Skip to content
ProductArena

ChatGPT vs Microsoft Copilot

free-tier · subscription-flat · subscription-per-seat · enterprise-custom

·

free-tier · subscription-flat

ChatGPT wins · 35–5 (6 drawn)

ChatGPTAGENT-READY49/100BUILT-IN AI86/100
Agenticness
AGENT-READY0/100BUILT-IN AI24/100Microsoft Copilot

Agenticness — how well agents can access and operate the productAgenticness

How well agents can access and operate the product

Agent access

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

    weight 2 · round to ChatGPT
    ChatGPTpartialprobed5/10

    ChatGPT's Browser and MCP features let a user direct the agent to fetch and use third-party documentation or websites (e.g. Context7 for developer docs, browsing arbitrary URLs), which would technically allow pointing it at an llms.txt or agent-oriented doc page. The evidence pack also shows ChatGPT's own docs site publishes an llms.txt (probe-1), indicating familiarity with the convention, but there is no explicit documented feature or example of a user instructing ChatGPT to consume an llms.txt file specifically. Missing for 10: explicit product support/example for llms.txt ingestion, confirmation that browsing normalizes/parses such files as agent-context rather than generic web content, independent hands-on verification.

    • [probe] “PROBE llms.txt: HTTP 200 at https://learn.chatgpt.com/llms.txt # Codex > Build with the Codex CLI, IDE extension, and cloud automation to s…”
    • [claimed-docs] “Browser lets ChatGPT open websites, gather current information, and take action while you stay in control.”
    • [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”
    • [claimed-docs] “to add Context7 (a free MCP server for developer documentation)”
    proof ↗⚑ flag
    Microsoft Copilotnone0/10

    Probes show no llms.txt, no markdown docs endpoint, and no OpenAPI spec for Microsoft Copilot's support site, and no evidence anywhere in the pack of agent-oriented documentation formats being offered. This axis applies (any product could publish llms.txt or agent-friendly docs) but there is no evidence Copilot does so.

    • [probe] “PROBE llms.txt: HTTP 404 at https://support.microsoft.com/llms.txt”
    • [probe] “PROBE docs-md: HTTP 404 at https://support.microsoft.com/en-us/copilot.md”
    • [probe] “PROBE openapi: all candidate paths 404 (https://support.microsoft.com/openapi.json, https://support.microsoft.com/swagger.json, https://supp…”
    proof ↗⚑ flag

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

    weight 3 · round to ChatGPT
    ChatGPTfullclaimed8/10

    ChatGPT has first-party documentation for MCP support, explicitly describing configuring MCP servers (e.g., Context7) so ChatGPT/Codex can access third-party tools like documentation, browser, or Figma, with config stored in config.toml and scoping options for trusted projects, plus cross-client portability once configured. missing for 10: independent/hands-on community corroboration of MCP server usage specifically (community evidence covers plugins/browsing but not MCP directly).

    • [claimed-docs] “let it interact with developer tools like your browser or Figma”
    • [claimed-docs] “Once you configure your MCP servers, you can switch among those clients without redoing setup.”
    • [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] “to add Context7 (a free MCP server for developer documentation)”
    • [claimed-docs] “you can also scope MCP servers to a project with `.codex/config.toml` (trusted projects only)”
    • [claimed-docs] “Codex stores MCP configuration in `config.toml`”
    • [claimed-docs] “Model Context Protocol (MCP) connects models to tools and context. Use it to give ChatGPT or Codex access to third-party documentation”
    proof ↗⚑ flag
    Microsoft Copilotnone0/10

    The evidence pack describes Copilot connecting to first-party consumer services (OneDrive, Outlook.com, Google Drive/Gmail) via 'Copilot connectors,' but there is no mention of MCP (Model Context Protocol) server support or an ability for users to plug in arbitrary MCP tool servers. This is an applicable axis for an AI assistant product, but no evidence shows the capability exists.

    • [claimed-docs] “Copilot can connect with the following consumer services: * Microsoft OneDrive * Microsoft Outlook.com (email, calendar, and contacts) …”
    • [claimed-docs] “Copilot can connect with the following consumer services: Microsoft OneDrive, Microsoft Outlook.com (email, calendar, and contacts), Google …”
    • [claimed-docs] “Copilot connectors are currently available on Copilot.com and on Copilot Mobile (iOS and Android)”
    proof ↗⚑ flag

  3. ai-native userUse an official CLI

    weight 2 · round to ChatGPT
    ChatGPTfullprobed7/10

    ChatGPT ships an official Codex CLI with documented commands (--search, --cd, /memories, /fast, MCP config via config.toml, codex-security bulk-scan), and the llms.txt probe confirms 'Codex CLI' as a first-party interface for building and automating dev workflows, satisfying the AI-native official CLI story. Missing for 10: independent/hands-on community verification of the CLI itself, since community evidence only covers the general ChatGPT web product, not Codex CLI usage.

    • [claimed-docs] “In Codex CLI, use /memories in an interactive session to control whether the current chat can use existing local memories or become an input…”
    • [claimed-docs] “Run codex from the directory you want Codex to work in, or pass --cd (-C) to set it explicitly.”
    • [claimed-docs] “In the CLI, pass `--search` to fetch live results for one run”
    • [claimed-docs] “pass `--search` to fetch live results for one run”
    • [claimed-docs] “Use the Codex SDK to automate coding tasks, including jobs in CI.”
    • [claimed-docs] “Inspect code, make changes, run commands, and automate repeatable work without leaving your terminal.”
    • [claimed-docs] “Codex reads AGENTS.md files before doing any work.”
    • [claimed-docs] “Use rules to control which commands Codex can run outside the sandbox.”
    • [claimed-docs] “Use `/fast on`, `/fast off`, or `/fast status` in the CLI to change or inspect the current setting.”
    • [claimed-docs] “Use its command-line interface (CLI) to scan repositories you own or have permission to assess, review findings over time”
    • [claimed-docs] “Use `npx @openai/codex-security bulk-scan` to review repositories in one campaign.”
    • [probe] “PROBE llms.txt: HTTP 200 at https://learn.chatgpt.com/llms.txt # Codex > Build with the Codex CLI, IDE extension, and cloud automation to s…”
    proof ↗⚑ flag
    Microsoft Copilotnone0/10

    No evidence of an official CLI for Microsoft Copilot; all evidence covers chat, browser, and Office app integrations, with probes confirming no machine-readable API/CLI artifacts.

    • [probe] “PROBE llms.txt: HTTP 404 at https://support.microsoft.com/llms.txt”
    • [probe] “PROBE docs-md: HTTP 404 at https://support.microsoft.com/en-us/copilot.md”
    • [probe] “PROBE openapi: all candidate paths 404 (https://support.microsoft.com/openapi.json, https://support.microsoft.com/swagger.json, https://supp…”
    proof ↗⚑ flag

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

    weight 3 · round to ChatGPT
    ChatGPTpartialprobed4/10

    There is documented evidence of programmatic/scriptable access via the Codex CLI and Codex SDK ('Use the Codex SDK to automate coding tasks, including jobs in CI', CLI flags like --search, --cd, /fast, config.toml), which lets an AI-native user drive parts of the product outside the chat UI. However, a probe for a standard documented public API (openapi.json/swagger) at the docs site returned 404 on all candidate paths, and none of the evidence describes a general, versioned public API for driving ChatGPT itself (as opposed to Codex-specific tooling or MCP client configuration). Missing for 10: an explicit REST/GraphQL API reference for ChatGPT product actions, OpenAPI/swagger spec, and independent corroboration that non-Codex ChatGPT features are API-drivable.

    • [claimed-docs] “Use the Codex SDK to automate coding tasks, including jobs in CI.”
    • [claimed-docs] “Inspect code, make changes, run commands, and automate repeatable work without leaving your terminal.”
    • [claimed-docs] “Use its command-line interface (CLI) to scan repositories you own or have permission to assess, review findings over time”
    • [claimed-docs] “Use `npx @openai/codex-security bulk-scan` to review repositories in one campaign.”
    • [probe] “PROBE openapi: all candidate paths 404 (https://learn.chatgpt.com/openapi.json, https://learn.chatgpt.com/swagger.json, https://learn.chatgp…”
    proof ↗⚑ flag
    Microsoft Copilotnone0/10

    No evidence of a documented public API for programmatically driving Microsoft Copilot; probes for OpenAPI/llms.txt specs all returned 404, and all docs describe end-user chat/UI interactions rather than API access. Missing for 10: any public API documentation, SDK, or endpoint spec that lets developers programmatically invoke Copilot's capabilities.

    • [probe] “PROBE llms.txt: HTTP 404 at https://support.microsoft.com/llms.txt”
    • [probe] “PROBE docs-md: HTTP 404 at https://support.microsoft.com/en-us/copilot.md”
    • [probe] “PROBE openapi: all candidate paths 404 (https://support.microsoft.com/openapi.json, https://support.microsoft.com/swagger.json, https://supp…”
    proof ↗⚑ flag

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

    weight 2 · round to ChatGPT
    ChatGPTpartialclaimed4/10

    ChatGPT/Codex docs show some least-privilege mechanisms for agent tool access — MCP servers can be scoped to a trusted project via `.codex/config.toml` (chatgpt-docs-55), sandbox command rules can restrict what Codex can run outside the sandbox (chatgpt-docs-95), and workspace admins can control access to browser use, plugins, and network access (chatgpt-docs-88), plus GPT builders can configure scoped third-party API actions (chatgpt-docs-34, chatgpt-docs-44). However there is no evidence of a user-facing mechanism to actually issue/generate a scoped or least-privilege API credential/token specifically for an agent to use. missing for 10: explicit scoped API key/token issuance workflow, granularity/expiry controls on such credentials, and any documentation or independent confirmation that a user can mint a restricted-permission credential for agent use.

    • [claimed-docs] “you can also scope MCP servers to a project with `.codex/config.toml` (trusted projects only)”
    • [claimed-docs] “Use rules to control which commands Codex can run outside the sandbox.”
    • [claimed-docs] “Your workspace administrator can control access to ChatGPT Work, plugins, browser use, and network access.”
    • [claimed-docs] “Allow GPT builders to use approved workspace apps or configure actions that interact with permitted third-party APIs.”
    • [claimed-docs] “configure actions that interact with permitted third-party APIs”
    proof ↗⚑ flag
    Microsoft Copilotnone0/10

    No evidence describes issuing scoped or least-privilege API credentials for an agent; Copilot's documented connectors involve OAuth-style account sign-in to consumer services, not developer-controlled scoped credential issuance. missing for 10: any mention of API keys, scoped tokens, permission scoping, or credential management for agent access.

      ⚑ flag

    • ai-native userBuild against official SDKs

      weight 2 · round to ChatGPT
      ChatGPTpartialprobed3/10

      The pack contains a single line noting 'Use the Codex SDK to automate coding tasks, including jobs in CI' (chatgpt-docs-91), indicating an official SDK exists for Codex/automation, but there is no linked documentation, API reference, code samples, or independent corroboration of this SDK's use. The openapi probe found no public API spec, reinforcing that developer-facing SDK documentation is thin in this evidence set. missing for 10: dedicated SDK documentation/reference pages, code examples, language support details, independent developer reports of building with the SDK.

      • [claimed-docs] “Use the Codex SDK to automate coding tasks, including jobs in CI.”
      • [probe] “PROBE openapi: all candidate paths 404 (https://learn.chatgpt.com/openapi.json, https://learn.chatgpt.com/swagger.json, https://learn.chatgp…”
      proof ↗⚑ flag
      Microsoft Copilotnone0/10

      The evidence pack covers Microsoft Copilot as a consumer AI assistant with features like connectors, browsing, and app integrations, but contains no mention of official SDKs, developer APIs, or programmatic build tooling for third-party developers; probes for API/OpenAPI specs returned 404s, further indicating no discoverable developer SDK surface.

      • [probe] “PROBE llms.txt: HTTP 404 at https://support.microsoft.com/llms.txt”
      • [probe] “PROBE docs-md: HTTP 404 at https://support.microsoft.com/en-us/copilot.md”
      • [probe] “PROBE openapi: all candidate paths 404 (https://support.microsoft.com/openapi.json, https://support.microsoft.com/swagger.json, https://supp…”
      proof ↗⚑ flag

    • ai-native userSubscribe to events via webhooks

      weight 2 · round to ChatGPT
      ChatGPTpartialclaimed4/10

      ChatGPT's Automations/Scheduled Tasks support event-driven triggers ('act on pull request feedback without polling on a fixed cadence') tied to Gmail, Slack, and GitHub events, which functions like a webhook-subscription mechanism, but this is not exposed as a general-purpose webhook subscription API — it's limited to a few pre-integrated services with no documented endpoint/config for arbitrary webhook URLs. Missing for 10: a generic webhook subscription API/config for third-party or custom events, documentation of payload/security handling, and any independent confirmation of reliability.

      • [claimed-docs] “Scheduled tasks can now start when a supported event occurs in Gmail, Slack, or GitHub.”
      • [claimed-docs] “Use an event trigger to triage new email, summarize channel activity, or act on pull request feedback without polling on a fixed cadence.”
      • [claimed-docs] “scheduled tasks can run when a supported Gmail, Slack, or GitHub event occurs”
      proof ↗⚑ flag
      Microsoft Copilotnone0/10

      No evidence anywhere in the pack of Copilot offering webhook subscriptions or any event-driven notification API for developers; probes for API/OpenAPI specs returned 404s, and docs only describe chat/connector features, not webhook subscription mechanisms.

      • [probe] “PROBE llms.txt: HTTP 404 at https://support.microsoft.com/llms.txt”
      • [probe] “PROBE docs-md: HTTP 404 at https://support.microsoft.com/en-us/copilot.md”
      • [probe] “PROBE openapi: all candidate paths 404 (https://support.microsoft.com/openapi.json, https://support.microsoft.com/swagger.json, https://supp…”
      proof ↗⚑ flag

    Agentic features

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

      weight 2 · round to ChatGPT
      ChatGPTfullclaimed8/10

      ChatGPT can analyze uploaded/connected data (files, projects, local folders, connected apps like Google Drive/SharePoint/Salesforce) and generate insights, summaries, and suggestions (e.g. 'Search the web, browse websites, compare sources, read files, analyze data, and summarize findings' and 'Create a deck, analyze files, draft a report, build a project plan'), with projects giving persistent context for tailored suggestions. Missing for 10: independent hands-on evidence specifically validating data-insight quality/accuracy (community evidence largely covers unrelated features like web search accuracy issues, not data-analysis insight quality).

      • [claimed-docs] “Search the web, browse websites, compare sources, read files, analyze data, and summarize findings.”
      • [claimed-docs] “Create a deck, analyze files, draft a report, build a project plan”
      • [claimed-docs] “Use a project to organize related chats and give ChatGPT the context it needs.”
      • [claimed-docs] “A local project gives chats access to one or more folders on your computer, such as a collection of source files or a codebase.”
      • [claimed-docs] “Plugins can connect ChatGPT to the tools and information you use for work, such as Google Drive, SharePoint, Salesforce, or Gong.”
      • [claimed-docs] “Turn research and analysis into documents, presentations, spreadsheets, and other finished work.”
      proof ↗⚑ flag
      Microsoft Copilotdisputedcontradicted5/10

      Microsoft heavily documents AI-generated insights across Word, Excel, PowerPoint, Outlook, Researcher, and Analyst, and describes proactive suggestions and code-run analysis (copilot-docs-2, copilot-docs-6, copilot-docs-16, copilot-docs-33, copilot-docs-31). However, hands-on community reports concretely contradict these claims for core products: a user found Copilot in Word 'couldn't do anything except append to the end of the document... couldn't create tables' (copilot-comm-4), and Outlook's summarization is described as 'so bad' with a tiny UI button (copilot-comm-5); others report never finding a use case (copilot-comm-9). One community report is positive about cross-document data fetching (copilot-comm-7), so evidence is genuinely mixed rather than uniformly negative. Missing for 10: independent benchmark of insight quality/accuracy, resolution of the Word/Outlook hands-on failures, and clearer distinction of chat vs. Office-integrated Copilot performance.

      • [claimed-docs] “Turn raw data into clear insights with Copilot in Excel.”
      • [claimed-docs] “Go from raw numbers to real insight—use Analyst to help analyze data with ease.”
      • [claimed-docs] “Turn raw data into clear insights with Copilot in Excel. Detail your task, attach data, and tweak via chat.”
      • [claimed-docs] “Copilot may proactively generate personalized research suggestions for users based on things like past research queries and Copilot memory.”
      • [claimed-docs] “Copilot can also run code to complete complex calculations and generate graphs.”
      • [community] “I subscribed for a trial month... Oh boy! It couldn't do anything except append to the end of the document. It couldn't create tables! It co…”
      • [community] “In MacOS Outlook they have a quarter inch sized bar in the main UI with just a button to summarize. It is so bad.”
      • [community] “the way it can fetch data from across documents in 365 is really good”
      • [community] “I use AI everyday and never found a use case for Copilot.”
      proof ↗⚑ flag

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

      weight 2 · round to ChatGPT
      ChatGPTfullclaimed8/10

      ChatGPT's Scheduled Tasks/Automations feature explicitly lets users schedule recurring or event-triggered tasks (Gmail, Slack, GitHub events) to run autonomously in the background, with a dashboard to review active, paused, and completed runs. This is well-documented first-party functionality directly matching the story. Missing for 10: independent hands-on verification of background automation reliability and no community corroboration specifically about the automations/scheduled-tasks feature.

      • [claimed-docs] “Schedule recurring tasks to run in the background.”
      • [claimed-docs] “Scheduled tasks can now start when a supported event occurs in Gmail, Slack, or GitHub.”
      • [claimed-docs] “Schedule recurring tasks to run in the background... Review active, paused, and completed tasks and recent runs in Scheduled.”
      • [claimed-docs] “scheduled tasks can run when a supported Gmail, Slack, or GitHub event occurs”
      • [claimed-docs] “Use an event trigger to triage new email, summarize channel activity, or act on pull request feedback without polling on a fixed cadence.”
      proof ↗⚑ flag
      Microsoft Copilotpartialclaimed4/10

      Docs mention agentic-style capabilities (Cowork multi-step task completion, automating repetitive tasks, proactive research suggestions, browser action-taking) suggesting some autonomy, but Browse with Copilot explicitly requires user attention/supervision for many actions and no docs describe scheduled or fully background-running automations without a user session. Missing for 10: explicit scheduling/trigger mechanism, evidence of unattended background execution, and independent confirmation that these automations run without active supervision.

      • [claimed-docs] “With Cowork, Copilot can also help with bigger, multi-step tasks and deliver completed to-dos.”
      • [claimed-docs] “Hand off repetitive work so you can focus on what matters.”
      • [claimed-docs] “A copilot can automate repetitive tasks, no coding required.”
      • [claimed-docs] “Copilot may proactively generate personalized research suggestions for users based on things like past research queries and Copilot memory.”
      • [claimed-docs] “Copilot will ask for your attention and supervision for certain actions, such as buying an item, booking a reservation, sending an email, or…”
      proof ↗⚑ flag

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

      weight 3 · round to ChatGPT
      ChatGPTfullclaimed9/10

      ChatGPT ships extensive built-in agentic delegation: Work/Codex modes carry tasks through to reviewable results, scheduled/background tasks and event-triggered automations, computer use and browser control, subagent delegation, and voice-initiated task delegation — all first-party features, not third-party add-ons. Missing for 10: independent hands-on verification of these newer agentic features (Work, subagents, Computer Use) beyond vendor docs.

      • [claimed-docs] “Schedule recurring tasks to run in the background.”
      • [claimed-docs] “Scheduled tasks can now start when a supported event occurs in Gmail, Slack, or GitHub.”
      • [claimed-docs] “Turn on Work in the switcher when you want ChatGPT to carry a larger task through to a reviewable result.”
      • [claimed-docs] “Run projects in parallel, work with files, use your computer, and keep long-running work moving from one desktop workspace.”
      • [claimed-docs] “Unlike Work on the Web, local Work can operate on resources that remain on your computer without requiring you to upload files to a cloud co…”
      • [claimed-docs] “In ChatGPT Work, ask ChatGPT to delegate independent work to subagents.”
      • [claimed-docs] “ChatGPT Voice can start separate tasks for longer work, check existing tasks, and send follow-up instructions.”
      • [claimed-docs] “Browser lets ChatGPT open websites, gather current information, and take action while you stay in control.”
      • [claimed-docs] “With Computer Use, ChatGPT can see and operate graphical user interfaces on macOS or Windows.”
      • [claimed-docs] “enter `/goal` to start Goal mode”
      proof ↗⚑ flag
      Microsoft Copilotpartialcommunity6/10

      Microsoft's own docs describe extensive delegation features—Copilot in Word/Excel/PowerPoint/Outlook, Researcher, Analyst, Browse with Copilot performing multi-step browser actions, and Cowork handling 'bigger, multi-step tasks'—clearly positioning Copilot as a built-in assistant that can take on tasks. However, hands-on community reports contradict smooth delegation in practice (e.g., Copilot in Word 'couldn't do anything except append to the end of the document,' couldn't create tables or maintain formatting, and some users report never finding a real use case), indicating real-world task execution is often shallow or unreliable. Missing for 10: independent verification of successful complex multi-step task completion, and resolution of documented editing/execution failures in flagship apps.

      • [claimed-docs] “Prompt Copilot with the task, add and upload notes, then refine in the chat—all with Copilot in Word.”
      • [claimed-docs] “Turn raw data into clear insights with Copilot in Excel.”
      • [claimed-docs] “Go from prompt to presentation with Copilot in PowerPoint. Outline the flow, describe visuals, and generate.”
      • [claimed-docs] “With Cowork, Copilot can also help with bigger, multi-step tasks and deliver completed to-dos.”
      • [claimed-docs] “Browse with Copilot lets Copilot perform actions directly in your Microsoft Edge browser, such as clicking, typing, and navigating tabs.”
      • [claimed-docs] “A copilot can automate repetitive tasks, no coding required.”
      • [community] “I subscribed for a trial month... Oh boy! It couldn't do anything except append to the end of the document. It couldn't create tables! It co…”
      • [community] “In MacOS Outlook they have a quarter inch sized bar in the main UI with just a button to summarize. It is so bad.”
      • [community] “I use AI everyday and never found a use case for Copilot.”
      proof ↗⚑ flag

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

      weight 2 · round to ChatGPT
      ChatGPTfullcommunity9/10

      ChatGPT is fundamentally a natural-language interface: users type or speak requests and it carries out tasks (browsing, coding, file edits, image generation, scheduling, computer use, voice) via plain conversational commands, per extensive first-party docs and corroborating community reports of natural-language driven capability (e.g. running Docker/filesystem commands via prompts). Missing for 10: independent hands-on verification specifically of newer agentic features (Work, Goal mode, subagents) beyond vendor docs.

      • [claimed-docs] “Browser lets ChatGPT open websites, gather current information, and take action while you stay in control.”
      • [claimed-docs] “With Computer Use, ChatGPT can see and operate graphical user interfaces on macOS or Windows.”
      • [claimed-docs] “Schedule recurring tasks to run in the background.”
      • [claimed-docs] “ChatGPT Voice lets you talk through ideas and coordinate tasks in Chat, Work, and Codex in the ChatGPT desktop app. Start work, check progre…”
      • [claimed-docs] “In the ChatGPT desktop app, enter `/goal` to start Goal mode.”
      • [claimed-docs] “In ChatGPT Work, ask ChatGPT to delegate independent work to subagents.”
      • [community] “I am beyond astounded. I was able to run a Docker image, utilize the fs inside of the container, and exit the container. Docker system comma…”
      • [community] “This is huge, essentially adding what people have been building with LangChain Tools into the core product. The browser and file-upload/inte…”
      proof ↗⚑ flag
      Microsoft Copilotdisputedcontradicted5/10

      Docs extensively describe natural-language operation—prompting Copilot in Word/Excel/PowerPoint, natural-language file/email/calendar search, and browser action commands (copilot-docs-1,2,3,8,14,20-22,26,27). However, hands-on community evidence directly contradicts this for at least one core surface: a user reports Copilot in Word 'couldn't do anything except append to the end of the document... couldn't create tables! couldn't search and replace! couldn't maintain formatting' (copilot-comm-4), and others found the Outlook summarize feature and overall NL assistant underwhelming or unused (copilot-comm-5, copilot-comm-9). This is a concrete documented failure of the claimed NL command capability, not mere skepticism. Missing for 10: independent third-party benchmarking of NL command reliability across all Office apps, and resolution of the reported Word functional gaps.

      • [claimed-docs] “Prompt Copilot with the task, add and upload notes, then refine in the chat—all with Copilot in Word.”
      • [claimed-docs] “Find my budget spreadsheet” or “Show me the project plan from last month.”
      • [claimed-docs] “Find files quickly: "Find my budget spreadsheet" or "Show me the project plan from last month."”
      • [claimed-docs] “Find Word documents about vacation plans” or “Show me all PDFs.”
      • [claimed-docs] “Find emails: “Show me emails from Sarah about the budget” or “Find my flight confirmation email.””
      • [community] “I subscribed for a trial month... Oh boy! It couldn't do anything except append to the end of the document. It couldn't create tables! It co…”
      • [community] “In MacOS Outlook they have a quarter inch sized bar in the main UI with just a button to summarize. It is so bad.”
      • [community] “I use AI everyday and never found a use case for Copilot.”
      proof ↗⚑ flag

    Api quality

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

      weight 2 · round drawn
      ChatGPTnone0/10

      The probe explicitly checked for an OpenAPI/machine-readable spec at all standard locations and found only 404s, with no other evidence pack item showing a downloadable API spec for ChatGPT itself.

      • [probe] “PROBE openapi: all candidate paths 404 (https://learn.chatgpt.com/openapi.json, https://learn.chatgpt.com/swagger.json, https://learn.chatgp…”
      proof ↗⚑ flag
      Microsoft Copilotnone0/10

      No evidence of a machine-readable API spec; explicit probes for OpenAPI/swagger endpoints all returned 404, and no docs mention a public API or spec for Microsoft Copilot as an end-user product.

      • [probe] “PROBE openapi: all candidate paths 404 (https://support.microsoft.com/openapi.json, https://support.microsoft.com/swagger.json, https://supp…”
      • [probe] “PROBE llms.txt: HTTP 404 at https://support.microsoft.com/llms.txt”
      • [probe] “PROBE docs-md: HTTP 404 at https://support.microsoft.com/en-us/copilot.md”
      proof ↗⚑ flag

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

      weight 2 · round drawn
      ChatGPTnone0/10

      No evidence of a versioned API or a documented deprecation policy is present; the OpenAPI probe explicitly returned 404s and none of the docs mention API versioning or deprecation practices.

      • [probe] “PROBE openapi: all candidate paths 404 (https://learn.chatgpt.com/openapi.json, https://learn.chatgpt.com/swagger.json, https://learn.chatgp…”
      proof ↗⚑ flag
      Microsoft Copilotnone0/10

      Microsoft Copilot is presented here as a consumer-facing AI assistant product; there is no evidence of a public versioned API, developer API reference, or documented deprecation policy for it. Probes for API/OpenAPI specs and llms.txt all return 404, confirming absence of such developer-facing documentation.

      • [probe] “PROBE llms.txt: HTTP 404 at https://support.microsoft.com/llms.txt”
      • [probe] “PROBE docs-md: HTTP 404 at https://support.microsoft.com/en-us/copilot.md”
      • [probe] “PROBE openapi: all candidate paths 404 (https://support.microsoft.com/openapi.json, https://support.microsoft.com/swagger.json, https://supp…”
      proof ↗⚑ flag

    Agents tasks — stories about agents tasks in this arenaAgents tasks

    Stories about agents tasks in this arena

    Agent mode

    1. power-userDelegate a multi-step task that the assistant works on autonomously in the background and returns for my review

      weight 3 · round to ChatGPT
      ChatGPTfullclaimed8/10

      ChatGPT's Tasks/automations feature explicitly supports scheduling and running multi-step work in the background (including event-triggered runs from Gmail/Slack/GitHub), with a review interface for active/completed runs, and 'Work' mode is described as carrying larger tasks through to a reviewable result; Codex further supports background coding tasks and subagent delegation. Missing for 10: independent hands-on verification of background task reliability/quality and no third-party review of the review/approval workflow.

      • [claimed-docs] “Schedule recurring tasks to run in the background.”
      • [claimed-docs] “Scheduled tasks can now start when a supported event occurs in Gmail, Slack, or GitHub.”
      • [claimed-docs] “Schedule recurring tasks to run in the background... Review active, paused, and completed tasks and recent runs in Scheduled.”
      • [claimed-docs] “Turn on Work in the switcher when you want ChatGPT to carry a larger task through to a reviewable result.”
      • [claimed-docs] “scheduled tasks can run when a supported Gmail, Slack, or GitHub event occurs”
      • [claimed-docs] “In ChatGPT Work, ask ChatGPT to delegate independent work to subagents.”
      • [claimed-docs] “Start a Codex task to run the tests and investigate anything that doesn't pass.”
      proof ↗⚑ flag
      Microsoft Copilotpartialclaimed5/10

      Copilot's 'Cowork' feature is explicitly described as handling 'bigger, multi-step tasks and deliver completed to-dos,' and 'Browse with Copilot' can perform multi-step actions while pausing for user approval on sensitive steps, which aligns with delegate-and-review workflows. However, these are single thin doc mentions with no independent/hands-on validation of true background/asynchronous operation, and community feedback focuses on other Copilot surfaces (Word, Outlook) being underwhelming rather than confirming Cowork's autonomous task delivery. Missing for 10: hands-on or independent evidence of a background task actually running unattended and returning a completed result, clearer scope/limits of Cowork, and confirmation this isn't just synchronous chat-assisted editing.

      • [claimed-docs] “With Cowork, Copilot can also help with bigger, multi-step tasks and deliver completed to-dos.”
      • [claimed-docs] “Browse with Copilot lets Copilot perform actions directly in your Microsoft Edge browser, such as clicking, typing, and navigating tabs.”
      • [claimed-docs] “You can see each step in real time and take control at any time. All actions run locally in your browser, ensuring full visibility and contr…”
      • [claimed-docs] “You can see each step in real time and take control at any time.”
      • [claimed-docs] “Copilot will ask for your attention and supervision for certain actions, such as buying an item, booking a reservation, sending an email, or…”
      proof ↗⚑ flag

    2. power-userHave the assistant operate a web browser on my behalf to research and complete tasks on websites

      weight 3 · round to ChatGPT
      ChatGPTfullclaimed8/10

      ChatGPT's Browser feature explicitly lets it open websites, gather information, and take action on the user's behalf while staying in control, and can complete multi-step tasks like comparing options or completing actions on a website; this is reinforced by Computer Use (operating GUIs) and Work/Codex browser tab integration for signed-in site tasks. missing for 10: independent hands-on verification of complex multi-step website task completion, and detail on reliability/success rate limits.

      • [claimed-docs] “Browser lets ChatGPT open websites, gather current information, and take action while you stay in control.”
      • [claimed-docs] “Use it to compare options, complete a multi-step task on a website, or review a page you're building.”
      • [claimed-docs] “With Computer Use, ChatGPT can see and operate graphical user interfaces on macOS or Windows.”
      • [claimed-docs] “ChatGPT can see and operate graphical user interfaces on macOS or Windows”
      • [claimed-docs] “Bring an open tab into a ChatGPT Work or Codex chat and work with the website where you're already signed in.”
      • [claimed-docs] “Follow the sign-in request and enter your details in the sign-in flow, not in the chat. This doesn't connect your local browser profile.”
      • [claimed-docs] “With Site tools (WebMCP), ChatGPT Work and Codex can use actions offered by a website in the desktop app's built-in browser.”
      proof ↗⚑ flag
      Microsoft Copilotpartialclaimed6/10

      Microsoft documents a dedicated 'Browse with Copilot' capability that lets Copilot click, type, and navigate tabs in Edge to complete web tasks, with real-time visibility and required user confirmation for sensitive actions like purchases or bookings, plus a 'Cowork' mode for multi-step task completion. However, all supporting evidence is first-party docs with no independent/hands-on confirmation of browser-operation success, and community feedback in the pack focuses on Office-integrated Copilot rather than this browsing agent feature. Missing for 10: independent/hands-on validation of the browse-and-complete-task capability, more detail on reliability/success rate on real websites.

      • [claimed-docs] “Browse with Copilot lets Copilot perform actions directly in your Microsoft Edge browser, such as clicking, typing, and navigating tabs.”
      • [claimed-docs] “You can see each step in real time and take control at any time. All actions run locally in your browser, ensuring full visibility and contr…”
      • [claimed-docs] “You can see each step in real time and take control at any time.”
      • [claimed-docs] “Copilot will ask for your attention and supervision for certain actions, such as buying an item, booking a reservation, sending an email, or…”
      • [claimed-docs] “With Cowork, Copilot can also help with bigger, multi-step tasks and deliver completed to-dos.”
      proof ↗⚑ flag

    3. power-userLet the assistant see and operate applications on my computer to complete work

      weight 2 · round to ChatGPT
      ChatGPTfullclaimed9/10

      ChatGPT's Computer Use feature explicitly lets it see and operate GUIs on macOS/Windows, including testing desktop/mobile app flows, backed by Browser and Work agent capabilities that carry out multi-step tasks on the user's behalf. Documentation is extensive and detailed across multiple first-party sources describing screen operation, browser control, and file/app interaction. Missing for 10: independent hands-on verification of Computer Use reliability in practice.

      • [claimed-docs] “With Computer Use, ChatGPT can see and operate graphical user interfaces on macOS or Windows.”
      • [claimed-docs] “ChatGPT can see and operate graphical user interfaces on macOS or Windows”
      • [claimed-docs] “ChatGPT can see and operate graphical user interfaces on macOS or Windows.”
      • [claimed-docs] “Testing a macOS app, Windows app, iOS simulator flow, or another desktop app that ChatGPT is building.”
      • [claimed-docs] “Browser lets ChatGPT open websites, gather current information, and take action while you stay in control.”
      • [claimed-docs] “Use it to compare options, complete a multi-step task on a website, or review a page you're building.”
      • [claimed-docs] “Run projects in parallel, work with files, use your computer, and keep long-running work moving from one desktop workspace.”
      • [claimed-docs] “Unlike Work on the Web, local Work can operate on resources that remain on your computer without requiring you to upload files to a cloud co…”
      • [claimed-docs] “Your ChatGPT data controls apply to content processed through ChatGPT, including screenshots taken by Computer Use.”
      proof ↗⚑ flag
      Microsoft Copilotpartialcommunity6/10

      Microsoft documents 'Browse with Copilot' letting the assistant click, type, and navigate tabs directly in Edge, plus 'Cowork' for multi-step task completion and Vision for seeing images/screens, with human-in-the-loop confirmation for sensitive actions. However, this operating capability is scoped mainly to the browser and Office apps rather than general desktop application control, and community reports describe weak real-world execution (e.g., Copilot in Word failing at basic edits, Outlook integration being minimal), undercutting the strength of the claim. Missing for 10: broad OS-level/desktop app automation beyond Edge/Office, and independent hands-on validation that agentic actions reliably complete tasks.

      • [claimed-docs] “Browse with Copilot lets Copilot perform actions directly in your Microsoft Edge browser, such as clicking, typing, and navigating tabs.”
      • [claimed-docs] “You can see each step in real time and take control at any time. All actions run locally in your browser, ensuring full visibility and contr…”
      • [claimed-docs] “With Cowork, Copilot can also help with bigger, multi-step tasks and deliver completed to-dos.”
      • [claimed-docs] “Copilot will ask for your attention and supervision for certain actions, such as buying an item, booking a reservation, sending an email, or…”
      • [community] “I subscribed for a trial month... Oh boy! It couldn't do anything except append to the end of the document. It couldn't create tables! It co…”
      • [community] “In MacOS Outlook they have a quarter inch sized bar in the main UI with just a button to summarize. It is so bad.”
      proof ↗⚑ flag

    Tasks

    1. power-userSchedule recurring or one-off tasks that run automatically and come back to me with results

      weight 2 · round to ChatGPT
      ChatGPTfullclaimed8/10

      ChatGPT's Automations/Scheduled Tasks feature explicitly supports scheduling recurring or one-off tasks that run in the background and report back, plus event-triggered tasks from Gmail/Slack/GitHub, with a UI to review active, paused, and completed runs. missing for 10: independent/hands-on community corroboration of scheduled task reliability and no detail on notification/result-delivery mechanics beyond docs.

      • [claimed-docs] “Schedule recurring tasks to run in the background.”
      • [claimed-docs] “Scheduled tasks can now start when a supported event occurs in Gmail, Slack, or GitHub.”
      • [claimed-docs] “Schedule recurring tasks to run in the background... Review active, paused, and completed tasks and recent runs in Scheduled.”
      • [claimed-docs] “scheduled tasks can run when a supported Gmail, Slack, or GitHub event occurs”
      • [claimed-docs] “Use an event trigger to triage new email, summarize channel activity, or act on pull request feedback without polling on a fixed cadence.”
      proof ↗⚑ flag
      Microsoft Copilotnone0/10

      The evidence shows Copilot can handle multi-step tasks (Cowork) and automate repetitive work, but there is no mention of scheduling recurring or one-off tasks that run automatically and return results later. Missing for 10: any documentation of a task-scheduling feature, recurrence settings, or proactive notification of completed scheduled runs.

      • [claimed-docs] “With Cowork, Copilot can also help with bigger, multi-step tasks and deliver completed to-dos.”
      • [claimed-docs] “Hand off repetitive work so you can focus on what matters.”
      • [claimed-docs] “A copilot can automate repetitive tasks, no coding required.”
      proof ↗⚑ flag

    Apps devices — stories about apps devices in this arenaApps devices

    Stories about apps devices in this arena

    Apps

    1. power-userUse an official desktop app with OS-level shortcuts and access to what is on my screen

      weight 2 · round to ChatGPT
      ChatGPTpartialclaimed6/10

      The evidence confirms an official ChatGPT desktop app (macOS/Windows) that can 'use your computer' and run 'Computer Use' to see and operate GUIs, including screenshot-based screen access, plus desktop-only features like floating Pets controls and multi-browser support. However, there is no documentation of OS-level global keyboard shortcuts (e.g., a system-wide hotkey to invoke the app) or of general 'what's on my screen' querying outside the specific Computer Use/testing use case. Missing for 10: explicit OS-level shortcut/hotkey documentation, general screen-content awareness beyond Computer Use testing scenarios, independent hands-on confirmation of these desktop-specific features.

      • [claimed-docs] “Run projects in parallel, work with files, use your computer, and keep long-running work moving from one desktop workspace.”
      • [claimed-docs] “Work in Edge, Brave, Opera, or Vivaldi as well as Chrome from the ChatGPT desktop app.”
      • [claimed-docs] “With Computer Use, ChatGPT can see and operate graphical user interfaces on macOS or Windows.”
      • [claimed-docs] “ChatGPT can see and operate graphical user interfaces on macOS or Windows”
      • [claimed-docs] “ChatGPT can see and operate graphical user interfaces on macOS or Windows.”
      • [claimed-docs] “Your ChatGPT data controls apply to content processed through ChatGPT, including screenshots taken by Computer Use.”
      • [claimed-docs] “Type a request or start a voice conversation from the floating Pets controls in the ChatGPT desktop app on macOS and Windows.”
      • [claimed-docs] “Testing a macOS app, Windows app, iOS simulator flow, or another desktop app that ChatGPT is building.”
      proof ↗⚑ flag
      Microsoft Copilotnone0/10

      The evidence pack covers web/Office integrations, browser automation (Edge), and mobile/iOS/Android connectors, but nowhere documents an official standalone desktop app with OS-level keyboard shortcuts or the ability to see/interact with the user's screen content outside a browser. Vision (copilot-docs-30) is limited to photo/image analysis, not live screen capture, and Browse with Copilot (copilot-docs-9, -15, -24) is scoped to actions inside Microsoft Edge, not OS-wide screen access.

      • [claimed-docs] “Browse with Copilot lets Copilot perform actions directly in your Microsoft Edge browser, such as clicking, typing, and navigating tabs.”
      • [claimed-docs] “You can see each step in real time and take control at any time. All actions run locally in your browser, ensuring full visibility and contr…”
      • [claimed-docs] “You can see each step in real time and take control at any time.”
      • [claimed-docs] “See and understand. Use Vision to analyze images, get insights from photos, and search visually.”
      proof ↗⚑ flag

    2. knowledge-workerUse full-featured official mobile apps for iOS and Android

      weight 2 · round to ChatGPT
      ChatGPTfullclaimed7/10

      The iOS App Store listing (chatgpt-docs-20/21/41/52/58/59) documents rich mobile features—voice mode, photo upload, image generation, stickers—confirming a full-featured iOS app, and doc references (chatgpt-docs-67) explicitly mention continuing tasks 'in ChatGPT Work on the web, iOS, or Android,' indicating Android parity. Missing for 10: no dedicated Android app store evidence pack, no independent hands-on reviews of the mobile apps' feature completeness or performance.

      • [claimed-docs] “Photo upload—Snap or upload a picture to transcribe a handwritten recipe or get info about a landmark.”
      • [claimed-docs] “Advanced Voice Mode–Tap the soundwave icon to have a real-time convo on the go.”
      • [claimed-docs] “Advanced Voice Mode–Tap the soundwave icon to have a real-time convo on the go. Settle a dinner table debate, or practice a new language.”
      • [claimed-docs] “Snap or upload a picture to transcribe a handwritten recipe or get info about a landmark.”
      • [claimed-docs] “Image generation–Generate original images from a description, or transform existing ones with a few simple words.”
      • [claimed-docs] “Choose an image and style, remix with emojis, and make personalized stickers that are ready to share in your group chat.”
      • [claimed-docs] “continue a task that needs a website account in ChatGPT Work on the web, iOS, or Android”
      proof ↗⚑ flag
      Microsoft Copilotpartialclaimed6/10

      Docs explicitly confirm 'Copilot connectors are currently available on Copilot.com and on Copilot Mobile (iOS and Android)', establishing official iOS/Android apps exist and support core connector/chat features. However, there's no first-party or hands-on evidence detailing mobile-specific feature parity (e.g., Word/Excel/PowerPoint copilots, Vision, voice mode) on the mobile apps, and community feedback focuses only on desktop/Office integration quality, not mobile experience. Missing for 10: mobile-specific feature parity details, hands-on mobile app reviews, and confirmation of full functionality (Vision, Voice, connectors) actually working within the mobile app UI.

      • [claimed-docs] “Copilot connectors are currently available on Copilot.com and on Copilot Mobile (iOS and Android)”
      • [claimed-docs] “Copilot can connect with the following consumer services: * Microsoft OneDrive * Microsoft Outlook.com (email, calendar, and contacts) …”
      • [claimed-docs] “If users send prompts in natural language voice within the Copilot Voice mode, they will receive audio responses.”
      • [claimed-docs] “See and understand. Use Vision to analyze images, get insights from photos, and search visually.”
      proof ↗⚑ flag

    Custom bots

    1. power-userBuild and share custom assistants with their own instructions and knowledge

      weight 2 · round to ChatGPT
      ChatGPTpartialclaimed5/10

      Docs confirm a 'GPT builder' concept for creating custom GPTs with configurable actions/connected apps and a dedicated 'gpts-and-sharing' doc implying sharing, but no evidence details custom instructions or uploading a knowledge base, and no independent/hands-on corroboration of the sharing flow. Missing for 10: explicit mention of setting custom instructions, uploading knowledge files, and community/hands-on validation of building and sharing a custom GPT.

      • [claimed-docs] “Allow GPT builders to use approved workspace apps or configure actions that interact with permitted third-party APIs.”
      • [claimed-docs] “configure actions that interact with permitted third-party APIs”
      • [claimed-docs] “GPT builders can use either connected apps or custom actions, but not both in the same GPT.”
      proof ↗⚑ flag
      Microsoft Copilotnone0/10

      No evidence describes creating custom Copilot agents/assistants with custom instructions and knowledge base (like Copilot Studio agents or GPT-builder equivalents) nor sharing them with others; evidence only covers built-in Office integrations, connectors, and memory features. Missing for 10: any mention of an agent/assistant builder, custom instructions, custom knowledge upload, and sharing/publishing mechanism for user-built assistants.

        ⚑ flag

      Automation depth — how much of the product can run unattendedAutomation depth

      How much of the product can run unattended

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

        weight 2 · round to ChatGPT
        ChatGPTpartialclaimed6/10

        ChatGPT/Codex docs show concrete bulk-style automation: 'bulk-scan' scanning many repositories in one campaign (chatgpt-docs-98), a CLI for scanning multiple repos over time (chatgpt-docs-97), running multiple projects in parallel (chatgpt-docs-32), and delegating work to subagents (chatgpt-docs-103), plus background scheduled tasks with multiple runs (chatgpt-docs-37). This covers meaningful bulk/parallel automation but is concentrated in coding/security contexts rather than general-purpose bulk operations across arbitrary item sets, and there's no independent/hands-on corroboration of these bulk claims. Missing for 10: evidence of bulk operations on non-code items (e.g., bulk document/data processing), and independent verification that bulk-scan/subagent delegation works reliably at scale.

        • [claimed-docs] “Use `npx @openai/codex-security bulk-scan` to review repositories in one campaign.”
        • [claimed-docs] “Use its command-line interface (CLI) to scan repositories you own or have permission to assess, review findings over time”
        • [claimed-docs] “Run projects in parallel, work with files, use your computer, and keep long-running work moving from one desktop workspace.”
        • [claimed-docs] “In ChatGPT Work, ask ChatGPT to delegate independent work to subagents.”
        • [claimed-docs] “Schedule recurring tasks to run in the background... Review active, paused, and completed tasks and recent runs in Scheduled.”
        proof ↗⚑ flag
        Microsoft Copilotpartialcommunity3/10

        Docs mention general automation of 'repetitive tasks' and multi-step task completion via Cowork, but there's no concrete evidence of bulk operations across many items (e.g., batch-editing many files, mass email actions, or large-scale spreadsheet manipulation). Community feedback (copilot-comm-4) reports Copilot in Word failing at basic single-document tasks like search-and-replace, casting doubt on any claim of robust bulk-item processing. missing for 10: explicit bulk/batch operation examples (e.g., mass-processing many files/rows/emails at once), independent hands-on evidence of successful bulk actions, and confirmation that Cowork or Analyst can operate at scale across many items reliably.

        • [claimed-docs] “With Cowork, Copilot can also help with bigger, multi-step tasks and deliver completed to-dos.”
        • [claimed-docs] “Hand off repetitive work so you can focus on what matters.”
        • [claimed-docs] “A copilot can automate repetitive tasks, no coding required.”
        • [community] “I subscribed for a trial month... Oh boy! It couldn't do anything except append to the end of the document. It couldn't create tables! It co…”
        proof ↗⚑ flag

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

        weight 3 · round to ChatGPT
        ChatGPTfullclaimed7/10

        ChatGPT's automations/scheduled tasks feature explicitly supports event-driven triggers (Gmail, Slack, GitHub) instead of just fixed schedules, letting users define rules that fire actions on external events, and lets them review active/paused/completed runs. Missing for 10: independent or hands-on verification that these event triggers work reliably in practice, and detail on how flexible/general the rule definitions can be beyond the three named integrations.

        • [claimed-docs] “Schedule recurring tasks to run in the background.”
        • [claimed-docs] “Scheduled tasks can now start when a supported event occurs in Gmail, Slack, or GitHub.”
        • [claimed-docs] “Use an event trigger to triage new email, summarize channel activity, or act on pull request feedback without polling on a fixed cadence.”
        • [claimed-docs] “Schedule recurring tasks to run in the background... Review active, paused, and completed tasks and recent runs in Scheduled.”
        • [claimed-docs] “scheduled tasks can run when a supported Gmail, Slack, or GitHub event occurs”
        proof ↗⚑ flag
        Microsoft Copilotnone0/10

        The evidence describes Copilot responding to prompts, browsing, summarizing, and connecting to services, but there is no mention of user-defined rules or triggers that fire actions automatically on events (e.g., 'when email arrives, do X' style automation). No scheduling, event-trigger, or workflow-builder capability is documented.

          ⚑ flag

        • ai-native userSchedule recurring jobs or workflows

          weight 2 · round to ChatGPT
          ChatGPTfullclaimed8/10

          ChatGPT's Scheduled Tasks/Automations feature explicitly supports recurring background jobs ('Schedule recurring tasks to run in the background,' with review of active/paused/completed runs) and even event-based triggers (Gmail, Slack, GitHub) as an alternative to fixed cadence. This directly matches the story of scheduling recurring jobs/workflows with first-party docs. Missing for 10: independent/hands-on community corroboration of the scheduling feature specifically (evidence pack community items don't address automations/scheduling) and more detail on reliability/limits in practice.

          • [claimed-docs] “Schedule recurring tasks to run in the background.”
          • [claimed-docs] “Schedule recurring tasks to run in the background... Review active, paused, and completed tasks and recent runs in Scheduled.”
          • [claimed-docs] “Scheduled tasks can now start when a supported event occurs in Gmail, Slack, or GitHub.”
          • [claimed-docs] “scheduled tasks can run when a supported Gmail, Slack, or GitHub event occurs”
          • [claimed-docs] “Use an event trigger to triage new email, summarize channel activity, or act on pull request feedback without polling on a fixed cadence.”
          proof ↗⚑ flag
          Microsoft Copilotnone0/10

          No evidence describes scheduling recurring jobs, timers, or automated recurring workflows in Microsoft Copilot; the pack shows one-off task automation (Cowork, connectors, browse actions) but nothing about recurrence or scheduling.

            ⚑ flag

          • ai-native userVersion, review, and roll back my automations

            weight 1 · round to ChatGPT
            ChatGPTpartialclaimed4/10

            ChatGPT supports scheduled/recurring automations with a review of active/paused/completed task runs (chatgpt-docs-11, chatgpt-docs-37, chatgpt-docs-47), which gives some review and status visibility, but there is no evidence of version history, diffing between automation versions, or a rollback mechanism to revert an automation to a prior state. missing for 10: explicit versioning of automations, diff/comparison between versions, and a documented rollback/revert feature.

            • [claimed-docs] “Schedule recurring tasks to run in the background.”
            • [claimed-docs] “Schedule recurring tasks to run in the background... Review active, paused, and completed tasks and recent runs in Scheduled.”
            • [claimed-docs] “scheduled tasks can run when a supported Gmail, Slack, or GitHub event occurs”
            proof ↗⚑ flag
            Microsoft Copilotnone0/10

            No evidence describes any versioning, history, review workflow, or rollback capability for Copilot's automations (e.g., Cowork, connectors, or agent tasks); evidence only covers connecting services, browsing, memory, and privacy controls. Missing for 10: version history UI, diff/review of automation changes, rollback/undo mechanism, any audit trail for automation edits.

              ⚑ flag

            Connectors apps — stories about connectors apps in this arenaConnectors apps

            Stories about connectors apps in this arena

            Connectors

            1. power-userBrowse a directory of third-party apps and connectors and add them to the assistant

              weight 2 · round to ChatGPT
              ChatGPTfullclaimed7/10

              ChatGPT documents a Plugins/connectors ecosystem — installing named plugins (Slack, Codex Security), connecting to third-party tools like Google Drive, SharePoint, Salesforce, and Gong, and GPT builders choosing 'connected apps' or custom actions from an approved list — which together describe browsing and adding third-party integrations to the assistant. Missing for 10: independent/hands-on confirmation of the actual browse-and-add directory UI/UX and its breadth beyond the named examples.

              • [claimed-docs] “Install the Slack plugin to summarize channels or draft replies.”
              • [claimed-docs] “Install the Codex Security plugin to scan authorized code and confirm plausible vulnerability findings.”
              • [claimed-docs] “Plugins can connect ChatGPT to the tools and information you use for work, such as Google Drive, SharePoint, Salesforce, or Gong.”
              • [claimed-docs] “Allow GPT builders to use approved workspace apps or configure actions that interact with permitted third-party APIs.”
              • [claimed-docs] “GPT builders can use either connected apps or custom actions, but not both in the same GPT.”
              • [claimed-docs] “configure actions that interact with permitted third-party APIs”
              proof ↗⚑ flag
              Microsoft Copilotpartialclaimed4/10

              Docs confirm Copilot supports 'connectors' to a small fixed list of services (OneDrive, Outlook.com, Google Drive, Gmail/Calendar/Contacts) and note these are available on Copilot.com/Mobile, but there is no evidence of a browsable directory/marketplace of third-party apps that power-users can explore and add beyond this short built-in list. missing for 10: evidence of a searchable app/connector marketplace, breadth of third-party (non-Microsoft/Google) integrations, and any independent confirmation of the browsing/add experience.

              • [claimed-docs] “Copilot can connect with the following consumer services: * Microsoft OneDrive * Microsoft Outlook.com (email, calendar, and contacts) …”
              • [claimed-docs] “Copilot can connect with the following consumer services: Microsoft OneDrive, Microsoft Outlook.com (email, calendar, and contacts), Google …”
              • [claimed-docs] “Copilot connectors are currently available on Copilot.com and on Copilot Mobile (iOS and Android)”
              • [claimed-docs] “Copilot can connect with the following consumer services: ... Google Drive ... Google Gmail, Calendar, Contacts”
              • [claimed-docs] “Copilot can connect with the following consumer services: Microsoft OneDrive... Google Drive... Google Gmail, Calendar, Contacts”
              proof ↗⚑ flag

            2. knowledge-workerConnect my cloud drive, email, and calendar so the assistant can search and use them in answers

              weight 3 · round to Microsoft Copilot
              ChatGPTpartialclaimed6/10

              Docs show ChatGPT can connect to Google Drive/SharePoint via plugins and can trigger on Gmail events, giving cloud-drive and email connectivity, and MCP/plugins provide a general connector framework for third-party tools. However, there is no explicit mention of calendar integration, and all evidence is vendor documentation with no independent/hands-on confirmation that these connectors actually surface content in answers. Missing for 10: explicit calendar connector support, independent corroboration of connector functionality, and clearer 'search across all three data sources in one answer' evidence.

              • [claimed-docs] “Plugins can connect ChatGPT to the tools and information you use for work, such as Google Drive, SharePoint, Salesforce, or Gong.”
              • [claimed-docs] “Install the Slack plugin to summarize channels or draft replies.”
              • [claimed-docs] “Scheduled tasks can now start when a supported event occurs in Gmail, Slack, or GitHub.”
              • [claimed-docs] “scheduled tasks can run when a supported Gmail, Slack, or GitHub event occurs”
              • [claimed-docs] “Model Context Protocol (MCP) connects models to tools and context. Use it to give ChatGPT or Codex access to third-party documentation”
              • [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.”
              proof ↗⚑ flag
              Microsoft Copilotfullcommunity8/10

              Microsoft's documentation explicitly describes connecting Copilot to OneDrive, Outlook.com (email/calendar/contacts), Google Drive, and Google Gmail/Calendar/Contacts, with example queries for finding files, emails, and calendar events, indicating the assistant can search and use this data in answers. Community evidence corroborates that cross-document/data fetching works well in some contexts, though other complaints focus on unrelated feature quality issues (e.g., editing limitations) rather than disputing the connector capability itself. Missing for 10: independent hands-on verification specifically of the cloud-drive/email/calendar connector search feature (rather than in-app Office Copilot) and more detail on reliability/completeness of search results.

              • [claimed-docs] “Copilot can connect with the following consumer services: * Microsoft OneDrive * Microsoft Outlook.com (email, calendar, and contacts) …”
              • [claimed-docs] “Find my budget spreadsheet” or “Show me the project plan from last month.”
              • [claimed-docs] “Copilot can connect with the following consumer services: Microsoft OneDrive, Microsoft Outlook.com (email, calendar, and contacts), Google …”
              • [claimed-docs] “Find files quickly: "Find my budget spreadsheet" or "Show me the project plan from last month."”
              • [claimed-docs] “Find Word documents about vacation plans” or “Show me all PDFs.”
              • [claimed-docs] “Show me emails from Sarah about the budget” or “Find my flight confirmation email.”
              • [claimed-docs] “What's on my calendar for tomorrow?” or “When is my next dentist appointment?”
              • [claimed-docs] “Find emails: “Show me emails from Sarah about the budget” or “Find my flight confirmation email.””
              • [claimed-docs] “Check in on your calendar: “What’s on my calendar for tomorrow?” or “When is my next dentist appointment?””
              • [claimed-docs] “Copilot connectors are currently available on Copilot.com and on Copilot Mobile (iOS and Android)”
              • [community] “the way it can fetch data from across documents in 365 is really good”
              proof ↗⚑ flag

            Files analysis — stories about files analysis in this arenaFiles analysis

            Stories about files analysis in this arena

            Analysis

            1. power-userHave the assistant write and run code on my data to produce charts, computed answers, and downloadable files

              weight 3 · round to ChatGPT
              ChatGPTfullcommunity8/10

              ChatGPT's Code Interpreter/Data Analysis capability (documented via file drafting, spreadsheet/PDF handling, interactive visualizations, and downloadable finished files) lets it write and execute code against uploaded data to produce charts and computed answers, then export results as documents/spreadsheets/PDFs. Docs explicitly describe analyzing files, building interactive visualizations, and downloading completed files, and community evidence corroborates real code/file execution capability (e.g., running code/containers, file interpretation plugins). Missing for 10: no dedicated first-party doc page specifically titled 'Code Interpreter/Data Analysis' in this pack, and no hands-on example showing a specific chart-from-CSV walkthrough.

              • [claimed-docs] “Draft and refine documents, presentations, spreadsheets, and PDF files. Review the result, ask for specific changes, and download the comple…”
              • [claimed-docs] “make interactive [visualizations], and build or share websites and apps with [Sites]”
              • [claimed-docs] “Create a deck, analyze files, draft a report, build a project plan”
              • [claimed-docs] “Search the web, browse websites, compare sources, read files, analyze data, and summarize findings.”
              • [claimed-docs] “Draft and refine [documents, presentations, spreadsheets, and PDF files]. Review the result, ask for specific changes, and download the comp…”
              • [community] “This is huge, essentially adding what people have been building with LangChain Tools into the core product. The browser and file-upload/inte…”
              proof ↗⚑ flag
              Microsoft Copilotpartialclaimed6/10

              Docs explicitly state Copilot can 'run code to complete complex calculations and generate graphs' and the 'Analyst' feature 'analyzes data with ease,' plus Excel/Word integrations for working with attached data—covering charts and computed answers. However, there is no explicit documentation of producing downloadable files as an output of this code-execution flow, and no hands-on/community evidence corroborates this specific capability working well (community comments focus on other Office Copilot shortcomings, not code-execution). Missing for 10: explicit downloadable-file output evidence, independent/hands-on confirmation of the code-execution feature itself.

              • [claimed-docs] “Copilot can also run code to complete complex calculations and generate graphs.”
              • [claimed-docs] “Go from raw numbers to real insight—use Analyst to help analyze data with ease.”
              • [claimed-docs] “Turn raw data into clear insights with Copilot in Excel. Detail your task, attach data, and tweak via chat.”
              • [claimed-docs] “Turn raw data into clear insights with Copilot in Excel.”
              proof ↗⚑ flag

            Artifacts

            1. knowledge-workerHave the assistant create and iteratively edit documents, presentations, and other files I can export

              weight 2 · round to ChatGPT
              ChatGPTfullclaimed9/10

              Docs strongly support creating and iteratively editing documents, presentations, spreadsheets, and PDFs, with review/annotation and export/download workflows (chatgpt-docs-8, chatgpt-docs-30, chatgpt-docs-60, chatgpt-docs-66, chatgpt-docs-68, chatgpt-docs-70), plus a dedicated artifacts/canvas viewer supporting annotations and comments for iterative refinement (chatgpt-docs-7, chatgpt-docs-18, chatgpt-docs-24, chatgpt-docs-101). Missing for 10: independent hands-on corroboration specifically of document/presentation export workflows (community evidence pack focuses on other capabilities like coding/search, not file export).

              • [claimed-docs] “Draft and refine documents, presentations, spreadsheets, and PDF files.”
              • [claimed-docs] “Draft and refine documents, presentations, spreadsheets, and PDF files. Review the result, ask for specific changes, and download the comple…”
              • [claimed-docs] “Draft and refine [documents, presentations, spreadsheets, and PDF files]. Review the result, ask for specific changes, and download the comp…”
              • [claimed-docs] “Create a deck, analyze files, draft a report, build a project plan”
              • [claimed-docs] “Turn research and analysis into documents, presentations, spreadsheets, and other finished work.”
              • [claimed-docs] “Use ChatGPT Work to turn notes, docs, research, or meeting materials into a structured deck.”
              • [claimed-docs] “Annotations let you point to a specific part of a file and tell ChatGPT what to change.”
              • [claimed-docs] “a document editor can provide tools to find a section or add a comment”
              • [claimed-docs] “Use annotations to point at a specific part of a supported preview and request a focused revision.”
              proof ↗⚑ flag
              Microsoft Copilotdisputedcontradicted4/10

              Microsoft's own docs claim Copilot in Word/Excel/PowerPoint can create and iteratively refine documents, spreadsheets, and presentations via chat (copilot-docs-1,2,3,16), which would let users export finished files. However, a hands-on community report directly contradicts this for Word, stating Copilot 'couldn't do anything except append to the end of the document,' couldn't create tables, search/replace, or maintain formatting (copilot-comm-4), and another user calls Outlook's summarize feature 'so bad' (copilot-comm-5). This is a concrete documented capability failure, not mere skepticism. Missing for 10: independent corroboration of successful iterative multi-turn editing, PowerPoint/Excel hands-on validation, and confirmation of clean export/formatting fidelity.

              • [claimed-docs] “Prompt Copilot with the task, add and upload notes, then refine in the chat—all with Copilot in Word.”
              • [claimed-docs] “Turn raw data into clear insights with Copilot in Excel.”
              • [claimed-docs] “Go from prompt to presentation with Copilot in PowerPoint. Outline the flow, describe visuals, and generate.”
              • [claimed-docs] “Turn raw data into clear insights with Copilot in Excel. Detail your task, attach data, and tweak via chat.”
              • [community] “I subscribed for a trial month... Oh boy! It couldn't do anything except append to the end of the document. It couldn't create tables! It co…”
              • [community] “In MacOS Outlook they have a quarter inch sized bar in the main UI with just a button to summarize. It is so bad.”
              proof ↗⚑ flag

            Files

            1. knowledge-workerUpload documents, spreadsheets, and PDFs and get accurate analysis of their contents

              weight 3 · round to ChatGPT
              ChatGPTfullclaimed7/10

              Docs confirm document/spreadsheet/PDF upload and analysis (draft/refine documents, presentations, spreadsheets, PDFs; 'analyze files'; 'read files, analyze data, and summarize findings'), which directly matches the story. However, evidence is entirely first-party documentation with no independent hands-on validation of accuracy specifically for uploaded file analysis (community evidence covers unrelated web-search accuracy issues, not file analysis). Missing for 10: independent/hands-on verification of analysis accuracy on real uploaded documents/spreadsheets/PDFs, and detail on limits (file size, complex spreadsheet formulas, OCR quality).

              • [claimed-docs] “Draft and refine documents, presentations, spreadsheets, and PDF files.”
              • [claimed-docs] “Draft and refine documents, presentations, spreadsheets, and PDF files. Review the result, ask for specific changes, and download the comple…”
              • [claimed-docs] “Draft and refine [documents, presentations, spreadsheets, and PDF files]. Review the result, ask for specific changes, and download the comp…”
              • [claimed-docs] “Create a deck, analyze files, draft a report, build a project plan”
              • [claimed-docs] “Search the web, browse websites, compare sources, read files, analyze data, and summarize findings.”
              proof ↗⚑ flag
              Microsoft Copilotpartialcommunity6/10

              Microsoft's own docs describe multiple file-analysis capabilities—attaching data in Excel, analyzing notes in Word, finding/searching PDFs and Office documents, an 'Analyst' tool for data insight, and code execution for calculations—giving broad first-party coverage of the story. However, hands-on community reports contradict smooth real-world usability (e.g. Word Copilot 'couldn't do anything except append text... couldn't maintain formatting' and Outlook summarization deemed 'so bad'), while another user praises cross-document data-fetching, so the accuracy/quality of analysis is mixed rather than assured. Missing for 10: independent verification of analysis accuracy on complex spreadsheets/PDFs, and resolution of the documented Word-editing/formatting failures.

              • [claimed-docs] “Prompt Copilot with the task, add and upload notes, then refine in the chat—all with Copilot in Word.”
              • [claimed-docs] “Turn raw data into clear insights with Copilot in Excel.”
              • [claimed-docs] “Go from raw numbers to real insight—use Analyst to help analyze data with ease.”
              • [claimed-docs] “Turn raw data into clear insights with Copilot in Excel. Detail your task, attach data, and tweak via chat.”
              • [claimed-docs] “Find Word documents about vacation plans” or “Show me all PDFs.”
              • [claimed-docs] “Copilot can also run code to complete complex calculations and generate graphs.”
              • [community] “I subscribed for a trial month... Oh boy! It couldn't do anything except append to the end of the document. It couldn't create tables! It co…”
              • [community] “the way it can fetch data from across documents in 365 is really good”
              proof ↗⚑ flag

            Memory context — stories about memory context in this arenaMemory context

            Stories about memory context in this arena

            Memory

            1. power-userHave the assistant remember relevant context from previous chats and apply it in new conversations

              weight 3 · round to ChatGPT
              ChatGPTfullclaimed8/10

              ChatGPT's Memories feature explicitly carries useful context from earlier chats into future conversations, with dedicated docs on memory controls (personalize.md, customization/memories.md) and even CLI-level controls (/memories) for whether a chat can use or contribute to memories. Missing for 10: independent/hands-on community corroboration of cross-chat memory recall working reliably, and detail on limits/scope of what memories retain.

              • [claimed-docs] “Memories let ChatGPT and Codex carry useful context from earlier work into future work.”
              • [claimed-docs] “Memories let ChatGPT carry useful context from earlier chats into future work.”
              • [claimed-docs] “In Codex CLI, use /memories in an interactive session to control whether the current chat can use existing local memories or become an input…”
              • [claimed-docs] “use `/memories` to choose whether a chat can use local memories or contribute to future memories”
              proof ↗⚑ flag
              Microsoft Copilotpartialclaimed6/10

              First-party docs confirm a memory feature: Copilot can store facts users ask it to remember and use that context in future responses, and can proactively surface suggestions based on past queries and memory (copilot-docs-32, copilot-docs-33). However, this is opt-in/explicit fact storage rather than full automatic context carry-over, and there is no independent/hands-on evidence confirming it works reliably across conversations. missing for 10: independent verification of cross-conversation recall, detail on scope/limits of automatic memory use, and confirmation it isn't just facts explicitly asked to be remembered.

              • [claimed-docs] “Copilot can store specific facts users request it to remember, allowing it to generate more relevant responses and suggestions based on that…”
              • [claimed-docs] “Copilot may proactively generate personalized research suggestions for users based on things like past research queries and Copilot memory.”
              • [claimed-docs] “you can delete individual conversations or your entire conversation history at any time”
              proof ↗⚑ flag

            2. power-userSet persistent custom instructions and preferences that shape every response

              weight 1 · round to ChatGPT
              ChatGPTfullclaimed8/10

              ChatGPT supports persistent custom instructions/personalization and Memories that carry context across chats, plus Codex's global AGENTS.md for persistent personal instructions in coding workflows, and fine-grained control via /memories. Missing for 10: independent hands-on verification that custom instructions reliably shape *every* response over long-term use, and no detail on limits/scope conflicts between memories and per-chat overrides.

              • [claimed-docs] “Memories let ChatGPT and Codex carry useful context from earlier work into future work.”
              • [claimed-docs] “Memories let ChatGPT carry useful context from earlier chats into future work.”
              • [claimed-docs] “In Codex, these personal instructions are stored in your global `AGENTS.md` file.”
              • [claimed-docs] “use `/memories` to choose whether a chat can use local memories or contribute to future memories”
              • [claimed-docs] “In Codex CLI, use /memories in an interactive session to control whether the current chat can use existing local memories or become an input…”
              proof ↗⚑ flag
              Microsoft Copilotpartialclaimed5/10

              Docs confirm a memory feature where Copilot can store facts users ask it to remember and use them to personalize future responses and suggestions, plus controls to view/delete memory (copilot-docs-32, copilot-docs-33, copilot-docs-38). However there is no dedicated 'custom instructions' setting described (unlike explicit persona/tone controls), and no independent/hands-on evidence confirming these stored facts consistently shape *every* response. Missing for 10: explicit custom-instructions UI documentation, hands-on confirmation that memory reliably influences all responses, and community corroboration of the feature's effectiveness.

              • [claimed-docs] “Copilot can store specific facts users request it to remember, allowing it to generate more relevant responses and suggestions based on that…”
              • [claimed-docs] “Copilot may proactively generate personalized research suggestions for users based on things like past research queries and Copilot memory.”
              • [claimed-docs] “you can delete individual conversations or your entire conversation history at any time”
              • [claimed-docs] “opt out of use of your conversation activity for model training”
              proof ↗⚑ flag

            Projects

            1. knowledge-workerOrganize related chats and files into a project or space that shares context and instructions

              weight 2 · round to ChatGPT
              ChatGPTfullclaimed8/10

              ChatGPT's Projects feature explicitly lets users organize related chats, share context/instructions, and even attach local folders/files for shared context, directly matching the story. Memories also reinforce carrying context across chats. Missing for 10: independent/hands-on corroboration of the Projects feature working as described, and detail on instruction-sharing UI beyond docs claims.

              • [claimed-docs] “Use a project to organize related chats and give ChatGPT the context it needs.”
              • [claimed-docs] “A local project gives chats access to one or more folders on your computer, such as a collection of source files or a codebase.”
              • [claimed-docs] “Memories let ChatGPT and Codex carry useful context from earlier work into future work.”
              • [claimed-docs] “Memories let ChatGPT carry useful context from earlier chats into future work.”
              proof ↗⚑ flag
              Microsoft Copilotnone0/10

              The evidence pack shows Copilot memory (storing facts), connectors to files/email/calendar, and per-app integrations, but nowhere describes a 'project' or 'space' concept that lets a user group related chats and files together with shared instructions/context, unlike competitors' project/space features. Community feedback focuses on integration quality issues, not on organizational/workspace features. Missing for 10: any documented 'project', 'space', 'workspace', or chat-grouping feature with shared custom instructions and file scoping.

              • [claimed-docs] “Copilot can store specific facts users request it to remember, allowing it to generate more relevant responses and suggestions based on that…”
              • [claimed-docs] “Copilot may proactively generate personalized research suggestions for users based on things like past research queries and Copilot memory.”
              • [claimed-docs] “Copilot can connect with the following consumer services: * Microsoft OneDrive * Microsoft Outlook.com (email, calendar, and contacts) …”
              proof ↗⚑ flag

            Multimodal — stories about multimodal in this arenaMultimodal

            Stories about multimodal in this arena

            Images

            1. knowledge-workerGenerate and edit images from natural-language prompts

              weight 2 · round to ChatGPT
              ChatGPTfullclaimed9/10

              ChatGPT's docs explicitly cover image generation and editing from natural-language prompts, including editing via Comment/annotations, reference images, and Canvas view for reviewing multiple images, plus mobile app support for generating/transforming images and creating stickers. This directly matches the knowledge-worker story of generating and editing images conversationally. Missing for 10: no independent/hands-on community corroboration specifically for image generation quality or reliability.

              • [claimed-docs] “Ask ChatGPT to generate or edit images.”
              • [claimed-docs] “use Comment to add precise feedback to one or more images”
              • [claimed-docs] “Generate or edit images, make interactive visualizations, and build or share websites and apps with Sites.”
              • [claimed-docs] “Ask ChatGPT to generate or edit images. Use image generation for UI assets, banners, backgrounds, illustrations”
              • [claimed-docs] “Switch between Focused view to inspect one image and Canvas view to see the images generated in the same chat.”
              • [claimed-docs] “In Canvas view, use Comment to add precise feedback to one or more images.”
              • [claimed-docs] “Add a reference image when you want ChatGPT to transform an existing asset or use it as visual guidance.”
              • [claimed-docs] “Image generation–Generate original images from a description, or transform existing ones with a few simple words.”
              • [claimed-docs] “Choose an image and style, remix with emojis, and make personalized stickers that are ready to share in your group chat.”
              proof ↗⚑ flag
              Microsoft Copilotnone0/10

              The evidence pack only shows Copilot's 'Vision' feature for analyzing and understanding images (copilot-docs-30), not generating or editing images from text prompts; no docs, community, or probe evidence mentions an image-generation or image-editing capability (e.g., a Designer/DALL·E-style feature).

              • [claimed-docs] “See and understand. Use Vision to analyze images, get insights from photos, and search visually.”
              proof ↗⚑ flag

            2. knowledge-workerShare screenshots and photos and have the assistant accurately interpret what is in them

              weight 2 · round to ChatGPT
              ChatGPTfullclaimed7/10

              First-party docs confirm ChatGPT accepts photo/screenshot uploads and interprets their content (e.g., transcribing a handwritten recipe or identifying a landmark from a photo), which directly matches the knowledge-worker use case of sharing images for analysis. Missing for 10: independent/hands-on evidence corroborating accuracy of image interpretation, and explicit documentation of screenshot-specific analysis (e.g., UI screenshots) rather than just general photo uploads.

              • [claimed-docs] “Photo upload—Snap or upload a picture to transcribe a handwritten recipe or get info about a landmark.”
              • [claimed-docs] “Snap or upload a picture to transcribe a handwritten recipe or get info about a landmark.”
              • [claimed-docs] “Image generation–Generate original images from a description, or transform existing ones with a few simple words.”
              proof ↗⚑ flag
              Microsoft Copilotpartialclaimed5/10

              Docs confirm Copilot has a 'Vision' capability to analyze images and photos ([copilot-docs-30]), directly supporting the story, but this is a single first-party mention with no elaboration on screenshot-specific use cases or accuracy, and no independent/hands-on evidence corroborates real-world interpretation quality. Missing for 10: detailed documentation on screenshot vs photo handling, accuracy benchmarks, and independent/community verification of correct image interpretation.

              • [claimed-docs] “See and understand. Use Vision to analyze images, get insights from photos, and search visually.”
              proof ↗⚑ flag

            Voice

            1. knowledge-workerHave a natural, real-time voice conversation with the assistant

              weight 2 · round to ChatGPT
              ChatGPTfullclaimed8/10

              ChatGPT ships Advanced Voice Mode for real-time spoken conversation on mobile ('Tap the soundwave icon to have a real-time convo on the go') and ChatGPT Voice on desktop that lets users talk through ideas, start work, check progress, or change direction without switching to typing. This directly matches the knowledge-worker story of natural, real-time voice conversation. Missing for 10: independent hands-on corroboration of voice quality/latency and any community verification beyond vendor docs.

              • [claimed-docs] “Advanced Voice Mode–Tap the soundwave icon to have a real-time convo on the go.”
              • [claimed-docs] “Advanced Voice Mode–Tap the soundwave icon to have a real-time convo on the go. Settle a dinner table debate, or practice a new language.”
              • [claimed-docs] “ChatGPT Voice lets you talk through ideas and coordinate tasks in Chat, Work, and Codex in the ChatGPT desktop app. Start work, check progre…”
              • [claimed-docs] “Start work, check progress, or change direction without switching back to typing.”
              • [claimed-docs] “ChatGPT Voice lets you talk through ideas and coordinate tasks in Chat, Work, and Codex in the ChatGPT desktop app.”
              • [claimed-docs] “ChatGPT Voice can start separate tasks for longer work, check existing tasks, and send follow-up instructions.”
              proof ↗⚑ flag
              Microsoft Copilotfullclaimed6/10

              Microsoft's transparency docs explicitly describe Copilot Voice mode: users send natural-language voice prompts and receive audio responses, with citations shown in conversation transcripts, confirming real-time spoken interaction. Missing for 10: independent/hands-on corroboration of voice mode's real-time quality, latency, or interruption handling, and no community evidence specifically validates or disputes the voice experience.

              • [claimed-docs] “If users send prompts in natural language voice within the Copilot Voice mode, they will receive audio responses.”
              • [claimed-docs] “This means that Copilot centers its response on high-ranking content from the web and provides hyperlinked citations following generated tex…”
              proof ↗⚑ flag

            Openness — open source, data portability, and self-hosting storiesOpenness

            Open source, data portability, and self-hosting stories

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

              weight 2 · round to ChatGPT
              ChatGPTpartialprobed3/10

              There is evidence of programmatic access via the Codex CLI/SDK for coding automation and CI jobs, and a security-scan CLI, but nothing shows that the broad set of UI-only capabilities (Canvas/image editing, Computer Use, Voice, Work desktop automations, Sites, MCP-in-chat, memories, scheduled tasks) are exposed through a general ChatGPT API with parity to the UI. A probe for an OpenAPI/swagger spec on the docs site also returned 404s, reinforcing the lack of a documented full API surface. missing for 10: documented API endpoints mirroring Canvas/image tools, Computer Use, Voice, Work automations, Sites, and MCP-in-chat; independent confirmation of API-UI feature parity.

              • [claimed-docs] “Use the Codex SDK to automate coding tasks, including jobs in CI.”
              • [claimed-docs] “Inspect code, make changes, run commands, and automate repeatable work without leaving your terminal.”
              • [claimed-docs] “Use its command-line interface (CLI) to scan repositories you own or have permission to assess, review findings over time”
              • [probe] “PROBE openapi: all candidate paths 404 (https://learn.chatgpt.com/openapi.json, https://learn.chatgpt.com/swagger.json, https://learn.chatgp…”
              proof ↗⚑ flag
              Microsoft Copilotnone0/10

              No evidence of a public API exposing Copilot's UI capabilities (chat, connectors, Word/Excel/PowerPoint copilots) programmatically; probes for OpenAPI/docs endpoints returned 404s, and all evidence describes UI/chat-only functionality. Missing for 10: any documented API/SDK, endpoint parity documentation, or third-party confirmation of programmatic access to Copilot features.

              • [probe] “PROBE llms.txt: HTTP 404 at https://support.microsoft.com/llms.txt”
              • [probe] “PROBE docs-md: HTTP 404 at https://support.microsoft.com/en-us/copilot.md”
              • [probe] “PROBE openapi: all candidate paths 404 (https://support.microsoft.com/openapi.json, https://support.microsoft.com/swagger.json, https://supp…”
              • [claimed-docs] “Prompt Copilot with the task, add and upload notes, then refine in the chat—all with Copilot in Word.”
              • [claimed-docs] “Browse with Copilot lets Copilot perform actions directly in your Microsoft Edge browser, such as clicking, typing, and navigating tabs.”
              proof ↗⚑ flag

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

              weight 3 · round drawn
              ChatGPTnone0/10

              No evidence in the pack of a data export feature producing open/portable formats, nor any mention of account data export or deletion workflow. Evidence only covers general product features (Codex, Work, MCP, image gen, etc.) with nothing about exporting personal chat/data history or leaving the platform with your data intact.

                ⚑ flag
                Microsoft Copilotnone0/10

                No evidence of a data export/portability feature or open-format export mechanism; docs only mention deleting conversation history, not exporting it, and probes for machine-readable docs/APIs 404. There is nothing showing users can export chats, memory, or generated content in open formats to leave the platform.

                • [claimed-docs] “you can delete individual conversations or your entire conversation history at any time”
                • [claimed-docs] “opt out of use of your conversation activity for model training”
                • [probe] “PROBE llms.txt: HTTP 404 at https://support.microsoft.com/llms.txt”
                • [probe] “PROBE docs-md: HTTP 404 at https://support.microsoft.com/en-us/copilot.md”
                • [probe] “PROBE openapi: all candidate paths 404 (https://support.microsoft.com/openapi.json, https://support.microsoft.com/swagger.json, https://supp…”
                proof ↗⚑ flag

              Privacy posture — data-handling and privacy storiesPrivacy posture

              Data-handling and privacy stories

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

                weight 2 · round drawn
                ChatGPTnone0/10

                No evidence in the pack addresses data residency or regional storage choice for ChatGPT; the evidence only touches general data controls (e.g., Computer Use screenshots) without any region-selection capability.

                  ⚑ flag
                  Microsoft Copilotnone0/10

                  No evidence in the pack mentions data residency, regional storage controls, or any user-facing setting to choose where data is stored; the docs cover features, connectors, and privacy opt-outs but not geographic data residency choices.

                    ⚑ flag

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

                    weight 3 · round to Microsoft Copilot
                    ChatGPTnone0/10

                    The evidence pack contains no documentation or mention of data-training opt-out controls, privacy settings, or 'improve the model for everyone' toggles; only tangential data-controls mention (chatgpt-docs-89) refers to Computer Use screenshots, not training opt-out generally. Missing for 10: any reference to training-data opt-out settings, business/API data-usage policies, or privacy dashboard controls.

                    • [claimed-docs] “Your ChatGPT data controls apply to content processed through ChatGPT, including screenshots taken by Computer Use.”
                    proof ↗⚑ flag
                    Microsoft Copilotpartialcommunity6/10

                    Microsoft's privacy FAQ explicitly states users can opt out of having conversation activity used for model training and can delete conversation history (copilot-docs-35, copilot-docs-36, copilot-docs-38), giving a documented mechanism to prevent training use. However, community reports (copilot-comm-6, copilot-comm-1) show real confusion about scope — a user working in Word had no clear indication whether their document content was being fed to training, and commenters note the opt-out/behavior differs between standalone Copilot chat and 365-integrated Copilot, undermining confidence that the control is comprehensive or transparent across all surfaces. missing for 10: independent verification that opt-out actually blocks training across all integrated products (Word/Excel/Outlook), clearer UI-level opt-out controls inside Office apps, and confirmation the toggle covers enterprise/connector data sources.

                    • [claimed-docs] “opt out of use of your conversation activity for model training”
                    • [claimed-docs] “Train our generative AI models to create a better experience for you and others.”
                    • [claimed-docs] “you can delete individual conversations or your entire conversation history at any time”
                    • [community] “When CoPilot showed up in my Word, I was writing a pitch doc... It made me realize I didn't know whether this doc was getting auto-pushed to…”
                    • [community] “To be clear this is only for the standalone Copilot chat or app and website; not for the 'Copilot' services integrated into Office 365 etc.”
                    proof ↗⚑ flag

                  • ai-native userControl data retention and deletion

                    weight 2 · round to Microsoft Copilot
                    ChatGPTpartialclaimed3/10

                    The only relevant evidence is a passing reference that 'ChatGPT data controls apply to content processed through ChatGPT, including screenshots taken by Computer Use,' implying some data-control/retention settings exist, but no documentation details how to view, export, or delete data, set retention periods, or manage memory deletion. Missing for 10: explicit data retention/export/delete documentation, memory deletion controls, and independent confirmation that these controls work as described.

                    • [claimed-docs] “Your ChatGPT data controls apply to content processed through ChatGPT, including screenshots taken by Computer Use.”
                    proof ↗⚑ flag
                    Microsoft Copilotpartialcommunity6/10

                    Docs confirm users can delete individual conversations or entire history and opt out of conversation data being used for model training, giving basic retention/deletion control for the standalone Copilot chat experience (copilot-docs-35, copilot-docs-38). However, community evidence notes this applies only to the standalone Copilot app/site, not to Copilot embedded in Office apps like Word, where a user reported uncertainty about whether their document was being auto-pushed for training with no visible deletion controls (copilot-comm-1, copilot-comm-6). Missing for 10: enterprise/Office-integrated retention controls, clarity on data retention duration before deletion, and independent verification that deletion actually removes data from training pipelines.

                    • [claimed-docs] “opt out of use of your conversation activity for model training”
                    • [claimed-docs] “you can delete individual conversations or your entire conversation history at any time”
                    • [community] “To be clear this is only for the standalone Copilot chat or app and website; not for the 'Copilot' services integrated into Office 365 etc.”
                    • [community] “When CoPilot showed up in my Word, I was writing a pitch doc... It made me realize I didn't know whether this doc was getting auto-pushed to…”
                    proof ↗⚑ flag

                  • ai-native userOpt out of telemetry and usage tracking

                    weight 2 · round to Microsoft Copilot
                    ChatGPTnone0/10

                    None of the evidence addresses telemetry/usage-tracking opt-out controls for ChatGPT; the docs cover data controls tangentially (e.g., data usage for Computer Use screenshots) but nothing about disabling telemetry or usage analytics.

                      ⚑ flag
                      Microsoft Copilotdisputedcontradicted5/10

                      Microsoft's own privacy FAQ states users can opt out of having conversation activity used for model training and can delete individual or entire conversation history (copilot-docs-35, copilot-docs-38), which is a real opt-out mechanism for the standalone Copilot chat. However, community reports directly contradict this for Copilot as embedded in Office apps: a Word for Mac user reports 'no way of turning it off' and 'no opt-out mechanism' (copilot-comm-3), and another user reports uncertainty over whether their document was being auto-pushed to Copilot for training with no visible control (copilot-comm-6) — and copilot-comm-1 clarifies the training opt-out only applies to the standalone chat app, not the Office-integrated Copilot surfaces. Missing for 10: a unified, product-wide opt-out control covering all Copilot surfaces (Office, Edge, Windows), independent verification that the training opt-out actually stops data use, and clarity on telemetry beyond training data.

                      • [claimed-docs] “opt out of use of your conversation activity for model training”
                      • [claimed-docs] “you can delete individual conversations or your entire conversation history at any time”
                      • [community] “To be clear this is only for the standalone Copilot chat or app and website; not for the 'Copilot' services integrated into Office 365 etc.”
                      • [community] “Hate that if you use Word for Mac, you now have Copilot next to your cursor with no way of turning it off. I just want to use Word... Now th…”
                      • [community] “When CoPilot showed up in my Word, I was writing a pitch doc... It made me realize I didn't know whether this doc was getting auto-pushed to…”
                      proof ↗⚑ flag

                    Research answers — stories about research answers in this arenaResearch answers

                    Stories about research answers in this arena

                    Research

                    1. knowledge-workerLaunch a deep research run that autonomously searches many sources and returns a cited report

                      weight 3 · round to ChatGPT
                      ChatGPTpartialclaimed6/10

                      Docs show ChatGPT can search the web, browse multiple sources, compare them, and produce cited results in-chat (docs-86, docs-90), and can turn research into finished documents/reports (docs-66, docs-68, docs-60). However, there is no explicit mention of a dedicated 'Deep Research' autonomous multi-source research mode/run with a structured long-form cited report as its own distinct feature — the evidence only shows general web-search-with-citations and document drafting capabilities. missing for 10: an explicitly named deep-research mode, evidence of autonomous long-running multi-source research runs, and a structured final cited-report output format.

                      • [claimed-docs] “Search results and citations appear in the chat when ChatGPT uses web search.”
                      • [claimed-docs] “Search the web, browse websites, compare sources, read files, analyze data, and summarize findings.”
                      • [claimed-docs] “Create a deck, analyze files, draft a report, build a project plan”
                      • [claimed-docs] “Turn research and analysis into documents, presentations, spreadsheets, and other finished work.”
                      • [claimed-docs] “Draft and refine [documents, presentations, spreadsheets, and PDF files]. Review the result, ask for specific changes, and download the comp…”
                      • [claimed-docs] “In the CLI, pass `--search` to fetch live results for one run”
                      proof ↗⚑ flag
                      Microsoft Copilotpartialclaimed5/10

                      Copilot's 'Researcher' agent is documented as designed to 'find, synthesize, and understand information faster' and Copilot's web-grounded answers include hyperlinked citations, which maps to the deep-research/cited-report story, but there is no detail on autonomous multi-source search depth, report format, or any hands-on/independent validation of report quality. Missing for 10: documentation of the autonomous multi-step search process, description of report output structure, and independent corroboration of research depth/accuracy.

                      • [claimed-docs] “Find, synthesize, and understand information faster with Researcher.”
                      • [claimed-docs] “This means that Copilot centers its response on high-ranking content from the web and provides hyperlinked citations following generated tex…”
                      • [claimed-docs] “Copilot may proactively generate personalized research suggestions for users based on things like past research queries and Copilot memory.”
                      proof ↗⚑ flag

                    2. knowledge-workerGet answers grounded in current web results with citations back to the sources

                      weight 2 · round drawn
                      ChatGPTfullcommunity8/10

                      ChatGPT's web search docs explicitly state that search results and citations appear in chat when web search is used, and describe searching, browsing, comparing sources, and summarizing findings — directly matching the story. Community feedback shows mixed satisfaction with search accuracy (e.g., comparisons to Perplexity, a weather inaccuracy) but doesn't concretely show citations failing to appear, so this doesn't rise to a dispute. Missing for 10: independent verification of citation accuracy/consistency across many queries and no first-party detail on citation formatting/source diversity.

                      • [claimed-docs] “Search results and citations appear in the chat when ChatGPT uses web search.”
                      • [claimed-docs] “Search the web, browse websites, compare sources, read files, analyze data, and summarize findings.”
                      • [claimed-docs] “In the CLI, pass `--search` to fetch live results for one run”
                      • [community] “AKA Bing Search in ChatGPT. So it is not it's own search engine and is still using Bing for its results just like the rest of them.”
                      • [community] “I gave it a quick spin and my initial impression is much worse than perplexity.”
                      • [community] “I asked it the current weather in my area and the temperature was off by 23 degrees F.”
                      proof ↗⚑ flag
                      Microsoft Copilotfullclaimed8/10

                      Docs explicitly state Copilot grounds responses in high-ranking web content and provides hyperlinked citations after generated responses, directly matching the story; this is corroborated by broader documentation on research/answer features (Researcher, ask questions and get answers fast). Missing for 10: independent hands-on verification of citation accuracy/quality and no community evidence specifically testing web-grounded citation behavior.

                      • [claimed-docs] “This means that Copilot centers its response on high-ranking content from the web and provides hyperlinked citations following generated tex…”
                      • [claimed-docs] “Ask questions and get answers fast.”
                      • [claimed-docs] “Find, synthesize, and understand information faster with Researcher.”
                      proof ↗⚑ flag

                    Trust controls — stories about trust controls in this arenaTrust controls

                    Stories about trust controls in this arena

                    Admin

                    1. team-adminManage members, permissions, and data policies for my organization's workspace

                      weight 2 · round to ChatGPT
                      ChatGPTpartialclaimed4/10

                      Only a single explicit doc line notes that a workspace administrator can control access to ChatGPT Work, plugins, browser use, and network access, plus general mentions of GPT builders using 'approved workspace apps' and data controls applying to processed content. There is no evidence of a full admin console covering member invitation/removal, granular role-based permissions, or explicit data retention/training-opt-out policy controls. missing for 10: admin console/member management UI, granular role/permission settings, explicit data-retention and training-opt-out policy controls, independent corroboration of these admin features.

                      • [claimed-docs] “Your workspace administrator can control access to ChatGPT Work, plugins, browser use, and network access.”
                      • [claimed-docs] “Allow GPT builders to use approved workspace apps or configure actions that interact with permitted third-party APIs.”
                      • [claimed-docs] “configure actions that interact with permitted third-party APIs”
                      • [claimed-docs] “Your ChatGPT data controls apply to content processed through ChatGPT, including screenshots taken by Computer Use.”
                      proof ↗⚑ flag
                      Microsoft Copilotnone0/10

                      The evidence pack covers only individual/consumer Copilot features (writing, spreadsheets, browsing, memory, privacy opt-outs for personal conversations) with no mention of team/workspace admin controls such as member management, role-based permissions, or organizational data policies. Missing for 10: admin console documentation, member/role management, org-wide data governance policies, and any evidence of a team-admin experience.

                        ⚑ flag

                      Data controls

                      1. knowledge-workerExport my complete chat history and account data

                        weight 1 · round drawn
                        ChatGPTnone0/10

                        The evidence pack contains no mention of data export, account data download, or chat history export features anywhere in the docs, community, or probe results; there is only a passing reference to 'data controls' applying to Computer Use content, which does not address exporting complete chat history or account data. Missing for 10: any documentation of an export data feature, its scope (chats, files, settings), format, or process, and any independent corroboration it works.

                        • [claimed-docs] “Your ChatGPT data controls apply to content processed through ChatGPT, including screenshots taken by Computer Use.”
                        proof ↗⚑ flag
                        Microsoft Copilotnone0/10

                        Evidence shows users can delete individual conversations or entire history (copilot-docs-38) and opt out of training use (copilot-docs-35), but there is no mention of an export/download feature for complete chat history or account data as required by the story.

                        • [claimed-docs] “you can delete individual conversations or your entire conversation history at any time”
                        • [claimed-docs] “opt out of use of your conversation activity for model training”
                        proof ↗⚑ flag

                      2. knowledge-workerControl whether my conversations are used to train models

                        weight 3 · round to Microsoft Copilot
                        ChatGPTnone0/10

                        The evidence pack covers ChatGPT's agentic/feature capabilities (Codex, Work, MCP, Computer Use, etc.) but contains no documentation or mention of data controls, training opt-out settings, or 'Improve the model for everyone' toggles that let a user control whether their conversations are used for model training.

                          ⚑ flag
                          Microsoft Copilotpartialcommunity6/10

                          Microsoft's own docs confirm a control exists: users can opt out of conversation activity being used for model training and can delete conversation history (copilot-docs-35, copilot-docs-36, copilot-docs-38). However, community evidence indicates confusion about scope—one commenter notes the opt-out applies to standalone Copilot chat/app, not to Copilot embedded in Office apps like Word (copilot-comm-1), and another user reports genuine uncertainty whether their Word document was being used for training with no clear indication (copilot-comm-6). Missing for 10: clear unified documentation covering training-data opt-out scope across all Copilot surfaces (Office-integrated vs standalone), and independent verification that the opt-out setting functions as described.

                          • [claimed-docs] “opt out of use of your conversation activity for model training”
                          • [claimed-docs] “Train our generative AI models to create a better experience for you and others.”
                          • [claimed-docs] “you can delete individual conversations or your entire conversation history at any time”
                          • [community] “To be clear this is only for the standalone Copilot chat or app and website; not for the 'Copilot' services integrated into Office 365 etc.”
                          • [community] “When CoPilot showed up in my Word, I was writing a pitch doc... It made me realize I didn't know whether this doc was getting auto-pushed to…”
                          proof ↗⚑ flag

                        Not comparable on these axes

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

                          weight 2 · not comparable
                          ChatGPTfullclaimed7/10

                          ChatGPT's Codex offers a CLI and SDK explicitly documented for headless/CI use ('Use the Codex SDK to automate coding tasks, including jobs in CI'), plus CLI flags (--search, /fast) and a bulk-scan command (npx @openai/codex-security bulk-scan) that support non-interactive automation workflows. missing for 10: independent/hands-on confirmation of actual CI pipeline runs, and more detail on authentication/headless setup specifics for CI environments.

                          • [claimed-docs] “Use the Codex SDK to automate coding tasks, including jobs in CI.”
                          • [claimed-docs] “Inspect code, make changes, run commands, and automate repeatable work without leaving your terminal.”
                          • [claimed-docs] “Use its command-line interface (CLI) to scan repositories you own or have permission to assess, review findings over time”
                          • [claimed-docs] “Use `npx @openai/codex-security bulk-scan` to review repositories in one campaign.”
                          • [claimed-docs] “Use `/fast on`, `/fast off`, or `/fast status` in the CLI to change or inspect the current setting.”
                          • [claimed-docs] “In the CLI, pass `--search` to fetch live results for one run”
                          proof ↗⚑ flag
                          Microsoft Copilotn/a

                          Microsoft Copilot is a consumer/office chat assistant product, not a developer tool or API/CLI designed for headless automation or CI pipelines; there's no evidence of any API, CLI, or SDK for scripted/headless invocation. This axis is a category mismatch for this product type.

                            ⚑ flag

                          • ai-native userConnect an agent via an official MCP server

                            weight 3 · not comparable
                            ChatGPTfullclaimed8/10

                            ChatGPT/Codex has official first-party documentation for MCP support: users can add official MCP servers (e.g., Context7 for docs, Figma, browser tools) to extend the agent, configuration is stored in config.toml, servers can be scoped per-project, and setup carries across clients without redoing it. This directly evidences 'connecting an agent via an official MCP server.' Missing for 10: independent/hands-on community corroboration of MCP server usage and broader detail on the range of officially supported/verified servers beyond the Context7 example.

                            • [claimed-docs] “let it interact with developer tools like your browser or Figma”
                            • [claimed-docs] “Once you configure your MCP servers, you can switch among those clients without redoing setup.”
                            • [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] “to add Context7 (a free MCP server for developer documentation)”
                            • [claimed-docs] “you can also scope MCP servers to a project with `.codex/config.toml` (trusted projects only)”
                            • [claimed-docs] “Codex stores MCP configuration in `config.toml`”
                            proof ↗⚑ flag
                            Microsoft Copilotn/a

                            Microsoft Copilot is itself an AI assistant/agent; the evidence only shows it acting as a client connecting to other services (OneDrive, Gmail, etc.) rather than exposing itself as an MCP server for other agents. Per the agent-role exception, this axis does not apply unless there's evidence of Copilot running as an MCP server, which is absent here.

                            • [claimed-docs] “Copilot can connect with the following consumer services: * Microsoft OneDrive * Microsoft Outlook.com (email, calendar, and contacts) …”
                            • [claimed-docs] “Copilot connectors are currently available on Copilot.com and on Copilot Mobile (iOS and Android)”
                            proof ↗⚑ flag

                          • ai-native userExplore an interactive API reference with runnable examples

                            weight 2 · not comparable
                            ChatGPTnone0/10

                            The evidence pack contains no documentation of an interactive API reference or runnable code examples; a direct probe for OpenAPI/swagger specs on the docs site returned 404 across all candidate paths, and no other citation mentions an API reference sandbox or runnable snippets.

                            • [probe] “PROBE openapi: all candidate paths 404 (https://learn.chatgpt.com/openapi.json, https://learn.chatgpt.com/swagger.json, https://learn.chatgp…”
                            proof ↗⚑ flag
                            Microsoft Copilotn/a

                            Microsoft Copilot is a consumer/productivity AI assistant, not a developer API/SDK product, so the concept of an interactive API reference with runnable examples is a category error for this axis.

                              ⚑ flag

                            • ai-native userTest against a sandbox environment without touching production data

                              weight 1 · not comparable
                              ChatGPTpartialclaimed4/10

                              Codex documentation indicates commands run inside a sandbox by default, with rules governing what can run 'outside the sandbox' (chatgpt-docs-95), and Codex Security's scanning is scoped to repos you own/have permission to assess (chatgpt-docs-97/98), implying isolated execution rather than direct production access. However, there is no explicit documentation describing a dedicated 'test/staging' environment distinct from production data, no detail on how production systems/data are excluded, and no independent/hands-on confirmation of this isolation. Missing for 10: explicit sandbox-vs-production data separation docs, details on network/data isolation guarantees, and independent verification of the sandbox boundary holding in practice.

                              • [claimed-docs] “Use rules to control which commands Codex can run outside the sandbox.”
                              • [claimed-docs] “Use its command-line interface (CLI) to scan repositories you own or have permission to assess, review findings over time”
                              • [claimed-docs] “Use `npx @openai/codex-security bulk-scan` to review repositories in one campaign.”
                              proof ↗⚑ flag
                              Microsoft Copilotn/a

                              Microsoft Copilot is a consumer/productivity AI assistant, not a developer platform with sandbox/test environments distinct from production data; no evidence pack content addresses sandbox testing concepts at all, and this axis is a category error for this product type.

                                ⚑ flag

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

                                weight 2 · not comparable
                                ChatGPTn/a

                                ChatGPT is a closed-source, proprietary SaaS product; open-sourcing its source code is not a plausible axis for this kind of product (unlike an open-source framework or tool), so this is a category mismatch rather than a missing capability.

                                  ⚑ flag
                                  Microsoft Copilotnone0/10

                                  Microsoft Copilot is closed-source proprietary software; no evidence indicates any open-license source availability, and probes for docs/API artifacts returned 404s. This is an applicable axis (a product could conceivably be open-sourced) but no evidence supports it, so verdict is none rather than na.

                                  • [probe] “PROBE llms.txt: HTTP 404 at https://support.microsoft.com/llms.txt”
                                  • [probe] “PROBE docs-md: HTTP 404 at https://support.microsoft.com/en-us/copilot.md”
                                  • [probe] “PROBE openapi: all candidate paths 404 (https://support.microsoft.com/openapi.json, https://support.microsoft.com/swagger.json, https://supp…”
                                  proof ↗⚑ flag

                                • ai-native userSelf-host the core product

                                  weight 3 · not comparable
                                  ChatGPTn/a

                                  ChatGPT is a closed, hosted proprietary product with no evidence of a self-hostable core model or server; self-hosting is not a fair axis for this SaaS product category (it does not ship open weights or an installable core).

                                    ⚑ flag
                                    Microsoft Copilotnone0/10

                                    Microsoft Copilot is a cloud-hosted SaaS product with no evidence of any self-hosted or on-premises deployment option; all documentation describes it as a hosted service (Copilot.com, Microsoft 365 cloud integration, Edge browser actions) with no self-hosting mechanism mentioned.

                                      ⚑ flag