Codex vs GitHub Copilot

Agent access

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

   weight 2 · round to GitHub Copilot
   Codex~partialprobed4/10

   A dedicated llms.txt file is absent (404 at platform.openai.com/llms.txt), but Codex does publish machine-readable markdown docs (learn.chatgpt.com/docs/codex/cli.md) confirmed reachable by probe, which is an agent-friendly doc format an AI agent could be pointed at. Missing for 10: a standard llms.txt manifest, evidence of agents actually being pointed at these docs, and confirmation across all doc pages (docs/codex.md also 404s).

   • [probe] “PROBE llms.txt: HTTP 404 at https://platform.openai.com/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://platform.openai.com/docs/codex.md”
   • [probe] “official CLI documented at https://learn.chatgpt.com/docs/codex/cli”

   proof ↗⚑ 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 Codex
   Codex✓fullclaimed8/10

   Codex CLI explicitly documents non-interactive execution via `codex exec` for use in repeatable workflows, scripts, and CI/CD pipelines (codex-docs-19, codex-docs-32), and permissions/sandbox controls can be configured for unattended runs (codex-docs-17, codex-docs-39). Missing for 10: no independent case study or CI provider (e.g. GitHub Actions) integration example, and no explicit exit-code/output-format spec for CI parsing.

   • [claimed-docs] “Run a non-interactive command in a repeatable workflow.”
   • [claimed-docs] “Compose with scripts and CI: Use Codex interactively or call codex exec from repeatable workflows and pipelines.”
   • [claimed-docs] “Choose when Codex can edit files or run commands without asking, and inspect the active sandbox and writable roots before you continue.”
   • [claimed-docs] “Set the boundaries for each run — /permissions: Choose when Codex can edit files or run commands without asking, and inspect the active sand…”

   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 drawn
   Codex✓fullclaimed9/10

   Codex CLI explicitly supports adding local/remote MCP servers via `codex mcp add`, inspecting available tools before use, and viewing active servers via `/mcp`; this configuration is shared across ChatGPT desktop app, CLI, and IDE extension. Docs also describe using MCP to connect to third-party tools like browsers or Figma. Missing for 10: independent hands-on verification of MCP tool usage in a real session beyond first-party docs.

   • [claimed-docs] “Add local or remote MCP servers, authenticate when needed, and inspect the tools available to the current session before Codex uses them.”
   • [claimed-docs] “The ChatGPT desktop app, Codex CLI, and IDE extension share this configuration. Once you configure your MCP servers, you can switch among th…”
   • [claimed-docs] “Connect external tools with MCP — codex mcp: Add local or remote MCP servers, authenticate when needed, and inspect the tools available to t…”
   • [claimed-docs] “Model Context Protocol (MCP) connects models to tools and context. Use it to give ChatGPT or Codex access to third-party documentation, or t…”
   • [claimed-docs] “codex mcp add <server-name> --env VAR1=VALUE1 --env VAR2=VALUE2 -- <stdio server-command>”
   • [claimed-docs] “In the `codex` TUI, use `/mcp` to see your active MCP servers.”

   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 userConnect an agent via an official MCP server

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

   Codex explicitly supports running itself as an MCP server (codex mcp-server) so other MCP clients can connect, but OpenAI's own docs mark this interface 'experimental' and now 'deprecated', pointing users to a newer 'Codex app server' as the recommended replacement. This is a genuine server-mode capability (not just Codex-as-MCP-client), but the deprecation and lack of independent hands-on confirmation of the replacement's stability keep it from a full verdict. Missing for 10: independent corroboration that the current 'Codex app server' MCP mode works reliably in production, and clearer first-party documentation of its interface now that the original is deprecated.

   • [github] “Codex MCP Server Interface [experimental]: a JSON-RPC API that runs over the Model Context Protocol (MCP) transport to control a local Codex…”
   • [claimed-docs] “codex mcp-server is deprecated. Use the Codex app server instead. ... This page documents the deprecated command for existing integrations. …”
   • [claimed-docs] “Add local or remote MCP servers, authenticate when needed, and inspect the tools available to the current session before Codex uses them.”

   proof ↗⚑ flag

   GitHub Copilot✓fullclaimed7/10

   GitHub documents an official GitHub MCP server (docs-25) that exposes repositories, issues, PRs, and other GitHub features via MCP, which other agents (not just Copilot itself) can connect to — this is a first-party server, not just Copilot's client-side MCP consumption. Missing for 10: independent/hands-on confirmation of third-party agents successfully connecting to this server, and details on server versioning/maturity.

   • [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] “Copilot works where you do—in GitHub, your IDE, the CLI, project tools, chat apps, and custom MCP servers.”
   • [claimed-docs] “Control which MCP servers developers can access from their IDEs, and use allow lists to prevent unauthorized access.”

   proof ↗⚑ flag

5. ai-native userUse an official CLI

   weight 2 · round to Codex
   Codex✓fullprobed9/10

   Codex ships an official, well-documented CLI (npm install -g @openai/codex) with rich agentic capabilities: local repo editing, exec/non-interactive scripting, MCP support, subagents, image input, sandbox/permissions control, cloud task delegation, and shell completions — all first-party documented and confirmed via GitHub repo and docs. Missing for 10: independent hands-on benchmarking specifically of CLI workflows (community evidence focuses mostly on model quality/UX rather than CLI mechanics) and some Linux-specific gaps noted by users.

   • [github] “Codex CLI is a coding agent from OpenAI that runs locally on your computer.”
   • [github] “npm install -g @openai/codex”
   • [claimed-docs] “Inspect code, make changes, run commands, and automate repeatable work without leaving your terminal.”
   • [claimed-docs] “Run a non-interactive command in a repeatable workflow.”
   • [claimed-docs] “Compose with scripts and CI: Use Codex interactively or call codex exec from repeatable workflows and pipelines.”
   • [claimed-docs] “Connect external tools with MCP — codex mcp: Add local or remote MCP servers, authenticate when needed, and inspect the tools available to t…”
   • [claimed-docs] “Split up a larger investigation — subagents: Ask Codex to delegate focused work to specialized agents, then bring their findings back into t…”
   • [claimed-docs] “Choose when Codex can edit files or run commands without asking, and inspect the active sandbox and writable roots before you continue.”
   • [claimed-docs] “Install the Codex CLI with the standalone installer for macOS and Linux.”
   • [probe] “official CLI documented at https://learn.chatgpt.com/docs/codex/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

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

   weight 3 · round to Codex
   Codex~partialcommunity5/10

   Codex documents multiple programmatic entry points — an MCP server interface for JSON-RPC control (though explicitly marked deprecated/experimental in favor of an undocumented 'app server'), a non-interactive `codex exec` mode for scripts/CI, and 'API key' usage — but these come with real caveats: API-key use 'requires additional setup', the flagship gpt-5.3-codex model was reportedly not yet available via API, and the primary MCP server route is deprecated rather than a stable first-class API. missing for 10: a single stable, non-deprecated documented public API surface, confirmation that the current model is API-accessible, and independent corroboration that third parties successfully drive Codex via this API.

   • [github] “You can also use Codex with an API key, but this requires additional setup.”
   • [github] “Codex MCP Server Interface [experimental]: a JSON-RPC API that runs over the Model Context Protocol (MCP) transport to control a local Codex…”
   • [claimed-docs] “codex mcp-server is deprecated. Use the Codex app server instead. ... This page documents the deprecated command for existing integrations. …”
   • [claimed-docs] “Run a non-interactive command in a repeatable workflow.”
   • [claimed-docs] “Compose with scripts and CI: Use Codex interactively or call codex exec from repeatable workflows and pipelines.”
   • [community] “gpt-5.3-codex isn't available on the API yet — 'We are working to safely enable API access soon.'”

   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

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

   weight 2 · round to Codex
   Codex~partialclaimed5/10

   OpenAI's platform docs describe RBAC and project/org-scoped API keys/custom roles, and Codex can authenticate via an API key (codex-gh-4), so scoped credentials are technically available to a Codex-using account. However, none of the evidence ties this RBAC/API-key scoping specifically to configuring or restricting a Codex agent's own permissions — missing for 10: Codex-specific docs on issuing least-privilege keys for agent sessions, guidance on scoping credentials per-task/per-repo, and independent confirmation that this RBAC applies to Codex's own execution rather than just general API access.

   • [claimed-docs] “Role-based access control (RBAC) lets you decide who can do what across your organization and projects—both through the API and in the Dashb…”
   • [github] “You can also use Codex with an API key, but this requires additional setup.”
   • [claimed-docs] “Create a model response — request/response reference with runnable code samples selectable per language: HTTP, Python, TypeScript, Go, Ruby,…”

   proof ↗⚑ 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

8. ai-native userBuild against official SDKs

   weight 2 · round to Codex
   Codex~partialcommunity6/10

   Codex is a coding agent, but the evidence shows a genuine SDK-adjacent surface: the underlying OpenAI Responses API has an official OpenAPI spec and multi-language code samples (Python, TypeScript, Go, Ruby, Java, HTTP, CLI), and Codex integrates via CLI/MCP for programmatic extension. However, there is no evidence of an official Codex-specific SDK (as opposed to the general OpenAI API SDK), and API access for the Codex model itself is explicitly noted as not yet available. missing for 10: a dedicated Codex SDK/library distinct from the general OpenAI Responses API, confirmation that Codex agent capabilities (not just chat completions) are exposed via SDK, independent developer corroboration of building against these SDKs.

   • [claimed-docs] “Create a model response — request/response reference with runnable code samples selectable per language: HTTP, Python, TypeScript, Go, Ruby,…”
   • [github] “A machine-readable description of the OpenAI REST API, authored in OpenAPI 3.1.”
   • [community] “gpt-5.3-codex isn't available on the API yet — 'We are working to safely enable API access soon.'”
   • [claimed-docs] “Add local or remote MCP servers, authenticate when needed, and inspect the tools available to the current session before Codex uses them.”

   proof ↗⚑ 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

9. ai-native userSubscribe to events via webhooks

   weight 2 · round drawn
   Codex—none0/10

   No evidence in the pack mentions webhooks or event subscription capabilities for Codex; the product exposes MCP servers, CLI, and cloud task integrations but nothing about outbound webhook events for AI-native consumers.

   ⚑ 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
   Codex~partialclaimed6/10

   Codex generates AI-driven insights and suggestions specifically about code: it produces prioritized review findings, diffs, and summaries during automated reviews and delegated tasks (codex-docs-5, codex-docs-10, codex-docs-41, codex-docs-45), and can delegate to subagents for deeper investigation (codex-docs-35). However, this is scoped to code/repository data rather than general business or product data insights. Missing for 10: evidence of insight generation over non-code data sources, dashboards, or analytics-style summaries beyond code review findings.

   • [claimed-docs] “Inspect the summary and diff, request a follow-up, or open a pull request when the result is ready.”
   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Review changes before they ship: Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized f…”
   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Split up a larger investigation — subagents: Ask Codex to delegate focused work to specialized agents, then bring their findings back into t…”

   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 to GitHub Copilot
   Codex✓fullclaimed7/10

   Codex cloud supports delegating longer tasks that run in isolated cloud environments in parallel, triggered from GitHub, GitLab, Linear, or Slack, and returning results (diff/PR) when ready — a clear background-automation workflow, and the CLI also supports non-interactive/repeatable workflows for scripted automation. Missing for 10: no documentation of scheduled/cron-style recurring triggers, and no independent/hands-on confirmation that long unattended background runs work reliably (community commentary focuses on interactive model quality/UX rather than background automation specifically).

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Start work in Codex cloud from GitHub pull requests, GitLab merge requests and issues, Linear issues, or Slack channels and threads.”
   • [claimed-docs] “Run tasks in parallel without tying up your local machine.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”
   • [claimed-docs] “Inspect the summary and diff, request a follow-up, or open a pull request when the result is ready.”
   • [claimed-docs] “Run a non-interactive command in a repeatable workflow.”

   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 to GitHub Copilot
   Codex✓fullclaimed8/10

   Codex documents explicit task delegation to its built-in agent, both for long-running cloud tasks ('Delegate a longer task and return when it is ready') and for sub-agent delegation within a session ('Ask Codex to delegate focused work to specialized agents, then bring their findings back into the main terminal session'), backed by detailed CLI/cloud docs. Missing for 10: independent hands-on verification specifically of the subagent delegation flow (community evidence discusses general agent quality/UX but not this feature directly).

   • [claimed-docs] “Delegate a longer task and return when it is ready.”
   • [claimed-docs] “Ask Codex to delegate focused work to specialized agents, then bring their findings back into the main terminal session.”
   • [claimed-docs] “Split up a larger investigation — subagents: Ask Codex to delegate focused work to specialized agents, then bring their findings back into t…”
   • [claimed-docs] “Move work to Codex cloud — codex cloud: Browse active and completed chats, submit work to a configured environment, and apply the result to …”
   • [github] “Codex CLI is a coding agent from OpenAI that runs locally on your computer.”

   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
   Codex✓fullcommunity8/10

   Codex CLI, IDE extension, cloud, and web surfaces are all operated by natural-language prompts/chats — e.g. starting tasks from prompts, resuming chats, delegating subagents, pasting images into the composer, and non-interactive `codex exec` for scripted natural-language instructions — all documented as the primary interaction mode across surfaces. Community threads corroborate heavy real-world use of this conversational/agentic workflow, even amid quality complaints about model performance. missing for 10: independent benchmarking specifically of natural-language command comprehension/robustness (community evidence is about overall agent quality/speed, not NL parsing specifically).

   • [claimed-docs] “Delegate a longer task and return when it is ready.”
   • [claimed-docs] “Start Codex in a repository to explore unfamiliar code, plan a change, edit files, and run your local development tools.”
   • [claimed-docs] “Ask Codex to delegate focused work to specialized agents, then bring their findings back into the main terminal session.”
   • [claimed-docs] “Run a non-interactive command in a repeatable workflow.”
   • [claimed-docs] “`codex resume`: Reopen a recent chat from the current repository, or search across local chats when you need to return to older work.”
   • [claimed-docs] “Bring visual context into the prompt — codex --image: Pass an error screenshot, architecture diagram, or design reference with the first pro…”
   • [github] “Codex CLI is a coding agent from OpenAI that runs locally on your computer.”
   • [community] “Genuinely excited to try this out. I've started using Codex much more heavily in the past two months and honestly, it's been shockingly good…”

   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 to Codex
   Codex~partialclaimed5/10

   The evidence shows OpenAI's general API reference (developers.openai.com) has runnable, per-language code samples with live examples, which an AI-native user could explore. However this is the general OpenAI Responses API reference, not a Codex-specific interactive API reference, and Codex itself is documented as a CLI/agent product rather than an API with its own dedicated reference docs. Missing for 10: a Codex-specific API reference page, evidence of interactivity beyond code-sample selection (e.g., live sandbox execution), and any Codex-specific documentation of this reference.

   • [claimed-docs] “Create a model response — request/response reference with runnable code samples selectable per language: HTTP, Python, TypeScript, Go, Ruby,…”
   • [github] “You can also use Codex with an API key, but this requires additional setup.”

   proof ↗⚑ 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 to Codex
   Codex~partialclaimed4/10

   OpenAI publishes a machine-readable OpenAPI 3.1 spec for its REST API (codex-gh-9) and Codex can be used via that API (codex-gh-4), but the evidence never confirms this spec explicitly covers or is dedicated to Codex-specific endpoints, nor is there a direct 'download spec' link tied to Codex docs. missing for 10: a Codex-specific OpenAPI/spec file, explicit download instructions, or confirmation the general OpenAI OpenAPI spec includes Codex CLI/agent endpoints.

   • [github] “A machine-readable description of the OpenAI REST API, authored in OpenAPI 3.1.”
   • [github] “You can also use Codex with an API key, but this requires additional setup.”
   • [claimed-docs] “Create a model response — request/response reference with runnable code samples selectable per language: HTTP, Python, TypeScript, Go, Ruby,…”

   proof ↗⚑ 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 userTest against a sandbox environment without touching production data

   weight 1 · round to GitHub Copilot
   Codex~partialcommunity6/10

   Codex offers isolated cloud task environments and CLI sandbox controls (writable roots, permission gating) that keep agent actions contained rather than acting directly on a live system, which functions as a sandbox layer for testing changes. However, there's no explicit documentation of test-vs-production data separation, and a community report raises unresolved concerns about the sandbox reading sensitive filesystem data without asking. Missing for 10: explicit production-data isolation guarantees, first-party documentation addressing the raised sandbox-safety concern, and independent verification that isolated environments never touch real prod data.

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Configure the dependencies, tools, variables, and setup steps each repository needs.”
   • [claimed-docs] “Choose when Codex can edit files or run commands without asking, and inspect the active sandbox and writable roots before you continue.”
   • [community] “Does that version of Codex still read sensitive data on your file system without even asking? Just curious. [links to github.com/openai/code…”

   proof ↗⚑ flag

   GitHub Copilot✓fullclaimed7/10

   GitHub Copilot explicitly documents that its cloud and local agent execution occurs in isolated sandboxes ('Cloud and local sandboxes provide isolated execution environments that let Copilot safely interact with code, tools, filesystem, and network resources securely on your local machine or in fully isolated cloud environments'), directly matching the story of testing/agentic work without touching production systems. Missing for 10: independent/hands-on verification of sandbox isolation guarantees, and explicit mention of protecting 'production data' specifically rather than just execution environment isolation.

   • [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] “Automations let you run Copilot cloud agent automatically, on a schedule or in response to events in a repository.”

   proof ↗⚑ flag

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

   weight 2 · round to Codex
   Codex~partialclaimed3/10

   There is a documented OpenAPI 3.1 spec and API reference (codex-gh-9, codex-docs-29) and one concrete example of a deprecation notice (codex mcp-server deprecated in favor of the Codex app server, codex-docs-23), showing some practice of versioning and deprecation. However, there is no comprehensive, documented deprecation policy (timelines, notice periods, version numbering scheme) covering the Codex/OpenAI API generally. Missing for 10: an explicit deprecation policy document, API version numbering scheme, and independent corroboration of adherence to it.

   • [github] “A machine-readable description of the OpenAI REST API, authored in OpenAPI 3.1.”
   • [claimed-docs] “Create a model response — request/response reference with runnable code samples selectable per language: HTTP, Python, TypeScript, Go, Ruby,…”
   • [claimed-docs] “codex mcp-server is deprecated. Use the Codex app server instead. ... This page documents the deprecated command for existing integrations. …”

   proof ↗⚑ 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 to Codex
   Codex~partialclaimed6/10

   Codex supports running multiple cloud tasks in parallel across repos (codex-docs-1, codex-docs-3, codex-docs-6) and delegating focused work to specialized sub-agents within a session (codex-docs-13), which gives some bulk/parallel automation capability. However, there's no explicit evidence of a bulk operation primitive (e.g., batch-apply an action across many files/items/tickets in one command) — the parallelism described is task-level (multiple independent runs) rather than a documented 'operate over N items at once' feature. Missing for 10: explicit bulk/batch API or CLI verb for acting across many items in one invocation, and independent confirmation of large-scale parallel throughput in practice.

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Run tasks in parallel without tying up your local machine.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”
   • [claimed-docs] “Ask Codex to delegate focused work to specialized agents, then bring their findings back into the main terminal session.”
   • [claimed-docs] “Run a non-interactive command in a repeatable workflow.”

   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
   Codex—none0/10

   Codex supports triggering tasks from external events (GitHub/GitLab/Linear/Slack) and running non-interactive workflows, but there is no evidence of a user-defined rules engine that lets users specify arbitrary trigger conditions and automated actions (e.g., 'on X event, do Y') — this is closer to integration hooks than a rules/automation framework. missing for 10: evidence of a rules/trigger definition interface, conditional logic configuration, or event-to-action mapping system that users can author themselves.

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Start work in Codex cloud from GitHub pull requests, GitLab merge requests and issues, Linear issues, or Slack channels and threads.”
   • [claimed-docs] “Run a non-interactive command in a repeatable workflow.”

   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 to GitHub Copilot
   Codex—none0/10

   The evidence shows Codex can run in CI/scripts (codex exec), be triggered from GitHub/GitLab/Slack, and run cloud tasks, but there is no mention of a native recurring/scheduled job or cron-like trigger mechanism within Codex itself. Automation is triggered by external events or manual invocation, not scheduled recurrence.

   • [claimed-docs] “Compose with scripts and CI: Use Codex interactively or call codex exec from repeatable workflows and pipelines.”
   • [claimed-docs] “Run a non-interactive command in a repeatable workflow.”
   • [claimed-docs] “Start work in Codex cloud from GitHub pull requests, GitLab merge requests and issues, Linear issues, or Slack channels and threads.”
   • [claimed-docs] “Move work to Codex cloud — codex cloud: Browse active and completed chats, submit work to a configured environment, and apply the result to …”

   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
   Codex~partialclaimed4/10

   Codex's CLI includes a dedicated review command that inspects diffs/commits without modifying the working tree (codex-docs-10, codex-doces-41/45), and it operates within git repos so changes are inherently versioned and revertible via git; skills/plugins can be packaged as reusable automations (codex-docs-20/42). However, there is no documented mechanism to version, review, or roll back the automations/skills/workflows themselves (e.g., skill version history, rollback of a plugin config, audit trail for automation changes) — only code diffs are reviewed. Missing for 10: explicit versioning of skills/automations, a rollback UI/command for automation configs, and independent evidence of this workflow in practice.

   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Review changes before they ship: Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized f…”
   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Package repeatable instructions as skills, then add plugins to connect Codex to your team's tools and data without leaving the CLI.”
   • [claimed-docs] “Use skills and plugins: Package repeatable instructions as skills, then add plugins to connect Codex to your team's tools and data without l…”

   proof ↗⚑ 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 Codex
   Codex✓fullcommunity8/10

   Codex cloud lets users delegate tasks that run in isolated cloud environments, inspect summaries/diffs, request follow-ups, and open pull requests for review, effectively building/testing/demoing changes end-to-end for user review (codex-docs-1,5,6,7,37). Community commentary corroborates real-world agentic task completion, though with performance/reliability caveats. Missing for 10: independent hands-on verification specifically of the cloud (not CLI) workflow's demo/test artifacts, and no explicit mention of a 'demo' step (e.g., live preview) beyond diff/PR review.

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Inspect the summary and diff, request a follow-up, or open a pull request when the result is ready.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”
   • [claimed-docs] “Start and review work from the web or Codex CLI.”
   • [claimed-docs] “Move work to Codex cloud — codex cloud: Browse active and completed chats, submit work to a configured environment, and apply the result to …”
   • [community] “Often Claude Code Opus 4.6, on hard enough problems, can do the impression of acting fast without really making progress. Then you spin the …”
   • [community] “Genuinely excited to try this out. I've started using Codex much more heavily in the past two months and honestly, it's been shockingly good…”

   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 to GitHub Copilot
   Codex✓fullclaimed7/10

   OpenAI's docs describe a dedicated Codex cloud mode that runs tasks in isolated cloud environments, in parallel, triggered from web/GitHub/GitLab/Linear/Slack, with configurable repo setup and a workflow to inspect diffs/PRs on completion, plus a CLI command (`codex cloud`) to submit and later pull results locally — squarely matching the story of delegating longer background tasks to an isolated cloud environment. missing for 10: independent or hands-on community corroboration specifically validating the cloud/background execution feature (community evidence in the pack discusses CLI/app UX and model quality, not the cloud delegation flow itself).

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Start work in Codex cloud from GitHub pull requests, GitLab merge requests and issues, Linear issues, or Slack channels and threads.”
   • [claimed-docs] “Run tasks in parallel without tying up your local machine.”
   • [claimed-docs] “Configure the dependencies, tools, variables, and setup steps each repository needs.”
   • [claimed-docs] “Inspect the summary and diff, request a follow-up, or open a pull request when the result is ready.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”
   • [claimed-docs] “Move work to Codex cloud — codex cloud: Browse active and completed chats, submit work to a configured environment, and apply the result to …”
   • [github] “If you are looking for the cloud-based agent from OpenAI, Codex Web, go to chatgpt.com/codex.”
   • [github] “If you are looking for the <em>cloud-based agent</em> from OpenAI, <strong>Codex Web</strong>, go to <a href="https://chatgpt.com/codex">cha…”

   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 to Codex
   Codex~partialclaimed6/10

   Codex Cloud docs state you can configure the dependencies, tools, variables, and setup steps each repository needs for isolated cloud environments, directly matching the story. However, there is no detail on how reproducibility is guaranteed (e.g., container images, caching, version pinning) or independent hands-on confirmation of this setup workflow. Missing for 10: concrete configuration file/schema details, reproducibility guarantees, and independent verification of the setup working as documented.

   • [claimed-docs] “Configure the dependencies, tools, variables, and setup steps each repository needs.”
   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”

   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 drawn
   Codex~partialcommunity6/10

   Codex Cloud supports running multiple tasks in parallel in isolated cloud environments, triggered from GitHub/GitLab/Linear/Slack, and delegating longer tasks to return to later, which covers parallel/async agent work. However, there is no explicit evidence of orchestrating large 'fleets' of many simultaneous agents, no stated duration limits confirming multi-day autonomous runs, and community feedback highlights usage-limit throttling that would constrain sustained parallel/long-running fleets. missing for 10: evidence of fleet-scale orchestration (many concurrent agents), confirmed multi-day autonomous run duration, and independent confirmation that parallel tasks aren't throttled by usage limits.

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Run tasks in parallel without tying up your local machine.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”
   • [claimed-docs] “Configure the dependencies, tools, variables, and setup steps each repository needs.”
   • [community] “Codex is my favorite UX for anything as it edits the files and I can use the proper tooling to adjust and test stuff... However lately the l…”
   • [community] “The main issue I have with Codex is that the best model is insanely slow, except at nights and weekends when Silicon Valley goes to bed... I…”

   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 Codex
   Codex~partialclaimed6/10

   Docs confirm Codex cloud can run tasks in parallel in isolated cloud environments without tying up the local machine, and results can be inspected (summary/diff) before choosing to follow up or open a PR — this covers running multiple attempts and reviewing outcomes. However, there's no explicit documentation of a dedicated 'compare multiple attempts side-by-side' UI/workflow, and no independent/community evidence confirming this parallel-comparison workflow works well in practice. missing for 10: explicit side-by-side comparison UI documentation, independent hands-on confirmation of comparing parallel attempts.

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Run tasks in parallel without tying up your local machine.”
   • [claimed-docs] “Inspect the summary and diff, request a follow-up, or open a pull request when the result is ready.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”

   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 to GitHub Copilot
   Codex~partialclaimed5/10

   Codex cloud supports starting tasks from external triggers (GitHub/GitLab issues & PRs, Linear issues, Slack messages) and running them in parallel isolated environments, which covers the 'triggers' half of the story, but there's no evidence of a true schedule/cron-based always-on agent that proactively maintains a repo without an external event. Missing for 10: explicit scheduled/cron execution, evidence of continuous unattended monitoring/maintenance loops, and independent confirmation these triggers reliably run autonomous fixes end-to-end.

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Start work in Codex cloud from GitHub pull requests, GitLab merge requests and issues, Linear issues, or Slack channels and threads.”
   • [claimed-docs] “Run tasks in parallel without tying up your local machine.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”

   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

Debugging

1. developerDebug issues and troubleshoot using natural-language queries

   weight 2 · round to GitHub Copilot
   Codex~partialcommunity7/10

   Codex CLI docs show clear natural-language debugging workflows: exploring unfamiliar code, running local tools, passing error screenshots for context, and running dedicated code review that reports prioritized findings (codex-docs-8, codex-docs-9, codex-docs-10, codex-docs-12). However, community evidence shows mixed real-world reliability on agentic/coding tasks and no independent confirmation specifically validating debugging accuracy. Missing for 10: hands-on validation of debugging/troubleshooting accuracy, and independent case studies showing successful root-cause diagnosis via NL queries.

   • [claimed-docs] “Inspect code, make changes, run commands, and automate repeatable work without leaving your terminal.”
   • [claimed-docs] “Start Codex in a repository to explore unfamiliar code, plan a change, edit files, and run your local development tools.”
   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Pass an error screenshot, architecture diagram, or design reference with the first prompt, or paste an image into the interactive composer.”
   • [community] “Having used codex a fair bit I find it really struggles with … almost anything. However using the equivalent chat gpt model is fantastic.”
   • [community] “Often Claude Code Opus 4.6, on hard enough problems, can do the impression of acting fast without really making progress. Then you spin the …”

   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 drawn
   Codex✓fullclaimed8/10

   Codex explicitly supports starting work from a tracked issue (GitHub, GitLab, Linear) in cloud environments, running the task, inspecting the diff/summary, and opening a pull request when done, covering the full issue-to-PR loop. missing for 10: independent hands-on confirmation of a full issue-to-merged-PR workflow succeeding end-to-end, and detail on how issue context/acceptance criteria are actually parsed.

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Start work in Codex cloud from GitHub pull requests, GitLab merge requests and issues, Linear issues, or Slack channels and threads.”
   • [claimed-docs] “Inspect the summary and diff, request a follow-up, or open a pull request when the result is ready.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”

   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
   Codex✓fullcommunity8/10

   Codex CLI and cloud docs describe the core loop of natural-language task description leading to autonomous file inspection, editing, running local tools, and producing a diff/PR (codex-docs-30, codex-docs-9, codex-docs-6, codex-docs-5), and community commentary corroborates it does real multi-file edits ('it edits the files and I can use the proper tooling', 'shockingly good... no worse than average L3-L4 engs') alongside some negative UX complaints that don't dispute the core capability. Missing for 10: independent benchmark/case-study evidence specifically confirming complex multi-file refactors across large codebases, and some community reports of it 'struggling with almost anything' create mild quality tension without rising to a concrete dispute.

   • [claimed-docs] “Work against your local repository: Let Codex inspect files, make edits, and run the tools already installed on your machine.”
   • [claimed-docs] “Start Codex in a repository to explore unfamiliar code, plan a change, edit files, and run your local development tools.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”
   • [claimed-docs] “Inspect the summary and diff, request a follow-up, or open a pull request when the result is ready.”
   • [github] “Codex CLI is a coding agent from OpenAI that runs locally on your computer.”
   • [community] “Codex is my favorite UX for anything as it edits the files and I can use the proper tooling to adjust and test stuff... However lately the l…”
   • [community] “Genuinely excited to try this out. I've started using Codex much more heavily in the past two months and honestly, it's been shockingly good…”
   • [community] “Having used codex a fair bit I find it really struggles with … almost anything. However using the equivalent chat gpt model is fantastic.”

   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
   Codex~partialcommunity6/10

   Codex CLI/cloud docs describe a general-purpose coding agent that can inspect code, edit files, run local dev tools, automate repeatable work, and review diffs before PRs — capabilities broad enough to plausibly cover writing tests, fixing lint issues, resolving conflicts, and updating dependencies (codex-docs-8, codex-docs-9, codex-docs-30, codex-docs-41). However, none of the docs explicitly name test-writing, lint-fixing, merge-conflict resolution, or dependency updates as supported workflows, and community feedback is mixed on real-world reliability for complex agentic tasks (codex-comm-3, codex-comm-13). missing for 10: explicit documentation/examples of test generation, lint-fix automation, merge-conflict resolution, and dependency-update workflows, plus hands-on confirmation these specific tasks succeed.

   • [claimed-docs] “Inspect code, make changes, run commands, and automate repeatable work without leaving your terminal.”
   • [claimed-docs] “Start Codex in a repository to explore unfamiliar code, plan a change, edit files, and run your local development tools.”
   • [claimed-docs] “Work against your local repository: Let Codex inspect files, make edits, and run the tools already installed on your machine.”
   • [claimed-docs] “Review changes before they ship: Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized f…”
   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [community] “Codex is my favorite UX for anything as it edits the files and I can use the proper tooling to adjust and test stuff... However lately the l…”
   • [community] “Having used codex a fair bit I find it really struggles with … almost anything. However using the equivalent chat gpt model is fantastic.”

   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 to Codex
   Codex~partialclaimed4/10

   Codex supports passing images (error screenshots, architecture diagrams, design references) into prompts, which is a partial building block for generating apps from a sketch/image, but there's no evidence of dedicated PDF-to-app workflows, multi-page design ingestion, or documented end-to-end 'sketch/image to working app' generation feature. missing for 10: explicit PDF design ingestion, dedicated image/design-to-app pipeline or template, independent hands-on demonstration of generating a full app from a design artifact.

   • [claimed-docs] “Pass an error screenshot, architecture diagram, or design reference with the first prompt, or paste an image into the interactive composer.”

   proof ↗⚑ 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 Codex
   Codex~partialclaimed6/10

   Codex CLI docs explicitly mention exploring unfamiliar code and planning changes within a repository, and it can inspect code, run local dev tools, and review diffs/commits — supporting codebase orientation. However, there's no dedicated codebase-mapping/visualization feature, no evidence of dependency-graph or architecture-summary generation, and community feedback focuses on agentic task execution rather than comprehension aids. Missing for 10: dedicated codebase-map/architecture-overview feature, independent hands-on evidence of effectively onboarding to unfamiliar large codebases, and richer navigation/search tooling beyond terminal chat resume.

   • [claimed-docs] “Start Codex in a repository to explore unfamiliar code, plan a change, edit files, and run your local development tools.”
   • [claimed-docs] “Inspect code, make changes, run commands, and automate repeatable work without leaving your terminal.”
   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Reopen a recent chat from the current repository, or search across local chats when you need to return to older work.”

   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 drawn
   Codex~partialclaimed5/10

   Codex CLI docs explicitly state it can be started in a repository 'to explore unfamiliar code, plan a change, edit files, and run your local development tools' (codex-docs-9), implying the agent autonomously navigates the codebase rather than requiring manual file selection, and codex-gh-1 confirms it runs as an autonomous coding agent locally. However, there's no detailed documentation of how it builds a whole-codebase map/summary, no explicit 'explain codebase' feature, and no independent hands-on evidence confirming this works well on large unfamiliar repos. Missing for 10: dedicated codebase-mapping/summarization feature documentation, evidence of handling very large repos, and independent user reports validating this specific capability.

   • [claimed-docs] “Start Codex in a repository to explore unfamiliar code, plan a change, edit files, and run your local development tools.”
   • [github] “Codex CLI is a coding agent from OpenAI that runs locally on your computer.”

   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 to Codex
   Codex~partialclaimed3/10

   Codex CLI supports `codex resume` to reopen or search past local chats in a repository, giving a limited form of session recall, but this requires manual user action rather than automatic memory building/recall across sessions. Missing for 10: evidence of automatic persistent memory (learned facts, preferences, or context) that Codex builds unprompted and recalls without explicit resume/search commands, and any cross-session synthesis beyond raw chat transcripts.

   • [claimed-docs] “Reopen a recent chat from the current repository, or search across local chats when you need to return to older work.”
   • [claimed-docs] “`codex resume`: Reopen a recent chat from the current repository, or search across local chats when you need to return to older work.”

   proof ↗⚑ 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
   Codex—none0/10

   No evidence in the pack describes Codex supporting multiple project directories or repositories being combined in a single session/context; documentation focuses on single-repository sessions, cloud tasks, and per-repository setup steps.

   ⚑ 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
   Codex—none0/10

   The evidence pack covers Codex's CLI, cloud, MCP, and review features but contains no mention of a project-level instructions/config file (e.g., AGENTS.md or similar) for setting coding standards or conventions the agent should follow. This is a plausible and common capability for coding agents, but nothing in the pack documents or demonstrates it.

   ⚑ 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 Codex
   Codex✓fullclaimed7/10

   Codex CLI docs explicitly describe exploring unfamiliar code and running local dev tools to investigate issues, passing error screenshots for context, delegating focused investigation to subagents, and running dedicated reviews against uncommitted changes/commits/base branches to verify fixes before committing — covering reproduce, narrow-down, and verify steps. Missing for 10: no explicit 'reproduce a bug' walkthrough or first-hand/independent account of successfully diagnosing and fixing a real bug end-to-end with Codex.

   • [claimed-docs] “Start Codex in a repository to explore unfamiliar code, plan a change, edit files, and run your local development tools.”
   • [claimed-docs] “Pass an error screenshot, architecture diagram, or design reference with the first prompt, or paste an image into the interactive composer.”
   • [claimed-docs] “Ask Codex to delegate focused work to specialized agents, then bring their findings back into the main terminal session.”
   • [claimed-docs] “Work against your local repository: Let Codex inspect files, make edits, and run the tools already installed on your machine.”
   • [claimed-docs] “Review changes before they ship: Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized f…”
   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Run a non-interactive command in a repeatable workflow.”

   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 Codex
   Codex✓fullclaimed7/10

   Codex CLI docs explicitly describe packaging repeatable instructions as "skills" and adding plugins to connect Codex to team tools/data from the CLI, directly matching the custom-skills story. Missing for 10: independent hands-on validation of skill creation/usage, and deeper documentation on skill authoring format/lifecycle beyond a single mention.

   • [claimed-docs] “Package repeatable instructions as skills, then add plugins to connect Codex to your team's tools and data without leaving the CLI.”

   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
   Codex~partialclaimed6/10

   Codex documents integration points for third-party ecosystem tools — triggering work from GitHub, GitLab, Linear, and Slack (partner platforms), and connecting to third-party MCP servers, plugins, and skills that give access to tools like Figma or a browser — which supports embedding partner-built capabilities into engineering workflows. However, the evidence is framed around Codex consuming tools/data sources rather than a curated marketplace of partner-built 'agent apps,' and there's no independent case study of a partner agent integration working end-to-end. Missing for 10: evidence of a partner/agent-app marketplace or certified third-party agent integrations, and independent verification of such integrations working in practice.

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Start work in Codex cloud from GitHub pull requests, GitLab merge requests and issues, Linear issues, or Slack channels and threads.”
   • [claimed-docs] “Package repeatable instructions as skills, then add plugins to connect Codex to your team's tools and data without leaving the CLI.”
   • [claimed-docs] “Use it to give ChatGPT or Codex access to third-party documentation, or to let it interact with developer tools like your browser or Figma.”
   • [claimed-docs] “Connect external tools with MCP — codex mcp: Add local or remote MCP servers, authenticate when needed, and inspect the tools available to t…”
   • [claimed-docs] “Use skills and plugins: Package repeatable instructions as skills, then add plugins to connect Codex to your team's tools and data without l…”
   • [claimed-docs] “Model Context Protocol (MCP) connects models to tools and context. Use it to give ChatGPT or Codex access to third-party documentation, or t…”

   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
   Codex—none0/10

   Codex documents repo-level cloud environments, RBAC, and MCP connections to team tools, but no evidence describes a shared 'workspace' feature that unifies docs and repos into a common source of truth for a team; this is a plausible ask for an engineering tool but Codex's evidence only covers per-task cloud environments and repo configuration, not a persistent shared knowledge/workspace layer.

   • [claimed-docs] “Configure the dependencies, tools, variables, and setup steps each repository needs.”
   • [claimed-docs] “Role-based access control (RBAC) lets you decide who can do what across your organization and projects—both through the API and in the Dashb…”
   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”

   proof ↗⚑ 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 Codex
   Codex~partialclaimed6/10

   Codex explicitly supports starting work from Slack (and GitHub/GitLab/Linear) and lets users add local or remote MCP servers to connect to third-party tools/docs (e.g. Figma, browser), giving a generic mechanism to extend context to workflow tools. However, there is no explicit documentation of native Jira or Google Drive connectors—only Slack is named among the story's specific tools, with Jira/Google Drive requiring the generic (and for one variant, deprecated/experimental) MCP server pathway. Missing for 10: named Jira integration, named Google Drive integration, and confirmation that the current (non-deprecated) MCP mechanism is broadly used for these specific SaaS tools.

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Start work in Codex cloud from GitHub pull requests, GitLab merge requests and issues, Linear issues, or Slack channels and threads.”
   • [claimed-docs] “Add local or remote MCP servers, authenticate when needed, and inspect the tools available to the current session before Codex uses them.”
   • [claimed-docs] “Package repeatable instructions as skills, then add plugins to connect Codex to your team's tools and data without leaving the CLI.”
   • [claimed-docs] “Use it to give ChatGPT or Codex access to third-party documentation, or to let it interact with developer tools like your browser or Figma.”
   • [claimed-docs] “Model Context Protocol (MCP) connects models to tools and context. Use it to give ChatGPT or Codex access to third-party documentation, or t…”
   • [claimed-docs] “Connect external tools with MCP — codex mcp: Add local or remote MCP servers, authenticate when needed, and inspect the tools available to t…”
   • [github] “Codex MCP Server Interface [experimental]: a JSON-RPC API that runs over the Model Context Protocol (MCP) transport to control a local Codex…”
   • [claimed-docs] “codex mcp-server is deprecated. Use the Codex app server instead. ... This page documents the deprecated command for existing integrations. …”

   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 Codex
   Codex✓fullclaimed8/10

   First-party docs explicitly state Codex cloud tasks can be started from GitHub pull requests, GitLab merge requests/issues, Linear issues, or Slack channels/threads, matching the story directly. Missing for 10: independent/hands-on verification of these specific integrations working in practice (community evidence covers CLI/app UX but not the GitHub/GitLab/Linear/Slack kickoff flows specifically).

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Start work in Codex cloud from GitHub pull requests, GitLab merge requests and issues, Linear issues, or Slack channels and threads.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”

   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 Codex
   Codex✓fullclaimed8/10

   Codex supports starting tasks in the cloud from web/GitHub/GitLab/Linear/Slack, working in parallel cloud environments, and later resuming or continuing work from the CLI via 'codex cloud' (browse active/completed chats, submit/apply results) or 'codex resume' to reopen local chats, plus a shared MCP config across ChatGPT desktop, CLI, and IDE extension enabling cross-client continuity. missing for 10: independent hands-on confirmation of seamless state sync across devices/browsers, and no explicit mention of resuming a cloud-started task from a different physical device's browser session.

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Start work in Codex cloud from GitHub pull requests, GitLab merge requests and issues, Linear issues, or Slack channels and threads.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”
   • [claimed-docs] “Start and review work from the web or Codex CLI.”
   • [claimed-docs] “Move work to Codex cloud — codex cloud: Browse active and completed chats, submit work to a configured environment, and apply the result to …”
   • [claimed-docs] “`codex resume`: Reopen a recent chat from the current repository, or search across local chats when you need to return to older work.”
   • [claimed-docs] “The ChatGPT desktop app, Codex CLI, and IDE extension share this configuration. Once you configure your MCP servers, you can switch among th…”

   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
   Codex—none0/10

   Evidence shows Codex's IDE extension explicitly targets VS Code, Cursor, and Windsurf (codex-gh-2), with no mention of JetBrains IDEs, interactive diff viewing within an IDE, or a 'share selected code as context' feature. The axis (IDE integration) is clearly applicable to Codex as a coding agent, but JetBrains-specific support and the described interactive-diff/context-sharing workflow are simply absent from the evidence pack.

   • [github] “If you want Codex in your code editor (VS Code, Cursor, Windsurf), install in your IDE.”

   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
   Codex✓fullcommunity8/10

   Codex explicitly offers an IDE extension for VS Code, Cursor, and Windsurf, plus a CLI usable within the terminal in your repo, both providing contextual chat/help with the codebase (edit files, run commands, review diffs). Community evidence confirms real-world usage of Codex CLI/app for editing and testing files in context, though some note UX friction compared to competitors. Missing for 10: deeper first-party documentation/screenshots of the IDE extension's chat UI specifically, and stronger independent hands-on corroboration of in-IDE chat quality.

   • [github] “If you want Codex in your code editor (VS Code, Cursor, Windsurf), install in your IDE.”
   • [claimed-docs] “Start Codex in a repository to explore unfamiliar code, plan a change, edit files, and run your local development tools.”
   • [claimed-docs] “Inspect code, make changes, run commands, and automate repeatable work without leaving your terminal.”
   • [community] “Codex is my favorite UX for anything as it edits the files and I can use the proper tooling to adjust and test stuff... However lately the l…”

   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 Codex
   Codex~partialcommunity5/10

   Codex ships a desktop app ("codex app"/Codex App page) and documents parallel task execution plus diff/summary inspection before merging, suggesting the underlying pieces exist, but the evidence never shows the desktop app UI actually presenting a visual diff viewer or multiple sessions arranged side by side. Community notes even flag basic desktop-app reliability issues (stuck on 'Loading projects...', Mac-only availability). Missing for 10: concrete documentation/screenshots of the desktop app's diff viewer, explicit multi-session/side-by-side UI description, and independent confirmation it works smoothly.

   • [github] “If you want the desktop app experience, run <code>codex app</code> or visit the Codex App page.”
   • [github] “If you want the desktop app experience, run <code>codex app</code> or visit <a href="https://chatgpt.com/codex?app-landing-page=true">the Co…”
   • [claimed-docs] “Inspect the summary and diff, request a follow-up, or open a pull request when the result is ready.”
   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Run tasks in parallel without tying up your local machine.”
   • [claimed-docs] “Review changes before they ship: Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized f…”
   • [community] “Genuinely excited to try this out. I've started using Codex much more heavily in the past two months and honestly, it's been shockingly good…”
   • [community] “Mac only. Again. Apple is great but this is OpenAI devs showing their disconnect from the mainstream.”

   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
   Codex✓fullcommunity7/10

   Codex documents cloud parallel task execution across multiple repos/environments (codex-docs-1,3,6), a web/CLI dashboard to browse active and completed chats and apply results locally (codex-docs-15), and resuming/searching across sessions (codex-docs-11,24), which together support managing multiple concurrent agent sessions from a unified interface. However, evidence is vendor-documentation only with no independent hands-on confirmation of a true 'unified workspace' UX for an engineering-lead managing many sessions simultaneously, and some community comments note UX rough edges (codex-comm-9,18). Missing for 10: independent/hands-on verification of multi-session management at scale, and clearer detail on cross-session visibility/coordination for a lead overseeing a team's agents.

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Run tasks in parallel without tying up your local machine.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”
   • [claimed-docs] “Browse active and completed chats, submit work to a configured environment, and apply the result to your local repository from the terminal.”
   • [claimed-docs] “Reopen a recent chat from the current repository, or search across local chats when you need to return to older work.”
   • [claimed-docs] “`codex resume`: Reopen a recent chat from the current repository, or search across local chats when you need to return to older work.”
   • [community] “I wish Codex App was open source. I like it, but there are always a bunch of little paper cuts that, if you were using codex cli, you could …”

   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 to Codex
   Codex✓fullcommunity9/10

   Codex CLI is explicitly documented as a coding agent that runs locally in the terminal, with npm/standalone install, working against the local repository, editing files, running commands, and offering interactive TUI plus non-interactive exec mode — well corroborated by first-party docs and GitHub README, with community usage discussion confirming real-world use. Missing for 10: independent hands-on verification specifically of pure local terminal usage (most community commentary discusses model quality/UX rather than the local-run mechanics) and some caveats about performance/limits reported by users.

   • [github] “Codex CLI is a coding agent from OpenAI that runs locally on your computer.”
   • [github] “npm install -g @openai/codex”
   • [claimed-docs] “Inspect code, make changes, run commands, and automate repeatable work without leaving your terminal.”
   • [claimed-docs] “Start Codex in a repository to explore unfamiliar code, plan a change, edit files, and run your local development tools.”
   • [claimed-docs] “Work against your local repository: Let Codex inspect files, make edits, and run the tools already installed on your machine.”
   • [claimed-docs] “Compose with scripts and CI: Use Codex interactively or call codex exec from repeatable workflows and pipelines.”
   • [claimed-docs] “Install the Codex CLI with the standalone installer for macOS and Linux.”
   • [community] “Codex is my favorite UX for anything as it edits the files and I can use the proper tooling to adjust and test stuff... However lately the l…”
   • [community] “Genuinely excited to try this out. I've started using Codex much more heavily in the past two months and honestly, it's been shockingly good…”

   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 Codex
   Codex✓fullclaimed8/10

   Docs explicitly describe running 'a non-interactive command in a repeatable workflow' and automating repeatable work without leaving the terminal, plus support for submitting work to configured environments from scripts (codex exec-style usage implied). Missing for 10: independent hands-on confirmation of non-interactive/CI usage and detailed exit-code/output-format documentation for scripting.

   • [claimed-docs] “Run a non-interactive command in a repeatable workflow.”
   • [claimed-docs] “Inspect code, make changes, run commands, and automate repeatable work without leaving your terminal.”
   • [claimed-docs] “Browse active and completed chats, submit work to a configured environment, and apply the result to your local repository from the terminal.”
   • [github] “Codex CLI is a coding agent from OpenAI that runs locally on your computer.”

   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 drawn
   Codex~partialcommunity3/10

   Codex ships rich CLI/UI-only capabilities (cloud tasks, resume/review, skills, plugins, MCP client integration) with no evidence these are exposed via a dedicated Codex API, and the general OpenAI API (RBAC, Responses API) is not shown to cover Codex-specific workflows; community evidence even confirms the latest gpt-5.3-codex model 'isn't available on the API yet,' a documented parity gap. Missing for 10: documented API endpoints for cloud task delegation, chat/session resume, MCP tool orchestration, and confirmation that current models/features are API-accessible at parity with CLI/UI.

   • [github] “You can also use Codex with an API key, but this requires additional setup.”
   • [community] “gpt-5.3-codex isn't available on the API yet — 'We are working to safely enable API access soon.'”
   • [claimed-docs] “Role-based access control (RBAC) lets you decide who can do what across your organization and projects—both through the API and in the Dashb…”
   • [claimed-docs] “Create a model response — request/response reference with runnable code samples selectable per language: HTTP, Python, TypeScript, Go, Ruby,…”
   • [claimed-docs] “codex mcp-server is deprecated. Use the Codex app server instead. ... This page documents the deprecated command for existing integrations. …”

   proof ↗⚑ 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
   Codex—none0/10

   No evidence of any data export feature or open-format export mechanism for chat history, project data, or configurations; Codex works with local files/git repos but there's no documented export/portability capability for user data (e.g., conversation history, settings) to leave the platform. Missing for 10: any documented data export tool, open-format export (JSON/Markdown dump), or data portability statement.

   ⚑ 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 to Codex
   Codex~partialcommunity4/10

   The Codex CLI source lives in a public GitHub repo (openai/codex) and a community comment implies its openness lets users 'diagnose and file an issue' the way they can't with the closed-source Codex App, suggesting at least the CLI's code is publicly viewable. However, no evidence pack item states an explicit open-source license, and the App/cloud components are explicitly described as closed. missing for 10: explicit license file/name (MIT, Apache, etc.), confirmation the full product (not just CLI) is open, and independent corroboration beyond one forum remark.

   • [github] “Codex CLI is a coding agent from OpenAI that runs locally on your computer.”
   • [community] “I wish Codex App was open source. I like it, but there are always a bunch of little paper cuts that, if you were using codex cli, you could …”

   proof ↗⚑ 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

4. ai-native userSelf-host the core product

   weight 3 · round drawn
   Codex—none0/10

   Codex CLI runs locally but requires signing into a ChatGPT account or OpenAI API key, and the core inference/model and cloud environments are OpenAI-hosted only; there is no self-hosted backend option. A commenter explicitly wishes the Codex App were open source, implying it is not, which forecloses self-hosting the core product.

   • [github] “We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Business, Edu, or Enterprise plan.”
   • [github] “You can also use Codex with an API key, but this requires additional setup.”
   • [community] “I wish Codex App was open source. I like it, but there are always a bunch of little paper cuts that, if you were using codex cli, you could …”

   proof ↗⚑ flag

   GitHub Copilot—none0/10

   GitHub Copilot is a proprietary cloud/IDE-integrated service with no evidence of any self-hostable core model, backend, or deployment option; all documented capabilities rely on GitHub's hosted infrastructure and models. Self-hosting is a legitimate axis for AI-native openness comparisons, but nothing in the evidence pack indicates it is possible.

   ⚑ flag

Authentication

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

   weight 2 · round to Codex
   Codex~partialcommunity5/10

   GitHub docs confirm Codex CLI supports API key authentication as an alternative to ChatGPT account login, but note it 'requires additional setup,' and the account-login flow (Sign in with ChatGPT) is the recommended default. Missing for 10: detailed API-key setup documentation, first-party quickstart parity with account login, and independent confirmation that API-key auth is fully feature-equivalent (e.g. codex-comm-5 shows some newer models aren't even available via API yet).

   • [github] “We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Business, Edu, or Enterprise plan.”
   • [github] “You can also use Codex with an API key, but this requires additional setup.”
   • [community] “gpt-5.3-codex isn't available on the API yet — 'We are working to safely enable API access soon.'”

   proof ↗⚑ 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 to Codex
   Codex~partialclaimed5/10

   Codex supports signing in with a ChatGPT Business/Enterprise/Edu account (codex-gh-3, codex-gh-7) and OpenAI's platform offers RBAC to scope access at org/project level (codex-docs-28), suggesting enterprise-grade authentication and access control exist. However, there is no explicit documentation of SSO/SAML/OIDC federation with enterprise identity providers (e.g., Okta, Azure AD) specific to Codex, nor details on how ChatGPT Enterprise auth ties into RBAC for Codex usage. Missing for 10: explicit SSO/SAML/OIDC integration docs, enterprise IdP federation details, and independent confirmation of compliance-grade auth flows for Codex specifically.

   • [github] “We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Business, Edu, or Enterprise plan.”
   • [github] “Run `codex` and select **Sign in with ChatGPT**. We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Busi…”
   • [claimed-docs] “Role-based access control (RBAC) lets you decide who can do what across your organization and projects—both through the API and in the Dashb…”

   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 Codex
   Codex✓fullclaimed9/10

   GitHub docs explicitly recommend signing in with ChatGPT to use Codex under existing Plus, Pro, Business, Edu, or Enterprise subscription plans, with API key as an alternative for those without such plans, directly confirming subscription-based sign-in. missing for 10: independent hands-on confirmation of the sign-in flow itself (evidence focuses on capability descriptions rather than a walkthrough).

   • [github] “We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Business, Edu, or Enterprise plan.”
   • [github] “Run `codex` and select **Sign in with ChatGPT**. We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Busi…”
   • [github] “Run codex and select Sign in with ChatGPT. We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Business, …”
   • [github] “You can also use Codex with an API key, but this requires additional setup.”

   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 to Codex
   Codex✓fullclaimed8/10

   Codex CLI explicitly recommends signing in with a ChatGPT account (Plus/Pro/Business/Edu/Enterprise) to use Codex without an API key, with API key usage noted as an alternative requiring additional setup. This directly matches the story of personal-account sign-in without managing API keys, though the exact free-tier scope/limits aren't detailed. Missing for 10: explicit confirmation of a genuinely free tier (vs. paid ChatGPT plans) and independent corroboration of the login flow's simplicity.

   • [github] “We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Business, Edu, or Enterprise plan.”
   • [github] “You can also use Codex with an API key, but this requires additional setup.”
   • [github] “Run `codex` and select **Sign in with ChatGPT**. We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Busi…”

   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
   Codex—none0/10

   Evidence shows Codex lets users manually choose the model and reasoning effort ('Stay in control: Choose the model, reasoning effort, permissions...') rather than any automatic best-model-per-task selection; no docs or community evidence describe an automatic model-routing/selection feature tied to cost or task type.

   • [claimed-docs] “Stay in control: Choose the model, reasoning effort, permissions, and commands that fit the task.”
   • [community] “The main issue I have with Codex is that the best model is insanely slow, except at nights and weekends when Silicon Valley goes to bed... I…”
   • [community] “First thoughts using gpt-5.3-codex-spark in Codex CLI: Blazing fast but it definitely has a small model feel... It has to be prompted to do …”

   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 to GitHub Copilot
   Codex—none0/10

   Docs confirm Codex lets users 'Choose the model, reasoning effort, permissions' (codex-docs-31), but this refers to selecting among OpenAI's own Codex/GPT models, not switching between different AI providers (e.g., Anthropic, Google). No evidence shows Codex supports plugging in or selecting non-OpenAI models/providers within a session.

   • [claimed-docs] “Stay in control: Choose the model, reasoning effort, permissions, and commands that fit the task.”
   • [github] “We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Business, Edu, or Enterprise plan.”
   • [github] “You can also use Codex with an API key, but this requires additional setup.”

   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
   Codex—none0/10

   No evidence in the pack mentions data residency, regional storage options, or geographic controls for where Codex data is stored; the pack covers RBAC, MCP, CLI features, and cloud task execution but nothing about choosing a storage region.

   ⚑ 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
   Codex—none0/10

   The evidence pack contains no mention of data-training opt-out controls, enterprise data usage policies, or privacy settings for excluding user data from model training; it covers CLI features, MCP, RBAC, and community sentiment but nothing about training-data exclusion.

   ⚑ 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
   Codex—none0/10

   No evidence pack items address data retention controls, deletion policies, or configurable retention windows for Codex; RBAC docs address access control, not retention/deletion. Missing for 10: any documentation of data retention settings, deletion APIs/workflows, or retention policy configuration.

   ⚑ 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
   Codex—none0/10

   No evidence in the pack mentions telemetry, usage tracking, data collection settings, or an opt-out mechanism for Codex; the docs and community threads cover features like MCP, CLI usage, and performance but never privacy/telemetry controls.

   ⚑ 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
   Codex—none0/10

   No evidence in the pack addresses data usage or training opt-out policies for code/prompts; RBAC and MCP docs are unrelated to this axis. Missing for 10: any enterprise data-usage/training opt-out policy documentation, admin controls for opting out, or third-party confirmation of such a policy.

   ⚑ 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
   Codex~partialclaimed6/10

   Codex docs explicitly describe inspecting diffs and opening a pull request when cloud work is ready (codex-docs-5), and CLI docs note reviewing changes 'before you commit or open a pull request' (codex-docs-45), implying git workflow integration. However, staging changes, writing commit messages, and creating branches are not explicitly documented as first-class agent actions — they are only implied via general local repo access and command execution (codex-docs-9, codex-docs-30, codex-docs-17). Missing for 10: explicit documentation of commit-message generation, branch creation, and staging as named agent capabilities, plus independent hands-on confirmation of full PR workflow automation.

   • [claimed-docs] “Inspect the summary and diff, request a follow-up, or open a pull request when the result is ready.”
   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Review changes before they ship: Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized f…”
   • [claimed-docs] “Start Codex in a repository to explore unfamiliar code, plan a change, edit files, and run your local development tools.”
   • [claimed-docs] “Work against your local repository: Let Codex inspect files, make edits, and run the tools already installed on your machine.”

   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 to GitHub Copilot
   Codex~partialclaimed5/10

   Codex CLI/cloud ships a dedicated 'review' capability that inspects uncommitted changes, a commit, or a base branch and reports prioritized findings without touching the working tree, and cloud tasks can be kicked off from GitHub PRs and later opened as PRs. However, there is no evidence of an automatic, PR-triggered review bot that comments on every pull request without manual invocation. missing for 10: evidence of automatic triggering on every PR (e.g., GitHub App/webhook auto-review), evidence of inline PR comments, independent confirmation of review quality on real PRs.

   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Review changes before they ship: Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized f…”
   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Start work in Codex cloud from GitHub pull requests, GitLab merge requests and issues, Linear issues, or Slack channels and threads.”
   • [claimed-docs] “Inspect the summary and diff, request a follow-up, or open a pull request when the result is ready.”

   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 drawn
   Codex✓fullclaimed8/10

   Codex CLI has a dedicated review command that inspects diffs against uncommitted changes, a commit, or a base branch, reporting prioritized findings without modifying the working tree, plus cloud/web flows to inspect summaries and diffs before opening a PR. Missing for 10: independent/hands-on corroboration of the review command's accuracy and any CI-integrated check-running beyond exec/scripts.

   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Review changes before they ship: Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized f…”
   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Inspect the summary and diff, request a follow-up, or open a pull request when the result is ready.”
   • [claimed-docs] “Compose with scripts and CI: Use Codex interactively or call codex exec from repeatable workflows and pipelines.”

   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 to GitHub Copilot
   Codex~partialclaimed6/10

   Codex documents fine-grained control over external tool access at the session/repo level: engineers can add/remove local or remote MCP servers, inspect available tools before they're used, and set permission boundaries for edits/commands via /permissions (codex-docs-16, codex-docs-38, codex-docs-39, codex-docs-46). This gives an engineer meaningful control over which integrations the agent can reach, and RBAC exists for org/project-level API access (codex-docs-28), but that RBAC is about API/dashboard permissions, not specifically about restricting agent tool/integration access org-wide for a lead managing a team's Codex usage. Missing for 10: evidence of centralized, lead-enforced policy that restricts which MCP servers/tools individual developers can enable (vs. per-session self-configuration), and independent confirmation this control actually prevents unauthorized tool access in practice.

   • [claimed-docs] “Add local or remote MCP servers, authenticate when needed, and inspect the tools available to the current session before Codex uses them.”
   • [claimed-docs] “Connect external tools with MCP — codex mcp: Add local or remote MCP servers, authenticate when needed, and inspect the tools available to t…”
   • [claimed-docs] “Set the boundaries for each run — /permissions: Choose when Codex can edit files or run commands without asking, and inspect the active sand…”
   • [claimed-docs] “In the `codex` TUI, use `/mcp` to see your active MCP servers.”
   • [claimed-docs] “Role-based access control (RBAC) lets you decide who can do what across your organization and projects—both through the API and in the Dashb…”

   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
   Codex✓fullcommunity7/10

   First-party docs explicitly describe sandboxed execution: Codex lets you 'choose when Codex can edit files or run commands without asking, and inspect the active sandbox and writable roots' (codex-docs-17), and cloud tasks run in 'isolated cloud environments' with configurable dependencies/tools (codex-docs-1, codex-docs-4). This directly matches the engineering-lead's need for sandboxed code/tool interaction, though network-resource sandboxing specifics are not spelled out and there's no independent hands-on verification of sandbox robustness (a community comment raises but does not concretely confirm a sandbox-bypass issue). Missing for 10: explicit documentation of network-level sandbox controls, and independent/hands-on confirmation that the sandbox reliably contains tool/network access.

   • [claimed-docs] “Choose when Codex can edit files or run commands without asking, and inspect the active sandbox and writable roots before you continue.”
   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Configure the dependencies, tools, variables, and setup steps each repository needs.”
   • [community] “Do people really want codex to have control over their computer and apps? I'm still paranoid about keeping things securely sandboxed.”

   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
   Codex—none0/10

   No evidence anywhere in the pack mentions license detection, public-code matching, or provenance references for AI-suggested code; Codex's review features (codex-docs-10, -41, -45) only cover code quality/prioritized findings, not license/public-code attribution.

   ⚑ 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
   Codex~partialclaimed3/10

   Codex CLI has a dedicated review command that inspects uncommitted changes, commits, or branches and reports 'prioritized findings' (codex-docs-10, codex-docs-41, codex-docs-45), which could surface security issues, and as a general coding agent it can edit files/run commands. However, the review feature explicitly reports findings 'without modifying your working tree,' meaning it does not auto-fix, and no evidence specifically frames this as security-vulnerability detection/explanation with automatic remediation. missing for 10: explicit security-vulnerability scanning/explanation feature, evidence of automatic fix application (vs. just flagging), and any independent confirmation that Codex reliably identifies/fixes security issues.

   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Review changes before they ship: Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized f…”
   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Work against your local repository: Let Codex inspect files, make edits, and run the tools already installed on your machine.”

   proof ↗⚑ 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