Codex vs Cursor

Agent access

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

   weight 2 · round to Codex
   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

   Cursor—none0/10

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

   ⚑ flag

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

   Cursor~partialprobed6/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round to Codex
   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

   Cursor✓fullclaimed8/10

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

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

   proof ↗⚑ flag

4. 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

   Cursor✓fullprobed8/10

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

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

   proof ↗⚑ flag

5. 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

   Cursor~partialprobed3/10

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

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

   proof ↗⚑ flag

6. 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

   Cursor—none0/10

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

   ⚑ flag

7. 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

   Cursor—none0/10

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

   ⚑ flag

8. 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

   Cursor—none0/10

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

   ⚑ flag

Agentic features

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

   weight 2 · round to Cursor
   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

   Cursor✓fullclaimed7/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round to Cursor
   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

   Cursor✓fullclaimed8/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round to Cursor
   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

   Cursor✓fullclaimed9/10

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

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

   proof ↗⚑ flag

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

   Cursor✓fullclaimed8/10

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

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

   proof ↗⚑ flag

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

   Cursor—none0/10

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

   ⚑ flag

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

   Cursor—none0/10

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

   ⚑ flag

3. 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

   Cursor—none0/10

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

   ⚑ flag

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

   Cursor~partialclaimed5/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round to Cursor
   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

   Cursor~partialclaimed6/10

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

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

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round to Cursor
   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

   Cursor✓fullclaimed7/10

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

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

   proof ↗⚑ flag

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

   weight 1 · round to Codex
   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

   Cursor—none0/10

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

   ⚑ flag

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

   Cursor✓fullclaimed7/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round to Cursor
   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

   Cursor✓fullclaimed8/10

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

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

   proof ↗⚑ flag

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

   Cursor~partialclaimed4/10

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

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

   proof ↗⚑ flag

Parallel agents

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

   weight 2 · round to Cursor
   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

   Cursor✓fullclaimed8/10

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

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

   proof ↗⚑ flag

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

   weight 1 · round drawn
   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

   Cursor~partialclaimed6/10

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

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

   proof ↗⚑ flag

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 Cursor
   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

   Cursor✓fullclaimed8/10

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

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

   proof ↗⚑ flag

Debugging

1. developerDebug issues and troubleshoot using natural-language queries

   weight 2 · round to Codex
   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

   Cursor~partialcommunity6/10

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

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

   proof ↗⚑ flag

Feature implementation

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

   weight 3 · round to Codex
   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

   Cursor~partialclaimed7/10

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

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

   proof ↗⚑ flag

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

   Cursor✓fullcommunity8/10

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

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

   proof ↗⚑ flag

Maintenance automation

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

   weight 3 · round drawn
   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

   Cursor~partialclaimed6/10

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

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

   proof ↗⚑ flag

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

   Cursor—none0/10

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

   ⚑ flag

Codebase mapping

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

   weight 3 · round drawn
   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

   Cursor~partialclaimed6/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round to Codex
   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

   Cursor~partialclaimed4/10

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

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

   proof ↗⚑ flag

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

   Cursor—none0/10

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

   ⚑ flag

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

   Cursor—none0/10

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

   ⚑ flag

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

   weight 3 · round to Cursor
   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

   Cursor~partialclaimed3/10

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

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

   proof ↗⚑ flag

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

   Cursor~partialclaimed6/10

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

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

   proof ↗⚑ flag

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

   Cursor~partialclaimed6/10

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

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

   proof ↗⚑ flag

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

   weight 1 · round to Cursor
   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

   Cursor✓fullclaimed7/10

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

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

   proof ↗⚑ flag

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 drawn
   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

   Cursor—none0/10

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

   ⚑ flag

Tool integration

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

   weight 3 · round to Cursor
   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

   Cursor✓fullclaimed8/10

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

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

   proof ↗⚑ flag

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

   Cursor~partialclaimed7/10

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

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

   proof ↗⚑ flag

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

   Cursor~partialclaimed5/10

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

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

   proof ↗⚑ flag

Ide integration

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

   weight 1 · round drawn
   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

   Cursor—none0/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round to Codex
   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

   Cursor✓fullcommunity7/10

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

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

   proof ↗⚑ flag

Session management

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

   weight 2 · round to Cursor
   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

   Cursor✓fullclaimed6/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round drawn
   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

   Cursor✓fullclaimed7/10

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

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

   proof ↗⚑ flag

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

   Cursor✓fullprobed7/10

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

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

   proof ↗⚑ flag

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

   Cursor~partialprobed6/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round to Codex
   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

   Cursor—none0/10

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

   ⚑ flag

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

   Cursor—none0/10

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

   ⚑ flag

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

   Cursor—none0/10

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

   ⚑ flag

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

   Cursor—none0/10

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

   ⚑ flag

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

   Cursor—none0/10

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

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

   proof ↗⚑ flag

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

   Cursor—none0/10

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

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

   proof ↗⚑ flag

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

   Cursor—none0/10

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

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

   proof ↗⚑ flag

Model choice

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

   weight 1 · round drawn
   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

   Cursor—none0/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round to Cursor
   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

   Cursor✓fullclaimed8/10

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

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

   proof ↗⚑ flag

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

   Cursor—none0/10

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

   ⚑ flag

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

   weight 3 · round drawn
   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

   Cursor—none0/10

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

   ⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round drawn
   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

   Cursor—none0/10

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

   ⚑ flag

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

   weight 2 · round drawn
   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

   Cursor—none0/10

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

   ⚑ flag

Data governance

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

   weight 1 · round drawn
   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

   Cursor—none0/10

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

   ⚑ flag

Pr review

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

   weight 3 · round to Codex
   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

   Cursor~partialclaimed4/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round to Cursor
   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

   Cursor✓fullclaimed7/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round to Codex
   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

   Cursor~partialclaimed5/10

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

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

   proof ↗⚑ flag

Safe execution

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

   weight 2 · round to Cursor
   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

   Cursor✓fullclaimed8/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round to Codex
   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

   Cursor—none0/10

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

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

   proof ↗⚑ flag

Security checks

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

   weight 1 · round drawn
   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

   Cursor—none0/10

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

   ⚑ flag

2. developerGet contextual explanations and automatic fixes for security vulnerabilities

   weight 2 · round to Codex
   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

   Cursor—none0/10

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

   ⚑ flag