ChatGPT vs Poke

Agent access

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

   weight 2 · round to Poke
   ChatGPT~partialprobed5/10

   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

   Poke✓fullprobed8/10

   A live llms.txt file is confirmed via direct probe (HTTP 200) with actual agent-oriented content describing Poke, and Poke also maintains structured docs pages that agents/tools can be pointed at. missing for 10: no docs.md or openapi.json fallback (both 404), and no independent report of an agent successfully consuming llms.txt end-to-end.

   • [probe] “PROBE llms.txt: HTTP 200 at https://poke.com/llms.txt # Poke > Poke is the proactive AI assistant on Apple Messages, WhatsApp, Telegram, an…”
   • [claimed-docs] “The Poke API allows you to send messages programmatically from your applications, scripts, and automation tools.”
   • [probe] “PROBE docs-md: HTTP 404 at https://poke.com/docs.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://poke.com/openapi.json, https://poke.com/swagger.json, https://poke.com/api/openapi.json, htt…”

   proof ↗⚑ flag

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

   weight 2 · round to ChatGPT
   ChatGPT✓fullclaimed7/10

   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

   Poke~partialprobed6/10

   Poke's docs explicitly state its API can be called from scripts, CI/CD pipelines, and monitoring tools to trigger messages programmatically, which supports headless/automation use (poke-docs-1, poke-docs-2). However, there's no evidence of a full headless run mode (e.g., batch execution, structured output for CI parsing) and probes show no OpenAPI/swagger spec is exposed, suggesting the API's automation surface is thin and undocumented beyond message-sending. Missing for 10: independent/hands-on CI integration examples, a public OpenAPI schema, and evidence of structured/machine-readable responses needed for reliable CI pipelines.

   • [claimed-docs] “The Poke API allows you to send messages programmatically from your applications, scripts, and automation tools.”
   • [claimed-docs] “Services like GitHub, CI/CD pipelines, or monitoring tools can trigger Poke when something happens.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://poke.com/openapi.json, https://poke.com/swagger.json, https://poke.com/api/openapi.json, htt…”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   ChatGPT✓fullclaimed8/10

   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

   Poke✓fullprobed8/10

   Poke's docs explicitly describe MCP server support, with CLI commands to tunnel local MCP servers and add remote ones ('poke mcp add'), plus a recipe/marketplace ecosystem for sharing MCP-based tools. This is first-party documented and corroborated by a probe confirming the docs page exists, though there's no independent hands-on report of the MCP integration actually working. Missing for 10: independent/hands-on verification of MCP tool usage in practice, and more detail on tool invocation reliability.

   • [claimed-docs] “Poke supports Model Context Protocol (MCP) servers, allowing you to extend Poke with custom tools and data sources.”
   • [claimed-docs] “npx poke@latest tunnel http://localhost:3000/mcp -n "Local Dev MCP"”
   • [claimed-docs] “you earn revenue from MCP usage by users who install your recipe”
   • [claimed-docs] “npx poke@latest mcp add https://mcp.example.com/sse -n "My Server"”
   • [probe] “official MCP server documented at https://poke.com/docs/mcp-servers”

   proof ↗⚑ flag

4. ai-native userUse an official CLI

   weight 2 · round to ChatGPT
   ChatGPT✓fullprobed7/10

   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

   Poke~partialclaimed6/10

   Poke ships an official CLI invoked via `npx poke@latest` with subcommands like `login`, `tunnel`, and `mcp add`, confirming a real CLI exists for developer/MCP workflows. However, the documented CLI scope is narrow (mainly MCP server registration/tunneling and login) rather than a general-purpose CLI for broader AI-native automation tasks. Missing for 10: evidence of a fuller command set (e.g. messaging, recipe management, account/config commands) and any independent/hands-on verification of the CLI's reliability.

   • [claimed-docs] “npx poke@latest tunnel http://localhost:3000/mcp -n "Local Dev MCP"”
   • [claimed-docs] “npx poke@latest login”
   • [claimed-docs] “npx poke@latest mcp add https://mcp.example.com/sse -n "My Server"”
   • [claimed-docs] “Poke supports Model Context Protocol (MCP) servers, allowing you to extend Poke with custom tools and data sources.”

   proof ↗⚑ flag

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

   weight 3 · round to Poke
   ChatGPT~partialprobed4/10

   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

   Poke~partialprobed6/10

   Poke documents a public API for sending messages programmatically and integrating with external triggers (CI/CD, monitoring tools), plus CLI/MCP tooling for extending functionality, showing genuine programmatic access. However, no OpenAPI/Swagger spec or formal API reference was found (404s on standard discovery paths), so the API's documentation depth and completeness are unclear. Missing for 10: a full API reference/spec (OpenAPI schema), authentication details, rate limits, and independent developer corroboration of building against the API.

   • [claimed-docs] “The Poke API allows you to send messages programmatically from your applications, scripts, and automation tools.”
   • [claimed-docs] “Services like GitHub, CI/CD pipelines, or monitoring tools can trigger Poke when something happens.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://poke.com/openapi.json, https://poke.com/swagger.json, https://poke.com/api/openapi.json, htt…”

   proof ↗⚑ flag

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

   weight 2 · round to ChatGPT
   ChatGPT~partialclaimed4/10

   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

   Poke—none0/10

   Evidence shows Poke supports API access, integrations, and MCP servers, but there's no mention of scoped or least-privilege API credential/key issuance for agents — no API key management, permission scoping, or token-based access control documentation. The prompt-injection incident (poke-comm-1) raises security concerns but is unrelated to credential scoping specifically.

   ⚑ flag

7. ai-native userBuild against official SDKs

   weight 2 · round to Poke
   ChatGPT~partialprobed3/10

   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

   Poke~partialprobed4/10

   Poke exposes a documented API for sending messages programmatically and an official CLI (`npx poke@latest`) for managing MCP servers and recipes, which developers can build against, but there is no evidence of dedicated official SDK packages (e.g., Python/JS client libraries) — probes for OpenAPI/swagger specs and docs.md all returned 404, suggesting no formal SDK artifacts beyond the CLI/API docs. missing for 10: language-specific SDK packages, published OpenAPI/schema spec, independent developer corroboration of SDK usage.

   • [claimed-docs] “The Poke API allows you to send messages programmatically from your applications, scripts, and automation tools.”
   • [claimed-docs] “Services like GitHub, CI/CD pipelines, or monitoring tools can trigger Poke when something happens.”
   • [claimed-docs] “npx poke@latest login”
   • [claimed-docs] “npx poke@latest mcp add https://mcp.example.com/sse -n "My Server"”
   • [probe] “PROBE docs-md: HTTP 404 at https://poke.com/docs.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://poke.com/openapi.json, https://poke.com/swagger.json, https://poke.com/api/openapi.json, htt…”

   proof ↗⚑ flag

8. ai-native userSubscribe to events via webhooks

   weight 2 · round drawn
   ChatGPT~partialclaimed4/10

   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

   Poke~partialclaimed4/10

   Poke's API docs mention that external services like GitHub, CI/CD, or monitoring tools can trigger Poke via webhook-style calls, and the API can send messages programmatically, showing some webhook-adjacent integration. However, there's no explicit documentation of Poke exposing an outbound webhook subscription system for AI-native users to subscribe to Poke's own events. missing for 10: explicit outbound webhook/event subscription API, event types list, subscription management docs, independent confirmation of webhook reliability.

   • [claimed-docs] “The Poke API allows you to send messages programmatically from your applications, scripts, and automation tools.”
   • [claimed-docs] “Services like GitHub, CI/CD pipelines, or monitoring tools can trigger Poke when something happens.”

   proof ↗⚑ flag

Agentic features

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

   weight 2 · round to ChatGPT
   ChatGPT✓fullclaimed8/10

   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

   Poke~partialclaimed4/10

   Poke can extract and visualize data from shared images/spreadsheets into tables and charts, and integrations let it access and act on connected app data conversationally, which implies some data-driven insight generation. However, there's no explicit documentation of proactive AI-generated insights, trend analysis, or suggestions surfaced from a user's own accumulated data/history. missing for 10: dedicated insights/suggestions feature documentation, evidence of proactive analysis of user data patterns, independent/hands-on confirmation of this capability.

   • [claimed-docs] “Poke can now create tables and charts to help you visualize data. Describe what you want to see, or share images of existing data (like spre…”
   • [claimed-docs] “Integrations let you connect your favorite apps and services to Poke. Once connected, Poke can access information and perform actions across…”
   • [claimed-docs] “Once connected, Poke can access information and perform actions across apps and services through natural conversation.”

   proof ↗⚑ flag

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

   weight 2 · round to ChatGPT
   ChatGPT✓fullclaimed8/10

   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

   Poke~partialprobed5/10

   Poke's docs show building blocks for automation—an API that external tools (CI/CD, monitoring) can call to trigger Poke, and a 'recipes' system that can be created and published—plus positioning as a 'proactive AI assistant.' However there is no explicit documentation of scheduled/autonomous background jobs running without an external trigger or user prompt. missing for 10: documented scheduling/cron-like triggers, evidence of recipes running unattended in the background, independent confirmation of autonomous execution.

   • [claimed-docs] “The Poke API allows you to send messages programmatically from your applications, scripts, and automation tools.”
   • [claimed-docs] “Services like GitHub, CI/CD pipelines, or monitoring tools can trigger Poke when something happens.”
   • [claimed-docs] “npx poke@latest login”
   • [claimed-docs] “Publishing a recipe: marks it Published, generates a referral/share link, makes it eligible for payouts”
   • [probe] “PROBE llms.txt: HTTP 200 at https://poke.com/llms.txt # Poke > Poke is the proactive AI assistant on Apple Messages, WhatsApp, Telegram, an…”

   proof ↗⚑ flag

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

   weight 3 · round to ChatGPT
   ChatGPT✓fullclaimed9/10

   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

   Poke✓fullprobed8/10

   Poke IS the built-in AI assistant itself — users delegate tasks via natural conversation, integrations, MCP tools, and even real-human task execution (reservations, calls, deploying websites), all documented in first-party docs. Missing for 10: independent hands-on validation of task delegation beyond the security prompt-injection incident, which is off-topic here.

   • [claimed-docs] “Integrations let you connect your favorite apps and services to Poke. Once connected, Poke can access information and perform actions across…”
   • [claimed-docs] “Once connected, Poke can access information and perform actions across apps and services through natural conversation.”
   • [claimed-docs] “Poke can now bring in real people to take on tasks with a human touch - restaurant reservations, phone calls, placing orders, booking rides,…”
   • [claimed-docs] “Poke can also create and deploy websites for you at yourname.poke.com.”
   • [claimed-docs] “Poke supports Model Context Protocol (MCP) servers, allowing you to extend Poke with custom tools and data sources.”
   • [probe] “PROBE llms.txt: HTTP 200 at https://poke.com/llms.txt # Poke > Poke is the proactive AI assistant on Apple Messages, WhatsApp, Telegram, an…”

   proof ↗⚑ flag

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

   weight 2 · round to ChatGPT
   ChatGPT✓fullcommunity9/10

   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

   Poke✓fullprobed8/10

   Poke's entire interface is natural-language texting across WhatsApp/Apple Messages/Telegram, and its docs explicitly state integrations let it 'access information and perform actions across apps and services through natural conversation' (poke-docs-7/19), corroborated by the llms.txt description of Poke texting like a human (poke-probe-1). Missing for 10: independent hands-on user reviews confirming natural-language command reliability beyond vendor docs, and no detail on limits/edge cases of NL command parsing.

   • [claimed-docs] “Integrations let you connect your favorite apps and services to Poke. Once connected, Poke can access information and perform actions across…”
   • [claimed-docs] “Once connected, Poke can access information and perform actions across apps and services through natural conversation.”
   • [probe] “PROBE llms.txt: HTTP 200 at https://poke.com/llms.txt # Poke > Poke is the proactive AI assistant on Apple Messages, WhatsApp, Telegram, an…”
   • [claimed-docs] “Poke can now bring in real people to take on tasks with a human touch - restaurant reservations, phone calls, placing orders, booking rides,…”
   • [claimed-docs] “Poke can now create tables and charts to help you visualize data. Describe what you want to see, or share images of existing data (like spre…”

   proof ↗⚑ flag

Api quality

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

   weight 2 · round drawn
   ChatGPT—none0/10

   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

   Poke—none0/10

   No evidence of an interactive API reference or runnable examples; probes for OpenAPI/Swagger specs and docs.md all returned 404, and only basic prose docs about the messaging API exist.

   • [probe] “PROBE docs-md: HTTP 404 at https://poke.com/docs.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://poke.com/openapi.json, https://poke.com/swagger.json, https://poke.com/api/openapi.json, htt…”
   • [claimed-docs] “The Poke API allows you to send messages programmatically from your applications, scripts, and automation tools.”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   ChatGPT—none0/10

   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

   Poke—none0/10

   Direct probes for OpenAPI/swagger spec files all returned 404, and no documentation references a downloadable machine-readable API spec; only an llms.txt file exists, which is not an API spec.

   • [probe] “PROBE docs-md: HTTP 404 at https://poke.com/docs.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://poke.com/openapi.json, https://poke.com/swagger.json, https://poke.com/api/openapi.json, htt…”
   • [probe] “PROBE llms.txt: HTTP 200 at https://poke.com/llms.txt # Poke > Poke is the proactive AI assistant on Apple Messages, WhatsApp, Telegram, an…”

   proof ↗⚑ flag

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

   weight 1 · round to ChatGPT
   ChatGPT~partialclaimed4/10

   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

   Poke—none0/10

   No evidence pack mentions any sandbox environment, test/staging mode, or way to isolate testing from production data; Poke's docs focus on integrations, MCP servers, and messaging features with no mention of sandboxing.

   ⚑ flag

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

   weight 2 · round drawn
   ChatGPT—none0/10

   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

   Poke—none0/10

   There is no evidence of API versioning scheme, changelog for breaking changes, or a documented deprecation policy; probes show no OpenAPI spec available (404s), and docs only describe basic API usage without versioning or deprecation commitments.

   • [claimed-docs] “The Poke API allows you to send messages programmatically from your applications, scripts, and automation tools.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://poke.com/openapi.json, https://poke.com/swagger.json, https://poke.com/api/openapi.json, htt…”
   • [probe] “PROBE docs-md: HTTP 404 at https://poke.com/docs.md”

   proof ↗⚑ flag

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
   ChatGPT✓fullclaimed8/10

   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

   Poke~partialprobed5/10

   Poke's docs show it can be triggered by external events (GitHub, CI/CD) and can even delegate real-world tasks to humans (reservations, calls) and act across integrated apps 'through natural conversation,' plus the llms.txt describes it as a 'proactive AI assistant.' However, there is no explicit documentation of a structured multi-step task queue, autonomous background execution status, or a dedicated review/approval step for complex delegated tasks. Missing for 10: explicit multi-step task orchestration docs, background task status/progress tracking, and a defined 'review results' UX beyond ad-hoc chat replies.

   • [claimed-docs] “Services like GitHub, CI/CD pipelines, or monitoring tools can trigger Poke when something happens.”
   • [claimed-docs] “Integrations let you connect your favorite apps and services to Poke. Once connected, Poke can access information and perform actions across…”
   • [claimed-docs] “Poke can now bring in real people to take on tasks with a human touch - restaurant reservations, phone calls, placing orders, booking rides,…”
   • [probe] “PROBE llms.txt: HTTP 200 at https://poke.com/llms.txt # Poke > Poke is the proactive AI assistant on Apple Messages, WhatsApp, Telegram, an…”

   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
   ChatGPT✓fullclaimed8/10

   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

   Poke—none0/10

   Poke's docs describe integrations, MCP tool connections, and even outsourcing tasks to humans, but there is no evidence Poke itself drives a web browser to navigate sites or complete web-based research/tasks autonomously. missing for 10: any mention of browser automation, web navigation, or headless browsing capability.

   • [claimed-docs] “Integrations let you connect your favorite apps and services to Poke. Once connected, Poke can access information and perform actions across…”
   • [claimed-docs] “Poke can now bring in real people to take on tasks with a human touch - restaurant reservations, phone calls, placing orders, booking rides,…”
   • [claimed-docs] “Once connected, Poke can access information and perform actions across apps and services through natural conversation.”

   proof ↗⚑ flag

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

   weight 2 · round to ChatGPT
   ChatGPT✓fullclaimed9/10

   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

   Poke—none0/10

   Poke's evidence shows it connects to cloud services/integrations and MCP tool servers (poke-docs-7, poke-docs-19, poke-docs-3) but there is no evidence of it seeing a user's screen or directly operating local desktop applications — its automation is limited to API/webhook-based integrations and remote 'recipes,' not computer-use style control of a user's machine.

   • [claimed-docs] “Integrations let you connect your favorite apps and services to Poke. Once connected, Poke can access information and perform actions across…”
   • [claimed-docs] “Once connected, Poke can access information and perform actions across apps and services through natural conversation.”
   • [claimed-docs] “Poke supports Model Context Protocol (MCP) servers, allowing you to extend Poke with custom tools and data sources.”

   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
   ChatGPT✓fullclaimed8/10

   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

   Poke—none0/10

   The evidence pack shows Poke's API/integrations for triggering messages from external events (CI/CD, monitoring) and MCP tool extensions, but nothing documents a user-facing scheduler for recurring or one-off tasks that return results later. Missing for 10: any explicit scheduling/reminder feature, recurrence configuration, or hands-on proof of a task running and reporting back autonomously.

   • [claimed-docs] “The Poke API allows you to send messages programmatically from your applications, scripts, and automation tools.”
   • [claimed-docs] “Services like GitHub, CI/CD pipelines, or monitoring tools can trigger Poke when something happens.”
   • [claimed-docs] “Integrations let you connect your favorite apps and services to Poke. Once connected, Poke can access information and perform actions across…”

   proof ↗⚑ flag

Apps

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

   weight 2 · round to ChatGPT
   ChatGPT✓fullclaimed7/10

   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

   Poke—none0/10

   Evidence shows Poke operates through existing messaging channels (Apple Messages, WhatsApp, Telegram) rather than shipping its own official iOS/Android app; no documentation or probe evidence mentions a dedicated Poke mobile app.

   • [claimed-docs] “Poke is now available on Apple Messages as the first and only AI product to be verified on the platform.”
   • [claimed-docs] “Poke now works with Telegram as an alternative to WhatsApp while it is temporarily unavailable (except in Italy and Brazil).”
   • [probe] “PROBE llms.txt: HTTP 200 at https://poke.com/llms.txt # Poke > Poke is the proactive AI assistant on Apple Messages, WhatsApp, Telegram, an…”

   proof ↗⚑ flag

Custom bots

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

   weight 2 · round drawn
   ChatGPT~partialclaimed5/10

   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

   Poke~partialclaimed5/10

   Poke supports 'recipes' that can be created, published, shared via referral link, and monetized, plus MCP servers/integrations that extend its knowledge and behavior — this maps loosely to custom assistants with instructions/knowledge. However, there's no explicit documentation of defining a persistent 'assistant persona' with custom instructions in the way tools like GPTs allow; recipes appear more tool/automation-centric than persona-centric. missing for 10: explicit support for custom system-prompt/persona instructions per assistant, evidence of knowledge-base attachment beyond MCP tool integration, independent user validation of sharing custom assistants.

   • [claimed-docs] “you earn revenue from MCP usage by users who install your recipe”
   • [claimed-docs] “npx poke@latest login”
   • [claimed-docs] “Publishing a recipe: marks it Published, generates a referral/share link, makes it eligible for payouts”
   • [claimed-docs] “Go to poke.com/recipes to browse all first-party and approved third-party recipes.”
   • [claimed-docs] “Poke supports Model Context Protocol (MCP) servers, allowing you to extend Poke with custom tools and data sources.”
   • [claimed-docs] “Integrations let you connect your favorite apps and services to Poke. Once connected, Poke can access information and perform actions across…”

   proof ↗⚑ flag

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

   weight 2 · round to ChatGPT
   ChatGPT~partialclaimed6/10

   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

   Poke—none0/10

   Evidence shows Poke can message, integrate apps, and run recipes/MCP tools, but nothing describes performing bulk operations across many items at once (e.g., batch processing, multi-item automation loops); this remains unevidenced.

   ⚑ flag

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

   weight 3 · round to ChatGPT
   ChatGPT✓fullclaimed7/10

   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

   Poke~partialclaimed5/10

   Poke supports external triggers via its API (services like GitHub/CI/CD can trigger Poke) and integrations that let it act across apps, which enables event-driven automation, but there's no documented user-facing rules engine (e.g., 'if X happens, do Y' conditional automation builder) — triggers rely on third-party services calling the API rather than Poke itself defining declarative rules. missing for 10: a native rule/condition definition UI or DSL, evidence of multi-step conditional logic, and independent confirmation of reliability of triggered automations.

   • [claimed-docs] “The Poke API allows you to send messages programmatically from your applications, scripts, and automation tools.”
   • [claimed-docs] “Services like GitHub, CI/CD pipelines, or monitoring tools can trigger Poke when something happens.”
   • [claimed-docs] “Integrations let you connect your favorite apps and services to Poke. Once connected, Poke can access information and perform actions across…”
   • [claimed-docs] “Once connected, Poke can access information and perform actions across apps and services through natural conversation.”

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round to ChatGPT
   ChatGPT✓fullclaimed8/10

   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

   Poke—none0/10

   No evidence describes a scheduling or recurring-job/workflow feature; docs cover API messaging, integrations, MCP servers, and recipes but nothing about setting up recurring or time-based automations. The 'proactive assistant' description in the probe snippet is too vague to confirm recurring job scheduling. missing for 10: any documentation of cron-like scheduling, recurring triggers, or persistent workflow automation.

   • [claimed-docs] “The Poke API allows you to send messages programmatically from your applications, scripts, and automation tools.”
   • [claimed-docs] “Services like GitHub, CI/CD pipelines, or monitoring tools can trigger Poke when something happens.”
   • [probe] “PROBE llms.txt: HTTP 200 at https://poke.com/llms.txt # Poke > Poke is the proactive AI assistant on Apple Messages, WhatsApp, Telegram, an…”

   proof ↗⚑ flag

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

   weight 1 · round to ChatGPT
   ChatGPT~partialclaimed4/10

   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

   Poke—none0/10

   No evidence describes versioning, review workflows, or rollback capability for Poke's automations/recipes; docs mention creating, publishing, and monetizing recipes but nothing about version history or reverting changes.

   ⚑ flag

Connectors

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

   weight 2 · round drawn
   ChatGPT✓fullclaimed7/10

   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

   Poke✓fullclaimed7/10

   Poke docs describe poke.com/recipes as a directory of first-party and approved third-party recipes/integrations that users can browse and add, plus a separate Integrations page for connecting apps/services. This matches the power-user story of browsing and adding connectors. missing for 10: independent/hands-on evidence of the directory's breadth or UX, and no confirmation of search/filtering or ratings within the directory.

   • [claimed-docs] “Go to poke.com/recipes to browse all first-party and approved third-party recipes.”
   • [claimed-docs] “Integrations let you connect your favorite apps and services to Poke. Once connected, Poke can access information and perform actions across…”
   • [claimed-docs] “Once connected, Poke can access information and perform actions across apps and services through natural conversation.”
   • [claimed-docs] “Webflow - Design and deploy websites visually”
   • [claimed-docs] “Poke supports Model Context Protocol (MCP) servers, allowing you to extend Poke with custom tools and data sources.”

   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 ChatGPT
   ChatGPT~partialclaimed6/10

   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

   Poke~partialclaimed3/10

   Poke's docs describe a general 'Integrations' system that lets users connect apps/services (with Webflow given as the only named example) and mention an email-address feature, but no evidence names concrete cloud-drive (e.g., Google Drive), email (Gmail/Outlook), or calendar connectors, nor demonstrates search/use of such data in answers. Missing for 10: named cloud-drive integration, named email inbox integration, named calendar integration, and evidence of search/retrieval across them.

   • [claimed-docs] “Integrations let you connect your favorite apps and services to Poke. Once connected, Poke can access information and perform actions across…”
   • [claimed-docs] “Once connected, Poke can access information and perform actions across apps and services through natural conversation.”
   • [claimed-docs] “Webflow - Design and deploy websites visually”
   • [claimed-docs] “You can now set up a @poke.com address to use with your primary email account in Poke.”

   proof ↗⚑ flag

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
   ChatGPT✓fullcommunity8/10

   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

   Poke~partialclaimed4/10

   Poke's docs show it can create tables and charts from described data or shared images (poke-docs-21), but there's no evidence of an underlying code-execution environment, computed numeric answers, or generation of downloadable files. missing for 10: evidence of actual code execution/sandbox, computed-answer capability, downloadable file output.

   • [claimed-docs] “Poke can now create tables and charts to help you visualize data. Describe what you want to see, or share images of existing data (like spre…”

   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
   ChatGPT✓fullclaimed9/10

   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

   Poke—none0/10

   Evidence shows Poke can create websites and generate tables/charts from data, but there is no evidence of creating or iteratively editing documents/presentations that can be exported (e.g. Word, PDF, PowerPoint files). Missing for 10: document creation/editing evidence, presentation creation, export functionality for standard file formats.

   • [claimed-docs] “Poke can also create and deploy websites for you at yourname.poke.com.”
   • [claimed-docs] “Poke can now create tables and charts to help you visualize data. Describe what you want to see, or share images of existing data (like spre…”

   proof ↗⚑ flag

Files

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

   weight 3 · round to ChatGPT
   ChatGPT✓fullclaimed7/10

   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

   Poke~partialclaimed3/10

   The only relevant evidence is that Poke can 'extract and visualize' data from shared images of spreadsheets to create tables/charts, which is a narrow slice of the story. There is no documentation of direct document or PDF upload, parsing, or accurate content analysis for knowledge-worker use cases. Missing for 10: explicit PDF/document upload support, evidence of accuracy on structured/text-heavy files, and any hands-on validation of analysis quality.

   • [claimed-docs] “Poke can now create tables and charts to help you visualize data. Describe what you want to see, or share images of existing data (like spre…”

   proof ↗⚑ flag

Memory

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

   weight 3 · round to ChatGPT
   ChatGPT✓fullclaimed8/10

   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

   Poke~partialclaimed5/10

   Docs mention Poke's Memory as a concept tied to account merging (poke-docs-20), implying persistent memory exists across the assistant, but there's no detailed documentation of how memory is captured, retained, or applied across separate conversations, nor independent confirmation of its effectiveness. Missing for 10: dedicated memory documentation explaining retention/retrieval mechanics, examples of cross-chat context recall, and independent/hands-on verification that it works reliably.

   • [claimed-docs] “This keeps Poke's Memory, Recipes, and Integrations from the selected account, and your messaging channels ... will be connected to it.”

   proof ↗⚑ flag

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

   weight 1 · round to ChatGPT
   ChatGPT✓fullclaimed8/10

   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

   Poke~partialclaimed3/10

   The docs mention a 'Memory' feature tied to a user's account (carried over when merging accounts), implying some persistent context storage, but there is no documentation of a dedicated custom-instructions/preferences setting that explicitly shapes every response. Missing for 10: explicit UI/API for setting persistent custom instructions, examples of how such preferences influence responses, and independent confirmation of this behavior.

   • [claimed-docs] “This keeps Poke's Memory, Recipes, and Integrations from the selected account, and your messaging channels ... will be connected to it.”

   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
   ChatGPT✓fullclaimed8/10

   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

   Poke—none0/10

   Poke's docs describe messaging, integrations, MCP servers, and recipes, but there is no mention of organizing chats/files into projects or spaces with shared context/instructions, which is a distinct memory-organization feature not evidenced here.

   ⚑ flag

Images

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

   weight 2 · round to ChatGPT
   ChatGPT✓fullclaimed9/10

   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

   Poke—none0/10

   Evidence shows Poke can create tables/charts from data and extract data from images (poke-docs-21), and can create websites, but there is no mention of generating or editing images from natural-language prompts anywhere in the docs or release notes.

   ⚑ flag

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

   weight 2 · round to ChatGPT
   ChatGPT✓fullclaimed7/10

   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

   Poke~partialclaimed5/10

   Poke's release notes explicitly state it can 'share images of existing data (like spreadsheets) for Poke to extract and visualize,' showing some image-interpretation capability, but this is limited to structured data extraction rather than general photo/screenshot understanding across varied content. Missing for 10: evidence of accurate interpretation of arbitrary photos/screenshots (e.g., UI screenshots, handwritten notes, general scenes), independent hands-on verification of accuracy, and any first-party documentation describing general vision/OCR capability beyond the spreadsheet example.

   • [claimed-docs] “Poke can now create tables and charts to help you visualize data. Describe what you want to see, or share images of existing data (like spre…”

   proof ↗⚑ flag

Voice

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

   weight 2 · round to ChatGPT
   ChatGPT✓fullclaimed8/10

   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

   Poke—none0/10

   Poke is described as a text-based assistant across messaging platforms (WhatsApp, Telegram, Apple Messages) with no evidence of real-time voice call or voice conversation capability; all documented interactions are text/message-based.

   ⚑ flag

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

   weight 2 · round to Poke
   ChatGPT~partialprobed3/10

   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

   Poke~partialprobed4/10

   Poke exposes a documented API for sending messages programmatically and triggering it from external systems (poke-docs-1, poke-docs-2), plus an MCP server/tunnel mechanism for extending tools (poke-docs-3/4/16). However, there's no evidence of API parity for major UI capabilities like managing integrations, recipes, human-task requests, website deployment, or memory/account management, and no public OpenAPI/spec was found (poke-probe-2, poke-probe-3 both 404). missing for 10: API coverage for integrations/recipes/human-tasks/website-deploy features, published OpenAPI spec, independent confirmation of API-UI parity.

   • [claimed-docs] “The Poke API allows you to send messages programmatically from your applications, scripts, and automation tools.”
   • [claimed-docs] “Services like GitHub, CI/CD pipelines, or monitoring tools can trigger Poke when something happens.”
   • [claimed-docs] “Poke supports Model Context Protocol (MCP) servers, allowing you to extend Poke with custom tools and data sources.”
   • [claimed-docs] “npx poke@latest tunnel http://localhost:3000/mcp -n "Local Dev MCP"”
   • [claimed-docs] “npx poke@latest mcp add https://mcp.example.com/sse -n "My Server"”
   • [probe] “PROBE docs-md: HTTP 404 at https://poke.com/docs.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://poke.com/openapi.json, https://poke.com/swagger.json, https://poke.com/api/openapi.json, htt…”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   ChatGPT—none0/10

   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

   Poke—none0/10

   No evidence of any data export feature or open-format data portability in Poke's docs; the pack covers messaging API, MCP servers, integrations, and account merging but nothing about exporting user data (memory, conversation history, recipes) in open formats or account closure/data takeout.

   ⚑ flag

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

   weight 2 · round drawn
   ChatGPT—none0/10

   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

   Poke—none0/10

   No evidence anywhere in the pack mentions data residency, region selection, or storage location controls; Poke's docs cover integrations, MCP, messaging channels, and pricing but nothing about where user data is stored or any regional choice.

   ⚑ flag

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

   weight 3 · round drawn
   ChatGPT—none0/10

   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

   Poke—none0/10

   No evidence in the pack addresses data-training opt-out or privacy controls regarding AI model training; the docs focus on messaging, integrations, MCP, and recipes with no mention of data usage policies or opt-out settings.

   ⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round to ChatGPT
   ChatGPT~partialclaimed3/10

   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

   Poke—none0/10

   No evidence pack item addresses data retention policies, deletion controls, or export/delete-my-data mechanisms; docs cover memory merging and integrations but not retention/deletion controls, and the prompt-injection report is unrelated to this axis.

   ⚑ flag

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

   weight 2 · round drawn
   ChatGPT—none0/10

   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

   Poke—none0/10

   No evidence pack item discusses telemetry, analytics opt-out, or usage-tracking controls for Poke users; docs cover API, MCP, integrations, pricing, and release notes but never privacy/telemetry settings.

   ⚑ flag

Research

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

   weight 3 · round to ChatGPT
   ChatGPT~partialclaimed6/10

   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

   Poke—none0/10

   Poke's evidence pack covers messaging integrations, MCP tool extensibility, recipes, and various assistant features, but nothing describes an autonomous multi-source deep research capability that returns a cited report. No mention of web search breadth, citation generation, or research-report output.

   ⚑ flag

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

   weight 2 · round to ChatGPT
   ChatGPT✓fullcommunity8/10

   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

   Poke—none0/10

   No evidence describes Poke performing web search, retrieval-augmented answers, or providing citations back to sources; docs focus on messaging, integrations, MCP tooling, and account features, not grounded research answers.

   ⚑ flag

Data controls

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

   weight 1 · round drawn
   ChatGPT—none0/10

   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

   Poke—none0/10

   No evidence in the pack mentions any data export, chat history download, or account data portability feature; documentation covers integrations, MCP, recipes, and messaging channels but nothing about exporting user data.

   ⚑ flag

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

   weight 3 · round drawn
   ChatGPT—none0/10

   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

   Poke—none0/10

   No evidence pack item addresses model-training data usage or opt-out controls for conversation data; documentation covers integrations, MCP, pricing, and release notes but nothing about training data policy. Missing for 10: any privacy/data-training policy page, opt-out toggle, or enterprise data-use agreement.

   ⚑ flag