed-docs] “Cloud and local sandboxes provide isolated execution environments that let Copilot safely interact with code, tools, filesystem, and network…”

   proof ↗⚑ flag

Marketplace

1. developerEquip the agent with custom skills to perform specialized tasks

   weight 1 · round to GitHub Copilot
   Cursor~partialclaimed6/10

   Cursor's docs mention a marketplace to 'Add plugins, skills, MCPs, and rules from one place' and detailed MCP support (custom servers, marketplace install, enterprise controls), enabling developers to extend the agent with specialized tool integrations. However, there's no dedicated documentation on a 'skills' framework distinct from MCP/rules, no examples of custom skill creation workflow, and no independent/community corroboration of this specific capability. Missing for 10: detailed skills documentation/tutorial, examples of custom skill authoring, independent hands-on validation.

   • [claimed-docs] “Add plugins, skills, MCPs, and rules from one place”
   • [claimed-docs] “Model Context Protocol (MCP) enables Cursor to connect to external tools and data sources.”
   • [claimed-docs] “Click "Add to Cursor" on a marketplace entry to install it and authenticate with OAuth.”
   • [claimed-docs] “Configure custom MCP servers with a JSON file”
   • [claimed-docs] “Enterprise admins can control which MCP servers users may run from the Cursor dashboard.”

   proof ↗⚑ flag

   GitHub Copilot✓fullclaimed6/10

   Docs explicitly describe a 'Skills' feature ('Skills allow Copilot to perform specialized tasks') and 'Custom agents' that let developers tailor Copilot's expertise, plus MCP server extensibility to add custom tools/context. This directly matches the story of equipping the agent with custom skills, though details are thin. Missing for 10: concrete developer walkthrough of creating a skill, independent/hands-on confirmation of using custom skills, and richer documentation depth beyond a single-line description.

   • [claimed-docs] “Skills allow Copilot to perform specialized tasks.”
   • [claimed-docs] “Custom agents allow you to tailor Copilot's expertise for specific tasks.”
   • [claimed-docs] “Connect MCP servers to Copilot Chat to share context from other applications.”
   • [claimed-docs] “You can create a new MCP server to fulfill your specific needs, and then integrate it with Copilot Chat.”

   proof ↗⚑ flag

2. engineering-leadIntegrate third-party partner-built agent apps into my workflows

   weight 1 · round to GitHub Copilot
   Cursor✓fullclaimed7/10

   Cursor documents a marketplace for adding third-party plugins, skills, and MCP servers with OAuth authentication, plus native integrations with GitHub, GitLab, Slack, Linear, and more, letting teams plug partner-built tools/agents into their workflows, with enterprise admin controls over which servers are allowed. Missing for 10: independent/hands-on corroboration of using specific partner-built agent apps (vs. generic tool connectors) and clearer distinction between simple MCP data-tools and full third-party 'agent apps'.

   • [claimed-docs] “Add plugins, skills, MCPs, and rules from one place”
   • [claimed-docs] “Work with GitHub, GitLab, Azure DevOps, Bitbucket, JetBrains, Slack, Linear, and more”
   • [claimed-docs] “Model Context Protocol (MCP) enables Cursor to connect to external tools and data sources.”
   • [claimed-docs] “Click "Add to Cursor" on a marketplace entry to install it and authenticate with OAuth.”
   • [claimed-docs] “Configure custom MCP servers with a JSON file”
   • [claimed-docs] “Enterprise admins can control which MCP servers users may run from the Cursor dashboard.”

   proof ↗⚑ flag

   GitHub Copilot✓fullclaimed8/10

   Docs explicitly describe 'Agent apps' that let partner-built agents be used directly in GitHub workflows powered by Copilot subscription, plus assigning tasks to third-party agents (Claude, OpenAI Codex) and MCP server integration for extending Copilot with external tools. Missing for 10: independent/hands-on verification of partner agent app integrations and detail on governance/setup friction beyond first-party docs.

   • [claimed-docs] “Agent apps let you use partner-built agents directly in your workflows on GitHub, powered by your Copilot subscription.”
   • [claimed-docs] “Assign tasks to agents like Copilot, Claude by Anthropic, and OpenAI Codex, and let them plan, explore, and execute work autonomously in the…”
   • [claimed-docs] “Connect MCP servers to Copilot Chat to share context from other applications.”
   • [claimed-docs] “You can create a new MCP server to fulfill your specific needs, and then integrate it with Copilot Chat.”
   • [claimed-docs] “Control which MCP servers developers can access from their IDEs, and use allow lists to prevent unauthorized access.”

   proof ↗⚑ flag

Team knowledge

1. engineering-leadCreate a shared workspace from my docs and repos as a common source of truth for the team

   weight 1 · round to GitHub Copilot
   Cursor—none0/10

   Evidence shows integrations (GitHub, Slack, Linear), MCP/plugins, and rules configuration, but nothing describes a dedicated 'shared workspace' feature that unifies docs and repos into a common team source of truth — this is a fair ask for a team-oriented dev tool but unaddressed in the pack.

   ⚑ flag

   GitHub Copilot~partialclaimed5/10

   Docs explicitly claim the ability to 'scale knowledge and keep teams consistent by creating a shared source of truth that includes context from your docs and repositories,' directly matching the story, and related enterprise-governance features (control planes, audit logs, MCP allow-lists) support team-wide consistency. However, this is a single vendor-claimed line item with no elaboration on setup, structure, or how it functions as a 'workspace,' and no independent/hands-on evidence corroborates it. Missing for 10: independent verification, concrete workflow/UI details, and community confirmation that teams actually use this as a shared source of truth.

   • [claimed-docs] “Scale knowledge and keep teams consistent by creating a shared source of truth that includes context from your docs and repositories.”
   • [claimed-docs] “Track activity with detailed audit logs and enforce governance by managing agents from a single control plane.”
   • [claimed-docs] “Control which MCP servers developers can access from their IDEs, and use allow lists to prevent unauthorized access.”

   proof ↗⚑ flag

Tool integration

1. developerConnect the agent to workflow tools like Jira, Slack, and Google Drive to extend its context

   weight 3 · round to Cursor
   Cursor✓fullclaimed8/10

   Cursor documents MCP support that connects to external tools/data sources, an MCP marketplace with OAuth install, and explicit integration with Slack alongside GitHub/GitLab/Linear/Jira-style trackers, plus Slack-based agent collaboration—covering the story's workflow-tool extension use case. Missing for 10: explicit first-party Jira/Google Drive connector documentation and independent hands-on verification of these integrations working end-to-end.

   • [claimed-docs] “Model Context Protocol (MCP) enables Cursor to connect to external tools and data sources.”
   • [claimed-docs] “Click "Add to Cursor" on a marketplace entry to install it and authenticate with OAuth.”
   • [claimed-docs] “Configure custom MCP servers with a JSON file”
   • [claimed-docs] “Work with GitHub, GitLab, Azure DevOps, Bitbucket, JetBrains, Slack, Linear, and more”
   • [claimed-docs] “Cursor runs in your terminal, collaborates in Slack, and reviews PRs in GitHub.”

   proof ↗⚑ flag

   GitHub Copilot~partialclaimed5/10

   Copilot supports connecting to external tools via MCP servers (docs-10, docs-20, docs-21, docs-25, docs-35), and states it can create custom MCP servers for specific needs, which theoretically enables Jira/Slack/Google Drive integration. However, no evidence names first-party or documented connectors for Jira, Slack, or Google Drive specifically. missing for 10: named official integrations or docs referencing Jira/Slack/Google Drive, independent confirmation these connectors work in practice.

   • [claimed-docs] “Connect MCP servers to Copilot Chat to share context from other applications.”
   • [claimed-docs] “You can create a new MCP server to fulfill your specific needs, and then integrate it with Copilot Chat.”
   • [claimed-docs] “Control which MCP servers developers can access from their IDEs, and use allow lists to prevent unauthorized access.”
   • [claimed-docs] “Copilot works where you do—in GitHub, your IDE, the CLI, project tools, chat apps, and custom MCP servers.”

   proof ↗⚑ flag

2. developerKick off agent tasks directly from GitHub, GitLab, Linear, or Slack

   weight 2 · round to Cursor
   Cursor~partialclaimed7/10

   Cursor's docs explicitly list integrations with GitHub, GitLab, Slack, and Linear, and describe agents that run on triggers/schedules and collaborate in Slack or review PRs in GitHub, supporting the story's core claim. However, there's no detailed first-party documentation of the exact trigger mechanics per platform (e.g., a Linear ticket auto-spawning an agent) nor independent/hands-on confirmation that this works reliably. Missing for 10: platform-specific trigger documentation for each of GitHub/GitLab/Linear/Slack, and independent verification of the workflow in practice.

   • [claimed-docs] “Work with GitHub, GitLab, Azure DevOps, Bitbucket, JetBrains, Slack, Linear, and more”
   • [claimed-docs] “Set up always-on agents that run on schedules or triggers to build, maintain, and fix your software.”
   • [claimed-docs] “Cursor runs in your terminal, collaborates in Slack, and reviews PRs in GitHub.”

   proof ↗⚑ flag

   GitHub Copilot~partialclaimed4/10

   Docs clearly show agent tasks can be kicked off from GitHub itself (mentioning @copilot on a PR, automations triggered by repo events, cloud agent background execution), and Copilot is described as working across 'chat apps' generically, but no evidence specifically documents launching agent tasks from GitLab, Linear, or Slack. Missing for 10: explicit GitLab integration, explicit Linear integration, explicit Slack integration for triggering agent tasks.

   • [claimed-docs] “With Copilot cloud agent, GitHub Copilot can work independently in the background to complete tasks, just like a human developer.”
   • [claimed-docs] “Mention `@copilot` in a comment on an existing pull request to ask it to make changes.”
   • [claimed-docs] “Set up an automation to run Copilot automatically, on a schedule or in response to events such as an issue being opened.”
   • [claimed-docs] “Copilot works where you do—in GitHub, your IDE, the CLI, project tools, chat apps, and custom MCP servers.”
   • [claimed-docs] “Agent apps let you use partner-built agents directly in your workflows on GitHub, powered by your Copilot subscription.”

   proof ↗⚑ flag

Cross device continuity

1. developerStart a task on one device and continue it later from another device or browser

   weight 2 · round to GitHub Copilot
   Cursor~partialclaimed5/10

   Cursor's Background Agents run remotely and can be monitored/interacted with via terminal, Slack, and GitHub PRs, implying a task could be checked or continued from different surfaces, but there is no explicit documentation of resuming a specific in-progress task from a different device or browser session. Missing for 10: explicit cross-device/browser session handoff documentation, hands-on confirmation of resuming a task started elsewhere, and details on state syncing across clients.

   • [claimed-docs] “Launch fleets of agents that work in parallel on ambitious tasks for hours or days.”
   • [claimed-docs] “Set up always-on agents that run on schedules or triggers to build, maintain, and fix your software.”
   • [claimed-docs] “Cursor runs in your terminal, collaborates in Slack, and reviews PRs in GitHub.”
   • [claimed-docs] “Accelerate development by handing off tasks to Cursor, while you focus on making decisions.”
   • [claimed-docs] “Agents use their own computers to build, test, and demo features end to end for you to review.”

   proof ↗⚑ flag

   GitHub Copilot~partialclaimed7/10

   Copilot's cloud agent and control-plane features (docs-8, docs-14, docs-31-33) let a developer assign a task to an agent from GitHub or an IDE and later check progress or continue via GitHub.com's centralized control page or desktop workspace, which is inherently accessible cross-device/browser. However, this is inferred from the cloud-agent architecture rather than an explicit 'continue from another device' claim, and there's no independent/hands-on confirmation of seamless handoff. Missing for 10: explicit documentation of cross-device session continuation and independent verification that state/context truly persists and is resumable identically on a different machine or browser.

   • [claimed-docs] “Launch work from GitHub, track progress across multiple agents, review changes, and merge completed work—all from one desktop workspace buil…”
   • [claimed-docs] “Use one centralized control page to jump between agent sessions, check progress, and stay in control without losing your place.”
   • [claimed-docs] “With Copilot cloud agent, GitHub Copilot can work independently in the background to complete tasks, just like a human developer.”
   • [claimed-docs] “Mention `@copilot` in a comment on an existing pull request to ask it to make changes.”
   • [claimed-docs] “Set up an automation to run Copilot automatically, on a schedule or in response to events such as an issue being opened.”

   proof ↗⚑ flag

Ide integration

1. developerView interactive diffs and share selected code as context from within my JetBrains IDE

   weight 1 · round to GitHub Copilot
   Cursor—none0/10

   The only evidence touching JetBrains is a single line listing JetBrains among integrations (cursor-docs-6), with no detail on interactive diffs or context-sharing features within a JetBrains IDE specifically. No documentation, screenshots, or community reports confirm this JetBrains-specific capability.

   • [claimed-docs] “Work with GitHub, GitLab, Azure DevOps, Bitbucket, JetBrains, Slack, Linear, and more”

   proof ↗⚑ flag

   GitHub Copilot~partialclaimed4/10

   Docs confirm Copilot Chat and agent-mode editing are available in JetBrains IDEs (github-copilot-docs-4, github-copilot-docs-24, github-copilot-docs-22), which implies some in-IDE diff/context capability, but no evidence specifically describes an interactive diff viewer or a 'share selected code as context' feature for JetBrains. Missing for 10: explicit documentation of JetBrains-specific interactive diff UI, explicit context-selection workflow, and independent/hands-on confirmation of these JetBrains features.

   • [claimed-docs] “chat functionality is currently available only in Visual Studio Code, JetBrains, and Visual Studio”
   • [claimed-docs] “GitHub Copilot integrates with leading editors, including Visual Studio Code, Visual Studio, JetBrains IDEs, and Neovim, and, unlike other A…”
   • [claimed-docs] “Copilot in your editor does it all, from explaining concepts and completing code, to proposing edits and validating files with agent mode.”

   proof ↗⚑ flag

2. developerChat with the coding assistant directly inside my IDE for contextual help

   weight 3 · round to GitHub Copilot
   Cursor✓fullcommunity7/10

   Cursor's docs describe an IDE-integrated assistant that traces repo structure, scopes changes via Plan Mode, reproduces issues, and hands off tasks while the developer reviews — all consistent with in-IDE contextual chat, and community commentary confirms it functions as a VS Code-based assistant with prompts/harness. missing for 10: no explicit citation naming a dedicated 'chat panel' UI or independent praise of chat quality/context-awareness specifically.

   • [claimed-docs] “Trace how a repo fits together and find the right places to start”
   • [claimed-docs] “Scope changes, use Plan Mode, and ship bigger work with confidence”
   • [claimed-docs] “Reproduce issues, narrow the root cause, and verify the fix”
   • [claimed-docs] “Accelerate development by handing off tasks to Cursor, while you focus on making decisions.”
   • [claimed-docs] “Agents use their own computers to build, test, and demo features end to end for you to review.”
   • [community] “"Cursor is an extension for VS Code, a harness and a bunch of prompts. They have their own model (Composer 2) which is based on Kimi K2.5, b…”

   proof ↗⚑ flag

   GitHub Copilot✓fullcommunity9/10

   Docs confirm Copilot Chat is built into VS Code, JetBrains, and Visual Studio for contextual in-IDE chat (explaining concepts, proposing edits, agent mode), and community feedback corroborates real usage inside the editor. Missing for 10: independent hands-on report specifically about the chat UX (most community evidence focuses on completions, not chat).

   • [claimed-docs] “chat functionality is currently available only in Visual Studio Code, JetBrains, and Visual Studio”
   • [claimed-docs] “Copilot in your editor does it all, from explaining concepts and completing code, to proposing edits and validating files with agent mode.”
   • [claimed-docs] “GitHub Copilot integrates with leading editors, including Visual Studio Code, Visual Studio, JetBrains IDEs, and Neovim, and, unlike other A…”
   • [community] “I've been using the alpha for the past 2 weeks, and I'm blown away. Copilot guesses the exact code I want about one in ten times... when it …”

   proof ↗⚑ flag

Session management

1. developerReview diffs visually and run multiple sessions side by side in a desktop app

   weight 2 · round to Cursor
   Cursor✓fullclaimed6/10

   Cursor's docs explicitly describe inspecting diffs before merge and launching fleets of agents to work in parallel, both core to a desktop IDE experience with visual diff review and concurrent sessions. Missing for 10: independent/hands-on confirmation of the side-by-side session UI and a detailed walkthrough of the diff viewer beyond marketing copy.

   • [claimed-docs] “Inspect diffs, run checks, and catch problems before you merge”
   • [claimed-docs] “Launch fleets of agents that work in parallel on ambitious tasks for hours or days.”
   • [claimed-docs] “Accelerate development by handing off tasks to Cursor, while you focus on making decisions.”
   • [claimed-docs] “Agents use their own computers to build, test, and demo features end to end for you to review.”

   proof ↗⚑ flag

   GitHub Copilot~partialclaimed4/10

   Docs mention a 'desktop workspace' for launching work, tracking multiple agent sessions, and reviewing changes (docs-8, docs-14), and a code-review feature with inline suggested changes (docs-28), suggesting some diff-review and multi-session tracking capability. However, it's unclear whether this 'desktop workspace' is a native desktop app or a web-based GitHub UI, and there's no explicit description of a visual side-by-side diff viewer or dedicated multi-pane session UI as in competing IDE tools. Missing for 10: confirmation of a true native desktop application (not browser-based), explicit visual diff-viewer description, and independent/hands-on evidence of side-by-side session usage.

   • [claimed-docs] “Launch work from GitHub, track progress across multiple agents, review changes, and merge completed work—all from one desktop workspace buil…”
   • [claimed-docs] “Use one centralized control page to jump between agent sessions, check progress, and stay in control without losing your place.”
   • [claimed-docs] “GitHub Copilot can review your code and provide feedback. Where possible, Copilot's feedback includes suggested changes which you can apply …”

   proof ↗⚑ flag

2. engineering-leadManage multiple agent-driven coding sessions from one unified workspace

   weight 2 · round to GitHub Copilot
   Cursor✓fullclaimed7/10

   Cursor's docs explicitly describe launching 'fleets of agents that work in parallel on ambitious tasks for hours or days' and setting up always-on agents on schedules/triggers, all accessible from Cursor's interface spanning terminal, Slack, and GitHub — directly matching a unified multi-session agent workspace for a lead overseeing parallel work. Missing for 10: independent/hands-on corroboration of the multi-agent dashboard UX, and no detail on cross-session visibility/coordination features specifically framed for engineering-lead oversight.

   • [claimed-docs] “Launch fleets of agents that work in parallel on ambitious tasks for hours or days.”
   • [claimed-docs] “Set up always-on agents that run on schedules or triggers to build, maintain, and fix your software.”
   • [claimed-docs] “Cursor runs in your terminal, collaborates in Slack, and reviews PRs in GitHub.”
   • [claimed-docs] “Accelerate development by handing off tasks to Cursor, while you focus on making decisions.”
   • [claimed-docs] “Agents use their own computers to build, test, and demo features end to end for you to review.”

   proof ↗⚑ flag

   GitHub Copilot✓fullclaimed8/10

   Docs describe a unified control page/desktop workspace to launch, track, and manage multiple agent sessions (Copilot, Claude, Codex) with progress tracking, review, merge, and governance/audit logs from one control plane, directly matching the story. Missing for 10: independent hands-on validation of the multi-agent dashboard experience and any reported friction managing many concurrent sessions.

   • [claimed-docs] “Assign tasks to agents like Copilot, Claude by Anthropic, and OpenAI Codex, and let them plan, explore, and execute work autonomously in the…”
   • [claimed-docs] “Launch work from GitHub, track progress across multiple agents, review changes, and merge completed work—all from one desktop workspace buil…”
   • [claimed-docs] “Use one centralized control page to jump between agent sessions, check progress, and stay in control without losing your place.”
   • [claimed-docs] “Track activity with detailed audit logs and enforce governance by managing agents from a single control plane.”

   proof ↗⚑ flag

Terminal workflow

1. developerRun a coding agent locally from my terminal

   weight 3 · round drawn
   Cursor✓fullprobed7/10

   Cursor ships an official CLI (cursor.com/cli) with a documented install command (curl ... | bash) and docs explicitly state 'Cursor runs in your terminal', confirming a local terminal-based agent capability alongside its IDE. Missing for 10: independent/hands-on verification of terminal agent usage and deeper CLI usage documentation beyond the install step.

   • [probe] “official CLI documented at https://cursor.com/cli”
   • [claimed-docs] “curl https://cursor.com/install -fsS | bash”
   • [claimed-docs] “Cursor runs in your terminal, collaborates in Slack, and reviews PRs in GitHub.”

   proof ↗⚑ flag

   GitHub Copilot✓fullprobed7/10

   GitHub Copilot CLI is officially documented as letting developers use Copilot directly from the terminal, including voice-to-text prompting, and is confirmed installable per docs and probe evidence. missing for 10: independent hands-on validation of the CLI agent's local execution/quality, and more detail on its autonomous/agentic capabilities (vs. just chat) within the terminal.

   • [claimed-docs] “The command-line interface (CLI) for GitHub Copilot allows you to use Copilot directly from your terminal.”
   • [claimed-docs] “As an alternative to typing, you can speak your prompt.”
   • [probe] “official CLI documented at https://docs.github.com/en/copilot/how-tos/copilot-cli/set-up-copilot-cli/install-copilot-cli”
   • [claimed-docs] “GitHub Copilot is also supported in terminals through GitHub CLI and as a chat integration in Windows Terminal Canary.”

   proof ↗⚑ flag

2. developerRun the agent non-interactively in scripts for workflow automation

   weight 2 · round to Cursor
   Cursor~partialprobed6/10

   Cursor ships an official CLI (cursor-probe-1, cursor-docs-14) and documents 'always-on agents that run on schedules or triggers to build, maintain, and fix your software' (cursor-docs-9), which implies non-interactive/automated agent execution suitable for scripts/CI. However, there is no concrete documentation of CLI flags, headless/print modes, exit codes, or scripting examples, nor independent hands-on confirmation of this workflow. Missing for 10: explicit CLI non-interactive flag/usage docs, examples of piping/scripting the agent, and independent verification that scheduled/triggered agents work as scripted automation.

   • [probe] “official CLI documented at https://cursor.com/cli”
   • [claimed-docs] “curl https://cursor.com/install -fsS | bash”
   • [claimed-docs] “Set up always-on agents that run on schedules or triggers to build, maintain, and fix your software.”

   proof ↗⚑ flag

   GitHub Copilot~partialclaimed5/10

   Copilot CLI (docs-26) lets you invoke Copilot from a terminal, and Copilot cloud agent 'Automations' (docs-15, docs-33) can be triggered on a schedule or repository events, which supports some non-interactive workflow automation. However, there is no direct evidence of a documented headless/non-interactive CLI flag (e.g., a scripted prompt-and-exit mode with exit codes) for running Copilot CLI itself inside arbitrary scripts. missing for 10: explicit CLI non-interactive/scripting mode docs, evidence of exit-code/output-parsing support for pipelines, independent hands-on confirmation of script usage.

   • [claimed-docs] “The command-line interface (CLI) for GitHub Copilot allows you to use Copilot directly from your terminal.”
   • [claimed-docs] “Automations let you run Copilot cloud agent automatically, on a schedule or in response to events in a repository.”
   • [claimed-docs] “Set up an automation to run Copilot automatically, on a schedule or in response to events such as an issue being opened.”
   • [claimed-docs] “With Copilot cloud agent, GitHub Copilot can work independently in the background to complete tasks, just like a human developer.”

   proof ↗⚑ flag

1. ai-native userDo everything through the API that I can do in the UI

   weight 2 · round to GitHub Copilot
   Cursor—none0/10

   The evidence pack shows no public API for Cursor; it mentions an official CLI and MCP (for connecting external tools INTO Cursor), but nothing about a programmatic interface exposing Cursor's own UI capabilities (agents, plan mode, review, etc.) for external control.

   ⚑ flag

   GitHub Copilot~partialprobed3/10

   Copilot offers a CLI (docs-26, probe-4) and MCP server integration (docs-25) that give some programmatic access to Copilot/GitHub features, but there is no evidence of a comprehensive public API/OpenAPI spec covering the full range of UI capabilities (chat, agent mode, cloud agent, code review) — the openapi probe returned 404 for all candidate endpoints (probe-3). Missing for 10: a documented REST/GraphQL API exposing chat, agent-mode edits, cloud-agent orchestration, and code review equivalently to the UI, and any independent confirmation that CLI/MCP covers full feature parity.

   • [claimed-docs] “The command-line interface (CLI) for GitHub Copilot allows you to use Copilot directly from your terminal.”
   • [probe] “official CLI documented at https://docs.github.com/en/copilot/how-tos/copilot-cli/set-up-copilot-cli/install-copilot-cli”
   • [claimed-docs] “Learn how to use the GitHub Model Context Protocol (MCP) server to interact with repositories, issues, pull requests, and other GitHub featu…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.github.com/openapi.json, https://docs.github.com/swagger.json, https://docs.github.com/…”

   proof ↗⚑ flag

2. ai-native userExport all of my data in open formats and leave

   weight 3 · round drawn
   Cursor—none0/10

   No evidence in the pack addresses data export, portability, or open-format data extraction from Cursor; being built on VS Code (a fork) doesn't itself guarantee user data/settings export tooling is documented anywhere here.

   ⚑ flag

   GitHub Copilot—none0/10

   No evidence in the pack describes any data export feature, open-format export, or account data portability mechanism for GitHub Copilot; documentation covers coding, agents, MCP, and models but nothing about exporting user data or leaving the platform with your data intact.

   ⚑ flag

3. ai-native userRead the product's source under an open license

   weight 2 · round drawn
   Cursor—none0/10

   Cursor is known to be closed-source (a proprietary VS Code fork), and the evidence pack contains no mention of any open-source license or public repository for Cursor's source code; all references are to product docs, features, or community complaints unrelated to licensing.

   ⚑ flag

   GitHub Copilot—none0/10

   GitHub Copilot is closed-source proprietary software; no evidence in the pack shows any open-license source availability, and community discussion instead focuses on training-data/licensing concerns, not the product's own source code being open.

   ⚑ flag

Authentication

1. developerAuthenticate with an API key instead of an account login

   weight 2 · round drawn
   Cursor—none0/10

   No evidence in the pack describes API key authentication as an alternative to account login for Cursor; docs reference OAuth-based MCP authentication and account-based login flows only.

   ⚑ flag

   GitHub Copilot—none0/10

   No evidence in the pack describes API-key authentication as an alternative to account login; Copilot's auth model is tied to GitHub account/subscription (IDE sign-in, CLI, etc.) with no mention of API keys for developer access.

   ⚑ flag

2. engineering-leadAuthenticate through an enterprise identity or cloud platform for compliance and scalability

   weight 2 · round drawn
   Cursor—none0/10

   The evidence pack shows Cursor has enterprise admin controls for MCP servers but contains no evidence of SSO/SAML integration, enterprise identity provider authentication (e.g., Okta, Azure AD, Google Workspace), or cloud platform login for compliance purposes. This is a fair and applicable axis for a widely-adopted dev tool sold to enterprises, so absence of evidence yields 'none' rather than 'na'.

   • [claimed-docs] “Enterprise admins can control which MCP servers users may run from the Cursor dashboard.”

   proof ↗⚑ flag

   GitHub Copilot—none0/10

   No evidence in the pack addresses SSO/SAML, enterprise identity providers (e.g., Okta, Azure AD), or cloud platform authentication for Copilot; docs cover agents, MCP, models, and governance features but not identity/authentication for enterprise compliance. Missing for 10: SSO/SAML integration docs, enterprise IdP support (Azure AD/Okta), any mention of authentication/compliance certifications tied to identity federation.

   ⚑ flag

3. developerSign in with my existing product subscription plan to use the coding agent

   weight 2 · round to GitHub Copilot
   Cursor—none0/10

   The evidence pack describes Cursor's agent features, MCP integrations, and installation steps, but contains no documentation or confirmation that users authenticate with an existing subscription plan to access the coding agent (only tangential community chatter about login policy hallucinations). Missing for 10: explicit account/subscription sign-in flow docs, plan-tier access confirmation, and any first-party statement linking subscription plan to agent usage.

   • [community] “Cursor's AI support agent hallucinated a single-device login policy, telling a user this was intentional. A Cursor developer later clarified…”

   proof ↗⚑ flag

   GitHub Copilot✓fullclaimed7/10

   Docs show that Copilot's cloud/coding agent features (agent mode, cloud agent, agent apps) are powered by and included in a user's existing Copilot subscription, e.g. 'Agent apps let you use partner-built agents directly in your workflows on GitHub, powered by your Copilot subscription' and 'Access to Cloud agent and code review' listed as plan features, meaning no separate sign-up is needed beyond the existing subscription/login. Missing for 10: explicit tier-by-tier sign-in flow documentation and independent user confirmation that no extra account creation is required beyond the existing GitHub/Copilot login.

   • [claimed-docs] “Agent apps let you use partner-built agents directly in your workflows on GitHub, powered by your Copilot subscription.”
   • [claimed-docs] “Access to Cloud agent and code review”
   • [claimed-docs] “With Copilot cloud agent, GitHub Copilot can work independently in the background to complete tasks, just like a human developer.”
   • [claimed-docs] “Launch work from GitHub, track progress across multiple agents, review changes, and merge completed work—all from one desktop workspace buil…”

   proof ↗⚑ flag

4. developerSign in with a personal account to get free-tier access without managing API keys

   weight 1 · round drawn
   Cursor—none0/10

   The evidence pack contains no documentation or first-party description of a sign-in flow that grants free-tier access without requiring API keys; only tangential community mentions of account workarounds for usage limits exist. Missing for 10: any docs on account creation/sign-in, free-tier terms, or explicit no-API-key requirement.

   • [community] “Cursor is caught in a cat-and-mouse game against workarounds where users create new accounts to get unlimited use; a repo enabling this (cur…”

   proof ↗⚑ flag

   GitHub Copilot—none0/10

   The evidence pack contains no mention of a free tier, personal GitHub account sign-in flow, or API-key-free authentication for Copilot; all docs items describe features (agent mode, MCP, code review) but never address account-based free-tier access or pricing/sign-in mechanics.

   ⚑ flag

Model choice

1. developerLet the tool automatically pick the best model for each task

   weight 1 · round to GitHub Copilot
   Cursor—none0/10

   The evidence shows Cursor lets developers manually choose among multiple models (OpenAI, Anthropic, Gemini, etc.) but nothing indicates an automatic 'best model for the task' selection feature. missing for 10: any documentation or claim of an auto-select/router feature that picks models per task, evidence of cost/performance-based automatic routing.

   • [claimed-docs] “Choose between every cutting-edge model from OpenAI, Anthropic, Gemini, SpaceXAI, and Cursor.”

   proof ↗⚑ flag

   GitHub Copilot✓fullclaimed7/10

   GitHub's own docs explicitly state Copilot can 'Automatically select the best model for each task' (docs-17), alongside supporting claims about multiple models optimized for speed/accuracy/cost (docs-7, docs-30). Missing for 10: independent/hands-on verification that auto-selection actually works well in practice, and details on how/when it triggers vs manual model choice.

   • [claimed-docs] “Automatically select the best model for each task.”
   • [claimed-docs] “Choose from leading LLMs optimized for speed, accuracy, or cost.”
   • [claimed-docs] “GitHub Copilot supports multiple AI models, each with different strengths. Some prioritize speed and cost-efficiency, while others are optim…”

   proof ↗⚑ flag

2. developerChoose which underlying AI model powers my session from multiple providers

   weight 2 · round drawn
   Cursor✓fullclaimed8/10

   cursor-docs-7 confirms Cursor lets developers choose between models from multiple providers (OpenAI, Anthropic, Gemini, and Cursor's own), directly matching the story. Missing for 10: independent hands-on verification of per-session model switching UI/behavior and pricing implications tied to model choice.

   • [claimed-docs] “Choose between every cutting-edge model from OpenAI, Anthropic, Gemini, SpaceXAI, and Cursor.”

   proof ↗⚑ flag

   GitHub Copilot✓fullclaimed8/10

   GitHub's own docs explicitly state Copilot supports multiple AI models from different providers (e.g., Claude, OpenAI Codex) and lets users 'choose from leading LLMs optimized for speed, accuracy, or cost,' with a dedicated supported-models reference page and an auto-select option. This directly matches the story of choosing the underlying model per session. Missing for 10: independent/hands-on community confirmation of the model-picker UI in practice and details on per-session persistence of the choice.

   • [claimed-docs] “Choose from leading LLMs optimized for speed, accuracy, or cost.”
   • [claimed-docs] “GitHub Copilot supports multiple AI models, each with different strengths. Some prioritize speed and cost-efficiency, while others are optim…”
   • [claimed-docs] “Assign tasks to agents like Copilot, Claude by Anthropic, and OpenAI Codex, and let them plan, explore, and execute work autonomously in the…”
   • [claimed-docs] “Automatically select the best model for each task.”

   proof ↗⚑ flag

1. ai-native userChoose where my data is stored (region/residency)

   weight 2 · round drawn
   Cursor—none0/10

   No evidence in the pack mentions data residency, region selection, or storage location controls for Cursor; the docs snippets cover agents, MCP, and integrations but nothing about choosing data storage region. Missing for 10: any mention of regional data residency options, enterprise data location controls, or compliance documentation addressing storage jurisdiction.

   ⚑ flag

   GitHub Copilot—none0/10

   No evidence in the pack mentions data residency, region selection, or geographic storage controls for GitHub Copilot; only data-training opt-out is mentioned, which is a different concern.

   ⚑ flag

2. ai-native userPrevent my data from being used to train AI models

   weight 3 · round to GitHub Copilot
   Cursor—none0/10

   The evidence pack contains no documentation of a privacy mode, opt-out of training, or data-retention controls for Cursor; all cited docs cover unrelated features (agents, MCP, integrations) and community threads are unrelated to training-data privacy.

   ⚑ flag

   GitHub Copilot~partialcommunity6/10

   GitHub's docs explicitly state individual subscribers can opt out of having their data used for AI model training at any time (github-copilot-docs-12), directly satisfying the story's core ask. However, the evidence pack lacks detail on how opt-out is enforced, whether it covers all Copilot data flows (e.g., telemetry, code review, agents), and community commentary voices skepticism (not concrete contradiction) about whether enterprise code can truly be excluded. Missing for 10: independent verification that opt-out is honored in practice, clarity on enterprise/org-level data-use guarantees, and details on scope of what 'training' opt-out actually excludes.

   • [claimed-docs] “Individual subscribers can opt out of having their data used for AI model training at any time”
   • [community] “Well, this can impose a serious risk to companies and their cloud strategy based on GitHub. Can these enterprises really make sure that thei…”

   proof ↗⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round to GitHub Copilot
   Cursor—none0/10

   The evidence pack contains no documentation of data retention settings, deletion controls, privacy dashboard, or data handling policies for Cursor; only unrelated docs on features (MCP, agents, integrations) and community complaints about bugs/pricing are present. Missing for 10: any first-party privacy policy docs, retention period settings, data deletion request mechanism, or enterprise data controls.

   ⚑ flag

   GitHub Copilot~partialcommunity5/10

   GitHub Copilot docs confirm individual subscribers can opt out of AI model training data use at any time, giving some control over data usage, but there is no documented self-service mechanism for deleting stored chat/history data or explicit retention period controls. Community commentary also raises unresolved skepticism about enterprise assurances that code won't be used for training. Missing for 10: explicit data-deletion tooling, documented retention windows, and enterprise-level deletion guarantees beyond opt-out.

   • [claimed-docs] “Individual subscribers can opt out of having their data used for AI model training at any time”
   • [community] “Well, this can impose a serious risk to companies and their cloud strategy based on GitHub. Can these enterprises really make sure that thei…”

   proof ↗⚑ flag

4. ai-native userOpt out of telemetry and usage tracking

   weight 2 · round to GitHub Copilot
   Cursor—none0/10

   The evidence pack contains no mention of telemetry settings, privacy controls, or usage-tracking opt-out mechanisms; docs only cover unrelated features like MCP, agents, and integrations. Missing for 10: any privacy policy or settings documentation, telemetry opt-out toggle, or usage data collection disclosure.

   ⚑ flag

   GitHub Copilot~partialcommunity4/10

   Docs confirm individual subscribers can opt out of having their code data used for AI model training, but this is narrower than opting out of telemetry/usage tracking broadly, and no evidence describes a general telemetry opt-out toggle. Community commentary (comm-5) even notes agreeing to 'additional telemetry terms' during a preview with no opt-out mentioned. Missing for 10: explicit telemetry/usage-tracking opt-out setting, documentation distinguishing telemetry from training-data opt-out, and independent confirmation that opting out actually stops telemetry collection.

   • [claimed-docs] “Individual subscribers can opt out of having their data used for AI model training at any time”
   • [community] “Gigantic caveat: 'I agree to these additional telemetry terms as part of the technical preview.'”

   proof ↗⚑ flag

Data governance

1. engineering-leadOpt out of having my code and prompts used for AI model training

   weight 1 · round to GitHub Copilot
   Cursor—none0/10

   The evidence pack contains no mention of privacy settings, opt-out of training, or data usage policies for Cursor; all docs entries relate to unrelated features (agents, MCP, integrations) and community items focus on bugs/pricing/model sourcing, not training data controls.

   ⚑ flag

   GitHub Copilot~partialcommunity6/10

   Docs explicitly state individual subscribers can opt out of AI model training at any time (github-copilot-docs-12), which covers a developer-level version of this story. However, evidence does not show an org-wide/enterprise admin policy control that an engineering-lead could set organization-wide, and one community comment expresses skepticism about enterprise assurance (not a concrete contradiction). Missing for 10: enterprise/org-level policy documentation, admin-console controls, and independent verification of enforcement.

   • [claimed-docs] “Individual subscribers can opt out of having their data used for AI model training at any time”
   • [community] “Well, this can impose a serious risk to companies and their cloud strategy based on GitHub. Can these enterprises really make sure that thei…”

   proof ↗⚑ flag

Pr review

1. developerHave the agent stage changes, write commit messages, create branches, and open pull requests

   weight 3 · round to GitHub Copilot
   Cursor~partialclaimed4/10

   Docs show GitHub/GitLab integration and agents that build/test/demo work end-to-end for review (cursor-docs-6, cursor-docs-10, cursor-docs-12), implying some git-workflow automation, but there's no explicit documentation of the agent staging changes, writing commit messages, creating branches, or opening pull requests. missing for 10: explicit commit-message generation, branch creation, PR-opening workflow documentation, and any hands-on confirmation these steps work end-to-end.

   • [claimed-docs] “Work with GitHub, GitLab, Azure DevOps, Bitbucket, JetBrains, Slack, Linear, and more”
   • [claimed-docs] “Cursor runs in your terminal, collaborates in Slack, and reviews PRs in GitHub.”
   • [claimed-docs] “Agents use their own computers to build, test, and demo features end to end for you to review.”
   • [claimed-docs] “Inspect diffs, run checks, and catch problems before you merge”

   proof ↗⚑ flag

   GitHub Copilot✓fullclaimed7/10

   GitHub Copilot's cloud/background agent is documented to work independently on tasks, make changes on existing PRs via @copilot mentions, and complete work 'just like a human developer,' which in GitHub's workflow model entails committing changes and opening/updating pull requests (docs-31, docs-32, docs-8, docs-14). However, explicit documentation of branch creation and commit-message authorship mechanics is not directly cited, and there is no independent/hands-on verification of the PR-opening workflow. Missing for 10: explicit branch-creation documentation, independent hands-on confirmation of commit/PR flow, and detail on staging-changes granularity.

   • [claimed-docs] “With Copilot cloud agent, GitHub Copilot can work independently in the background to complete tasks, just like a human developer.”
   • [claimed-docs] “Mention `@copilot` in a comment on an existing pull request to ask it to make changes.”
   • [claimed-docs] “Launch work from GitHub, track progress across multiple agents, review changes, and merge completed work—all from one desktop workspace buil…”
   • [claimed-docs] “Use one centralized control page to jump between agent sessions, check progress, and stay in control without losing your place.”
   • [claimed-docs] “Set up an automation to run Copilot automatically, on a schedule or in response to events such as an issue being opened.”

   proof ↗⚑ flag

2. developerGet automatic code review with contextual feedback on every pull request

   weight 3 · round drawn
   Cursor✓fullclaimed7/10

   Cursor's docs explicitly claim it 'reviews PRs in GitHub' and can 'inspect diffs, run checks, and catch problems before you merge,' directly matching automated PR review with contextual feedback, backed by GitHub/GitLab/Bitbucket integration claims. missing for 10: independent/hands-on verification of review quality, details on triggering on every PR automatically, and no community corroboration of this specific feature.

   • [claimed-docs] “Cursor runs in your terminal, collaborates in Slack, and reviews PRs in GitHub.”
   • [claimed-docs] “Inspect diffs, run checks, and catch problems before you merge”
   • [claimed-docs] “Work with GitHub, GitLab, Azure DevOps, Bitbucket, JetBrains, Slack, Linear, and more”

   proof ↗⚑ flag

   GitHub Copilot✓fullclaimed7/10

   GitHub Copilot's docs explicitly describe automated PR code review with contextual feedback, suggested fixes, and severity labeling (High/Medium/Low) for prioritization, plus 'Access to Cloud agent and code review' as a plan feature. This directly matches the story's request for automatic, contextual PR review feedback. Missing for 10: independent/hands-on community evidence specifically validating the PR-review feature's accuracy or usefulness (community citations mostly discuss code completion, not the review feature) and detail on review-triggering automation reliability.

   • [claimed-docs] “GitHub Copilot can review your code and provide feedback. Where possible, Copilot's feedback includes suggested changes which you can apply …”
   • [claimed-docs] “Copilot labels each comment with a severity level of "High," "Medium," or "Low" to help you prioritize the issues it finds based on their im…”
   • [claimed-docs] “Access to Cloud agent and code review”

   proof ↗⚑ flag

3. developerInspect diffs and run checks to catch problems before merging

   weight 3 · round to GitHub Copilot
   Cursor~partialclaimed5/10

   cursor-docs-4 explicitly claims the capability ('Inspect diffs, run checks, and catch problems before you merge') and cursor-docs-10/12 support a broader PR review workflow, but there is no independent or hands-on corroboration of diff inspection or check-running in practice, and community evidence focuses on unrelated bugs/pricing rather than this feature. missing for 10: independent verification of diff review UI, details on what 'checks' run (tests/linters/CI), and hands-on confirmation of pre-merge workflow.

   • [claimed-docs] “Inspect diffs, run checks, and catch problems before you merge”
   • [claimed-docs] “Cursor runs in your terminal, collaborates in Slack, and reviews PRs in GitHub.”
   • [claimed-docs] “Agents use their own computers to build, test, and demo features end to end for you to review.”

   proof ↗⚑ flag

   GitHub Copilot✓fullclaimed8/10

   Copilot provides code review with inline suggested changes and severity-labeled comments (docs-28, docs-29), integrated with PR diffs, plus Autofix for vulnerability detection (docs-13) and agent mode validation of files (docs-22). This directly supports inspecting diffs and catching problems pre-merge. Missing for 10: independent/hands-on evidence of the code-review feature's real-world accuracy and no explicit mention of running CI/test checks as part of the flow.

   • [claimed-docs] “GitHub Copilot can review your code and provide feedback. Where possible, Copilot's feedback includes suggested changes which you can apply …”
   • [claimed-docs] “Copilot labels each comment with a severity level of "High," "Medium," or "Low" to help you prioritize the issues it finds based on their im…”
   • [claimed-docs] “GitHub Copilot Autofix provides contextual explanations and code suggestions to help developers fix vulnerabilities in code”
   • [claimed-docs] “Copilot in your editor does it all, from explaining concepts and completing code, to proposing edits and validating files with agent mode.”
   • [claimed-docs] “Access to Cloud agent and code review”

   proof ↗⚑ flag

Safe execution

1. engineering-leadControl which external tools and integrations the agent is allowed to access

   weight 2 · round drawn
   Cursor✓fullclaimed8/10

   Docs show enterprise admins can restrict which MCP servers users may run from the Cursor dashboard, and users can toggle individual servers on/off, giving engineering leads direct control over external tool/integration access. Missing for 10: independent/hands-on corroboration of the admin dashboard controls and finer-grained per-tool permission examples beyond MCP servers.

   • [claimed-docs] “Enterprise admins can control which MCP servers users may run from the Cursor dashboard.”
   • [claimed-docs] “Toggle servers on/off without removing them”
   • [claimed-docs] “Model Context Protocol (MCP) enables Cursor to connect to external tools and data sources.”
   • [claimed-docs] “Configure custom MCP servers with a JSON file”

   proof ↗⚑ flag

   GitHub Copilot✓fullclaimed8/10

   GitHub Copilot provides explicit admin controls to allow-list MCP servers developers can access ('Control which MCP servers developers can access from their IDEs, and use allow lists to prevent unauthorized access'), plus a centralized control plane with audit logs for governance over agents. This directly matches the engineering-lead's need to restrict external tool/integration access. Missing for 10: independent/hands-on verification of the allow-list enforcement in practice, and more granular detail on per-tool (vs per-MCP-server) restriction scope.

   • [claimed-docs] “Control which MCP servers developers can access from their IDEs, and use allow lists to prevent unauthorized access.”
   • [claimed-docs] “Track activity with detailed audit logs and enforce governance by managing agents from a single control plane.”
   • [claimed-docs] “Connect MCP servers to Copilot Chat to share context from other applications.”

   proof ↗⚑ flag

2. engineering-leadHave the agent operate inside a sandbox when interacting with code, tools, and network resources

   weight 2 · round to GitHub Copilot
   Cursor—none0/10

   The evidence pack contains no mention of sandboxing, isolated execution environments, or network/tool restriction controls for the agent; docs describe agents using 'their own computers' but give no detail on containment/sandboxing mechanisms. Missing for 10: any documentation of a sandbox/isolation feature, network egress controls, or filesystem restriction for agent actions.

   • [claimed-docs] “Agents use their own computers to build, test, and demo features end to end for you to review.”

   proof ↗⚑ flag

   GitHub Copilot✓fullclaimed8/10

   Docs explicitly state that Cloud and local sandboxes provide isolated execution environments letting Copilot safely interact with code, tools, filesystem, and network resources, either locally or in fully isolated cloud environments, with additional governance controls like MCP server allow lists and audit logs. Missing for 10: independent/hands-on verification of sandbox isolation guarantees and no detail on sandbox escape/limits.

   • [claimed-docs] “Cloud and local sandboxes provide isolated execution environments that let Copilot safely interact with code, tools, filesystem, and network…”
   • [claimed-docs] “Control which MCP servers developers can access from their IDEs, and use allow lists to prevent unauthorized access.”
   • [claimed-docs] “Track activity with detailed audit logs and enforce governance by managing agents from a single control plane.”

   proof ↗⚑ flag

Security checks

1. engineering-leadSee license and public-code matching references for AI-suggested code

   weight 1 · round to GitHub Copilot
   Cursor—none0/10

   No evidence anywhere in the pack mentions license detection, public code matching, provenance references, or IP attribution for AI-suggested code; docs focus on repo navigation, diffs, agents, and integrations, none of which addresses license/code-match transparency.

   ⚑ flag

   GitHub Copilot~partialcommunity5/10

   GitHub Copilot documents a public-code matching feature that searches public GitHub repos for matches to a suggestion (docs-11), which is the closest evidence to the story's ask. However, the evidence pack gives no detail on how license attribution is actually surfaced to an engineering lead, and community discussion raises real concerns about verbatim/near-verbatim reproduction and licensing risk (comm-12, comm-13, comm-14, comm-16), with only partial rebuttal (comm-17) — indicating the feature's coverage and reliability for license-safety review is limited. Missing for 10: detailed docs on license display/attribution UI, audit/reporting workflow for engineering leads, and independent verification that the matching feature reliably flags copyleft/licensed snippets.

   • [claimed-docs] “This feature searches across public GitHub repositories for code that matches a Copilot suggestion.”
   • [community] “It certainly seems to be a laundering enabler. Say that you want to un-GPL-ify some famous copylefted code... you type a first innocuous cha…”
   • [community] “The potential inclusion of GPL'd code, and potentially even unlicensed code, is making me wary of using it. Fair Use doesn't exist here and …”
   • [community] “'We found that about 0.1% of the time, the suggestion may contain some snippets that are verbatim from the training set.' If it's spitting o…”
   • [community] “I just tested it myself on a random c file... it reproduced his full code verbatim from just the function header so clearly it does regurgit…”
   • [community] “It prints this code because you have it open in another editor tab. Wish people who don't know at all how it works stopped acting all outrag…”

   proof ↗⚑ flag

2. developerGet contextual explanations and automatic fixes for security vulnerabilities

   weight 2 · round to GitHub Copilot
   Cursor—none0/10

   The evidence pack shows general code review/diff-inspection features (cursor-docs-4) and broad agent capabilities, but nothing specifically documents contextual security vulnerability explanations or automated security fixes. Missing for 10: any mention of vulnerability detection, security scanning integration, or CVE/security-specific fix suggestions.

   ⚑ flag

   GitHub Copilot~partialclaimed6/10

   GitHub Copilot Autofix is explicitly documented to provide 'contextual explanations and code suggestions to help developers fix vulnerabilities in code' and Copilot code review adds severity-labeled feedback with suggested fixes, directly matching the story. However, this is first-party documentation only with no independent/hands-on validation of Autofix's real-world effectiveness, and no detail on scope/limitations (e.g., which languages, integration with Advanced Security). missing for 10: independent corroboration of Autofix accuracy, hands-on developer reports validating the fix quality, details on prerequisites/limitations of the feature.

   • [claimed-docs] “GitHub Copilot Autofix provides contextual explanations and code suggestions to help developers fix vulnerabilities in code”
   • [claimed-docs] “GitHub Copilot can review your code and provide feedback. Where possible, Copilot's feedback includes suggested changes which you can apply …”
   • [claimed-docs] “Copilot labels each comment with a severity level of "High," "Medium," or "Low" to help you prioritize the issues it finds based on their im…”

   proof ↗⚑ flag