Skip to content
ProductArena

AI Assistants Arena

Gemini vs Poke

Gemini logo

Gemini

Google

Arena17/100AGENT-READY9/100BUILT-IN AI70/100
MCP—CLI~API~
free-tier6/100 integrity
Poke logo

Poke

Cognition (The Interaction Company)

Arena24/100AGENT-READY42/100BUILT-IN AI56/100
MCP✓CLI~API~
free-tier40/100 integrity

Gemini wins · 24–12 (7 drawn)

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 Poke
    Gemininone0/10

    No evidence that Gemini can be pointed at llms.txt or agent-oriented documentation formats; the evidence only covers uploading files, GitHub repos, and connecting to apps, none of which address consuming llms.txt or agent-facing docs conventions. Missing for 10: any mention of llms.txt support, agent-oriented doc parsing, or a documented workflow for feeding agent-discovery docs to Gemini.

      ⚑ flag
      Pokefullprobed8/10

      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

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

      weight 2 · round to Poke
      Gemininone0/10

      The evidence pack is dominated by consumer-facing Gemini Apps documentation (chat, image generation, Gemini Live, notebooks) and contains no first-party documentation of a headless mode, CI integration, or automation-friendly API/CLI usage. The only hint of a CLI tool appears in community complaints (gemini-comm-14, gemini-comm-15) about login failures for Workspace accounts trying to use 'Gemini CLI' for software development, which does not establish that headless/CI automation works.

      • [community] “I love how fragmented Google's Gemini offerings are. I'm a Pro subscriber, but I now learn I should be a 'Gemini Code Assist Standard or Ent…”
      • [community] “'Failed to login. Ensure your Google account is not a Workspace account.' ... now as a Workspace account I cant use Gemini CLI for my work, …”
      proof ↗⚑ flag
      Pokepartialprobed6/10

      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

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

      weight 3 · round to Poke
      Gemininone0/10

      Evidence covers Gemini Apps' 'Connected Apps' feature (Gmail, Calendar, Maps, Flights) and coding-related uploads (GitHub repos, folders), but nothing describes plugging in Model Context Protocol (MCP) servers as a tool-connection mechanism. Missing for 10: any documentation or mention of MCP server support, MCP client configuration, or third-party tool registration via MCP standard.

      • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses. With your permission, Gemini can also he…”
      • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses.”
      • [claimed-docs] “With your permission, Gemini can also help you take actions, like editing and managing your content in other apps.”
      • [claimed-docs] “Boost productivity: Summarize emails from Gmail, create events in Google Calendar or third-party apps, or search for content across a variet…”
      • [claimed-docs] “Get started with Connected Apps in Gemini **Important:** For now, Gemini can’t use Connected Apps in Gemini in Google Messages.”
      proof ↗⚑ flag
      Pokefullprobed8/10

      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

    • ai-native userUse an official CLI

      weight 2 · round to Poke
      Geminipartialcommunity4/10

      Community discussion confirms the existence of an official 'Gemini CLI' used for software development (comm-13, comm-14), but there is no first-party documentation of it in the evidence pack, and a hands-on report shows it fails to work for Workspace accounts ('Failed to login... now as a Workspace account I cant use Gemini CLI for my work') (comm-15). Missing for 10: official CLI documentation/spec, installation and usage guides, and evidence that login/account restrictions have been resolved.

      • [community] “I have been using this for about a month and it's a beast, mostly thanks to 2.5pro being SOTA and also how it leverages that huge 1M context…”
      • [community] “I love how fragmented Google's Gemini offerings are. I'm a Pro subscriber, but I now learn I should be a 'Gemini Code Assist Standard or Ent…”
      • [community] “'Failed to login. Ensure your Google account is not a Workspace account.' ... now as a Workspace account I cant use Gemini CLI for my work, …”
      proof ↗⚑ flag
      Pokepartialclaimed6/10

      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

    • ai-native userDrive the product through a documented public API

      weight 3 · round to Poke
      Geminipartialcommunity5/10

      Community evidence confirms a public Gemini API exists and is actively used by developers (pricing tiers, model versions, Google AI Studio parameters like temperature and top_k), but the evidence pack contains no first-party API reference documentation, and one community report notes undocumented/hidden parameter behavior (fixed top_k, capped temperature) that limits full programmatic control. missing for 10: first-party API reference/docs citation, SDK/auth documentation, confirmation that documented parameters match actual behavior.

      • [community] “API pricing is up to $2/M for input and $12/M for output. For comparison: Gemini 2.5 Pro was $1.25/M for input and $10/M for output, Gemini …”
      • [community] “I'm sure this is a very impressive model, but gemini-3-pro-preview is failing spectacularly at my fairly basic python benchmark. In fact, ge…”
      • [community] “My favorite benchmark is to analyze a very long audio file recording of a management meeting and produce very good notes along with a transc…”
      • [community] “Temperature continues to be gated to maximum of 0.2, and there's still the hidden top_k of 64 that you can't turn off. I love the google AI …”
      • [community] “It still failed my image identification test (a photoshopped picture of a dog with 5 legs)... Gemini 3 however, while still failing, at leas…”
      proof ↗⚑ flag
      Pokepartialprobed6/10

      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

    • ai-native userBuild against official SDKs

      weight 2 · round to Poke
      Gemininone0/10

      The evidence pack only covers Gemini's consumer-facing app features (uploads, Gemini Live, Gems, connected apps) and does not document any official SDKs for building applications (e.g., Python/Node/Go SDKs for the Gemini API). Community mentions reference API pricing and a 'Gemini CLI' having login issues, but no concrete SDK documentation or hands-on developer usage evidence is present.

      • [community] “API pricing is up to $2/M for input and $12/M for output. For comparison: Gemini 2.5 Pro was $1.25/M for input and $10/M for output, Gemini …”
      • [community] “'Failed to login. Ensure your Google account is not a Workspace account.' ... now as a Workspace account I cant use Gemini CLI for my work, …”
      proof ↗⚑ flag
      Pokepartialprobed4/10

      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

    • ai-native userSubscribe to events via webhooks

      weight 2 · round to Poke
      Gemininone0/10

      No evidence in the pack describes Gemini offering a webhook subscription mechanism for events; the docs cover imports, connected apps, Gems, Live, Deep Research, etc., but nothing about outbound webhooks or event subscriptions for AI-native/agentic integration.

        ⚑ flag
        Pokepartialclaimed4/10

        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 Gemini
        Geminifullcommunity8/10

        Gemini's docs show robust support for generating insights from user data: uploading documents/spreadsheets/photos/videos for 'answers, summaries, and insights' (gemini-docs-25), Notebooks for organizing and querying sources (gemini-docs-11, gemini-docs-24, gemini-docs-29), Deep Research for in-depth analysis (gemini-docs-7), and Connected Apps that summarize Gmail and productivity data (gemini-docs-30). Independent hands-on reports corroborate real usage: navigating large codebases effortlessly (gemini-comm-13), replacing an OCR vendor for document ingestion with strong accuracy (gemini-comm-17), and NotebookLM being 'really powerful for comprehending large corpuses' (gemini-comm-19), though one report notes weaker accuracy on visual bounding-box tasks (gemini-comm-18). missing for 10: broader independent benchmarking specifically on insight-generation quality across data types, and resolution of the noted accuracy gaps in some visual tasks.

        • [claimed-docs] “You can upload documents, spreadsheets, notebooks, photos, videos, and more to Gemini Apps to get answers, summaries, and insights about you…”
        • [claimed-docs] “Notebooks provide a continuous chat experience that remembers your sources, instructions, and ongoing discussions.”
        • [claimed-docs] “you can use notebooks to organize your projects in a dedicated, focused space.”
        • [claimed-docs] “You can conduct in-depth and real-time research on almost any subject with Deep Research in Gemini Apps.”
        • [claimed-docs] “You can change or add other sources, like your personal Gmail or Drive, for your research. You can also upload files and add NotebookLM note…”
        • [claimed-docs] “Boost productivity: Summarize emails from Gmail, create events in Google Calendar or third-party apps, or search for content across a variet…”
        • [community] “I have been using this for about a month and it's a beast, mostly thanks to 2.5pro being SOTA and also how it leverages that huge 1M context…”
        • [community] “I work in fintech and we replaced an OCR vendor with Gemini at work for ingesting some PDFs... Processing time went from something like 12 m…”
        • [community] “I've been using NotebookLM powered by Gemini 2.0 for three projects and it is really powerful for comprehending large corpuses you can't pos…”
        • [community] “Unfortunately Gemini really seems to struggle on this, and no matter how we tried prompting it, it would generate wildly inaccurate bounding…”
        proof ↗⚑ flag
        Pokepartialclaimed4/10

        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 Gemini
        Geminipartialclaimed6/10

        Google's docs explicitly describe scheduling recurring actions so Gemini becomes part of daily/weekly/monthly routines (gemini-docs-8), and the Daily Brief feature autonomously delivers a personalized digest without user prompting (gemini-docs-32/41), supported by action-taking integrations with other apps (gemini-docs-10/17/23/30). However, evidence is limited to first-party docs with no independent/hands-on confirmation of reliability, no detail on trigger conditions, failure handling, or scope of what 'recurring actions' can actually do autonomously. Missing for 10: independent verification that scheduled automations run reliably unattended, documentation on trigger/condition logic, and evidence of broader autonomous multi-step task execution beyond simple digests.

        • [claimed-docs] “You can make Gemini a part of your daily, weekly, and monthly routines by scheduling recurring actions.”
        • [claimed-docs] “Start your day with a personalized digest from Gemini. Your Daily Brief understands your rhythms and personal preferences to deliver your to…”
        • [claimed-docs] “Start your day with a personalized digest from Gemini. Your Daily Brief understands your rhythms and personal preferences to deliver your to…”
        • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses. With your permission, Gemini can also he…”
        • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses.”
        • [claimed-docs] “With your permission, Gemini can also help you take actions, like editing and managing your content in other apps.”
        • [claimed-docs] “Boost productivity: Summarize emails from Gmail, create events in Google Calendar or third-party apps, or search for content across a variet…”
        proof ↗⚑ flag
        Pokepartialprobed5/10

        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 drawn
        Geminifullcommunity8/10

        Gemini's docs show extensive task delegation: connected apps to take actions in Gmail/Calendar/Maps/Flights (gemini-docs-10, gemini-docs-23, gemini-docs-30), scheduled recurring actions (gemini-docs-8), custom Gems for specific goals (gemini-docs-9), Deep Research for autonomous multi-step research (gemini-docs-7), and Daily Brief proactive digests (gemini-docs-32, gemini-docs-41). Community evidence corroborates real-world delegated use cases like large codebase analysis and audio transcription (gemini-comm-13, gemini-comm-10). missing for 10: independent hands-on verification specifically of agentic task delegation/action-taking (vs. just Q&A), and evidence of reliability/success rate when Gemini executes multi-step delegated tasks.

        • [claimed-docs] “You can conduct in-depth and real-time research on almost any subject with Deep Research in Gemini Apps.”
        • [claimed-docs] “You can make Gemini a part of your daily, weekly, and monthly routines by scheduling recurring actions.”
        • [claimed-docs] “To create a custom Gem to meet your goals, provide info about your request and requirements.”
        • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses. With your permission, Gemini can also he…”
        • [claimed-docs] “With your permission, Gemini can also help you take actions, like editing and managing your content in other apps.”
        • [claimed-docs] “Boost productivity: Summarize emails from Gmail, create events in Google Calendar or third-party apps, or search for content across a variet…”
        • [claimed-docs] “Start your day with a personalized digest from Gemini. Your Daily Brief understands your rhythms and personal preferences to deliver your to…”
        • [community] “I have been using this for about a month and it's a beast, mostly thanks to 2.5pro being SOTA and also how it leverages that huge 1M context…”
        • [community] “My favorite benchmark is to analyze a very long audio file recording of a management meeting and produce very good notes along with a transc…”
        proof ↗⚑ flag
        Pokefullprobed8/10

        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 drawn
        Geminifullclaimed8/10

        Gemini is fundamentally operated via natural-language chat and voice (Gemini Live's free-flowing conversation, 'Hey Google' voice commands, text prompts for image generation, scheduling recurring actions, custom Gems, and connected-app actions) rather than rigid commands or GUIs, per extensive first-party docs. Missing for 10: independent/hands-on verification that complex natural-language action requests (e.g., connected-app task execution) reliably work as described, and community evidence is mixed on model quality/accuracy for specific tasks rather than confirming the NL interface itself.

        • [claimed-docs] “With Gemini Live, you can have a natural, free-flowing conversation with Gemini. You can even interrupt it like when you want to add more de…”
        • [claimed-docs] “With Gemini Live, you can have a natural, free-flowing conversation with Gemini.”
        • [claimed-docs] “With Gemini Live, you can: * **Talk back and forth:** Talk to Gemini without typing, and Gemini will respond back verbally.”
        • [claimed-docs] “you can have a natural, free-flowing conversation with Gemini. You can even interrupt it like when you want to add more details or change th…”
        • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses. With your permission, Gemini can also he…”
        • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses.”
        • [claimed-docs] “With your permission, Gemini can also help you take actions, like editing and managing your content in other apps.”
        • [claimed-docs] “You can make Gemini a part of your daily, weekly, and monthly routines by scheduling recurring actions.”
        • [claimed-docs] “To create a custom Gem to meet your goals, provide info about your request and requirements.”
        • [claimed-docs] “Boost productivity: Summarize emails from Gmail, create events in Google Calendar or third-party apps, or search for content across a variet…”
        • [claimed-docs] “On Android, say “Hey Google” to ask Gemini for help with what’s on your screen”
        proof ↗⚑ flag
        Pokefullprobed8/10

        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 userRely on versioned APIs with a documented deprecation policy

        weight 2 · round drawn
        Gemininone0/10

        The evidence pack is entirely consumer-focused Gemini Apps documentation (image generation, Gemini Live, connected apps, notebooks) and general community sentiment about model quality/pricing; there is no mention of API versioning, version lifecycle, or a documented deprecation policy anywhere in the pack.

          ⚑ flag
          Pokenone0/10

          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

        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 Gemini
          Geminipartialclaimed6/10

          Deep Research lets users delegate an open-ended research task that Gemini works on autonomously and returns a report for review, and scheduled/recurring actions show background task automation; Connected Apps/Gems add some autonomous action-taking on the user's behalf. However there's no clear evidence of a general-purpose multi-step 'agent mode' that plans and executes across arbitrary apps end-to-end with an explicit review/approval step, nor independent hands-on confirmation of this workflow. Missing for 10: evidence of a broad autonomous agent (beyond Deep Research/scheduling) handling arbitrary multi-step tasks across apps, and independent/community validation of such background task delegation working reliably.

          • [claimed-docs] “You can conduct in-depth and real-time research on almost any subject with Deep Research in Gemini Apps.”
          • [claimed-docs] “You can make Gemini a part of your daily, weekly, and monthly routines by scheduling recurring actions.”
          • [claimed-docs] “To create a custom Gem to meet your goals, provide info about your request and requirements.”
          • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses. With your permission, Gemini can also he…”
          • [claimed-docs] “With your permission, Gemini can also help you take actions, like editing and managing your content in other apps.”
          • [claimed-docs] “Boost productivity: Summarize emails from Gmail, create events in Google Calendar or third-party apps, or search for content across a variet…”
          proof ↗⚑ flag
          Pokepartialprobed5/10

          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 Gemini
          Geminipartialclaimed4/10

          Deep Research lets Gemini conduct 'in-depth and real-time research' across web sources, and Connected Apps let it take actions in other apps (Gmail, Calendar, Maps, Flights) with permission — showing some research/task-automation capability. However, there is no evidence of Gemini actually driving a web browser (navigating pages, clicking, filling forms) to complete tasks on arbitrary websites, only sanctioned first-party app integrations. Missing for 10: explicit browser-control/agentic navigation evidence, hands-on demonstration of completing a multi-step website task, independent corroboration of this capability.

          • [claimed-docs] “You can conduct in-depth and real-time research on almost any subject with Deep Research in Gemini Apps.”
          • [claimed-docs] “You can change or add other sources, like your personal Gmail or Drive, for your research. You can also upload files and add NotebookLM note…”
          • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses. With your permission, Gemini can also he…”
          • [claimed-docs] “With your permission, Gemini can also help you take actions, like editing and managing your content in other apps.”
          • [claimed-docs] “Boost productivity: Summarize emails from Gmail, create events in Google Calendar or third-party apps, or search for content across a variet…”
          proof ↗⚑ flag
          Pokenone0/10

          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 Gemini
          Geminipartialclaimed5/10

          Gemini's Connected Apps feature lets it take actions in other apps (Gmail, Calendar, Maps, Flights) with permission, and on Android it can see what's on-screen to help with context, but this is limited to a curated set of app integrations/APIs rather than general computer-use/desktop automation across arbitrary applications. Missing for 10: broader OS-level screen perception, ability to click/type across arbitrary desktop apps, and independent hands-on evidence of an agentic computer-use mode.

          • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses. With your permission, Gemini can also he…”
          • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses.”
          • [claimed-docs] “With your permission, Gemini can also help you take actions, like editing and managing your content in other apps.”
          • [claimed-docs] “Boost productivity: Summarize emails from Gmail, create events in Google Calendar or third-party apps, or search for content across a variet…”
          • [claimed-docs] “On Android, say “Hey Google” to ask Gemini for help with what’s on your screen”
          • [claimed-docs] “Get started with Connected Apps in Gemini **Important:** For now, Gemini can’t use Connected Apps in Gemini in Google Messages.”
          proof ↗⚑ flag
          Pokenone0/10

          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 Gemini
          Geminipartialclaimed6/10

          Gemini docs confirm scheduling recurring actions (gemini-docs-8) and Daily Brief personalized digest (gemini-docs-32/41), showing one-off/recurring automated tasks that return results. However, evidence lacks detail on task complexity, multi-step agent tasks, notification delivery mechanisms, or independent/community corroboration of this specific feature working reliably. missing for 10: detailed documentation on scheduling flexibility, agentic multi-step task execution, notification/result delivery mechanisms, and independent hands-on validation of the scheduled-tasks feature.

          • [claimed-docs] “You can make Gemini a part of your daily, weekly, and monthly routines by scheduling recurring actions.”
          • [claimed-docs] “Start your day with a personalized digest from Gemini. Your Daily Brief understands your rhythms and personal preferences to deliver your to…”
          • [claimed-docs] “Start your day with a personalized digest from Gemini. Your Daily Brief understands your rhythms and personal preferences to deliver your to…”
          proof ↗⚑ flag
          Pokenone0/10

          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 devices — stories about apps devices in this arenaApps devices

        Stories about apps devices in this arena

        Apps

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

          weight 2 · round to Gemini
          Geminipartialclaimed6/10

          Docs confirm a full-featured Gemini mobile app with rich functionality (Gemini Live voice conversations, screen-aware Android assistant via 'Hey Google', Maps/Flights integration, daily briefs, scheduling, image generation, coding help) showing strong Android support, and generic mobile-app language implies broader availability, but the evidence never explicitly names or details an iOS app or iOS-specific parity. missing for 10: explicit iOS app documentation/feature parity, App Store presence, and any cross-platform comparison confirming equal functionality on iOS vs Android.

          • [claimed-docs] “On Android, say “Hey Google” to ask Gemini for help with what’s on your screen”
          • [claimed-docs] “With Gemini Live, you can have a natural, free-flowing conversation with Gemini. You can even interrupt it like when you want to add more de…”
          • [claimed-docs] “Make plans with Google Maps and Google Flights”
          • [claimed-docs] “The Gemini app provides quick access to AI features, allowing you to get help with writing, brainstorming, coding, and more, without needing…”
          • [claimed-docs] “get help with writing, brainstorming, coding, and more, without needing to open a web browser.”
          • [claimed-docs] “Start your day with a personalized digest from Gemini. Your Daily Brief understands your rhythms and personal preferences to deliver your to…”
          • [claimed-docs] “If you have access to Gemini Apps with a work or school account, some Gemini mobile app features aren’t available.”
          • [claimed-docs] “Start your day with a personalized digest from Gemini. Your Daily Brief understands your rhythms and personal preferences to deliver your to…”
          proof ↗⚑ flag
          Pokenone0/10

          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 to Gemini
          Geminipartialclaimed6/10

          Gemini's "Gems" feature (gemini-docs-9) lets power-users create a custom Gem with its own instructions and requirements, and Gems can be given knowledge via uploaded files/sources (gemini-docs-25), directly matching the core of this story. However, evidence does not confirm a straightforward sharing/publishing mechanism for Gems to other users, nor independent hands-on validation of the feature's robustness. Missing for 10: documentation of sharing/publishing custom Gems with other users, evidence of knowledge-base scope/limits, and independent community corroboration of Gems in practice.

          • [claimed-docs] “To create a custom Gem to meet your goals, provide info about your request and requirements.”
          • [claimed-docs] “You can upload documents, spreadsheets, notebooks, photos, videos, and more to Gemini Apps to get answers, summaries, and insights about you…”
          proof ↗⚑ flag
          Pokepartialclaimed5/10

          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

        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 Gemini
          Geminipartialcommunity3/10

          Gemini supports uploading whole code folders/repos and large codebases (a form of bulk ingestion) and can take actions across connected apps or run scheduled recurring actions, but there is no explicit documentation of a bulk/batch operation feature (e.g., applying an action to many items at once like bulk-editing files, mass-tagging, or batch task execution) as an AI-native automation capability. missing for 10: explicit bulk-action/batch-processing feature, evidence of applying one instruction across many discrete items simultaneously, independent corroboration of this specific capability.

          • [claimed-docs] “To add a code folder: click More Uploads Import Code Upload folder.”
          • [claimed-docs] “To add a code folder: click More Uploads ... Import Code ... Upload folder.”
          • [claimed-docs] “You can make Gemini a part of your daily, weekly, and monthly routines by scheduling recurring actions.”
          • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses. With your permission, Gemini can also he…”
          • [community] “I have been using this for about a month and it's a beast, mostly thanks to 2.5pro being SOTA and also how it leverages that huge 1M context…”
          proof ↗⚑ flag
          Pokenone0/10

          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

          • ai-native userDefine rules that trigger actions automatically on events

            weight 3 · round to Poke
            Geminipartialclaimed4/10

            Gemini supports 'scheduling recurring actions' as part of daily/weekly/monthly routines (gemini-docs-8), which is a form of automation, but this is time-based scheduling rather than user-defined conditional rules that trigger on arbitrary events. Connected Apps let Gemini take actions in other apps (gemini-docs-10, gemini-docs-23, gemini-docs-30) but only in response to a direct user request, not an automatic event trigger. Missing for 10: evidence of event-based (not just time-based) trigger conditions, ability to define custom 'if X happens then do Y' rules, and any confirmation of conditional logic beyond fixed recurring schedules.

            • [claimed-docs] “You can make Gemini a part of your daily, weekly, and monthly routines by scheduling recurring actions.”
            • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses. With your permission, Gemini can also he…”
            • [claimed-docs] “With your permission, Gemini can also help you take actions, like editing and managing your content in other apps.”
            • [claimed-docs] “Boost productivity: Summarize emails from Gmail, create events in Google Calendar or third-party apps, or search for content across a variet…”
            proof ↗⚑ flag
            Pokepartialclaimed5/10

            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

          • ai-native userSchedule recurring jobs or workflows

            weight 2 · round to Gemini
            Geminipartialclaimed6/10

            Gemini docs explicitly confirm scheduling recurring actions ('daily, weekly, and monthly routines') via a dedicated feature (gemini-docs-8), and Daily Brief shows an example of a recurring automated digest (gemini-docs-32/41). However, evidence lacks detail on workflow complexity, chaining multiple steps/tools, error handling, or independent/community validation of this scheduling feature. missing for 10: detail on multi-step workflow scheduling, chaining across apps, reliability/error handling, and independent hands-on confirmation.

            • [claimed-docs] “You can make Gemini a part of your daily, weekly, and monthly routines by scheduling recurring actions.”
            • [claimed-docs] “Start your day with a personalized digest from Gemini. Your Daily Brief understands your rhythms and personal preferences to deliver your to…”
            • [claimed-docs] “Start your day with a personalized digest from Gemini. Your Daily Brief understands your rhythms and personal preferences to deliver your to…”
            proof ↗⚑ flag
            Pokenone0/10

            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

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

            weight 1 · round drawn
            Gemininone0/10

            No evidence of version control, review workflows, or rollback capabilities for automations (e.g., scheduled actions, Gems, or connected app actions). The evidence only covers scheduling recurring actions and connecting apps, with no mention of versioning, diffing, review approval, or rollback of automations.

              ⚑ flag
              Pokenone0/10

              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 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 Poke
                Geminipartialclaimed6/10

                Gemini docs describe a 'Connected Apps' feature that lets users link Gmail, Calendar, Maps, Flights and 'a variety of productivity apps' so Gemini can search/create content and take actions, which matches the connectors-directory concept ([gemini-docs-10],[gemini-docs-17],[gemini-docs-23],[gemini-docs-30],[gemini-docs-33],[gemini-docs-19]). However, the evidence never shows a browsable app-store-like directory UI, doesn't clarify how many third-party (non-Google) apps are included, and there's no independent/hands-on confirmation of the browse-and-add experience. Missing for 10: explicit directory/marketplace UI screenshots or docs, breadth of third-party (non-Google) app listings, independent user corroboration of adding connectors.

                • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses. With your permission, Gemini can also he…”
                • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses.”
                • [claimed-docs] “With your permission, Gemini can also help you take actions, like editing and managing your content in other apps.”
                • [claimed-docs] “Boost productivity: Summarize emails from Gmail, create events in Google Calendar or third-party apps, or search for content across a variet…”
                • [claimed-docs] “Get started with Connected Apps in Gemini **Important:** For now, Gemini can’t use Connected Apps in Gemini in Google Messages.”
                • [claimed-docs] “Make plans with Google Maps and Google Flights”
                proof ↗⚑ flag
                Pokefullclaimed7/10

                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 Gemini
                Geminifullclaimed8/10

                Google's docs describe first-party 'Connected Apps' letting Gemini summarize Gmail, create Calendar events, search across productivity apps, and use personal Gmail/Drive as sources for Deep Research, directly matching the story's cloud drive/email/calendar connector requirement. Missing for 10: independent/hands-on verification of search quality and confirmation that calendar reading (not just event creation) works reliably.

                • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses. With your permission, Gemini can also he…”
                • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses.”
                • [claimed-docs] “With your permission, Gemini can also help you take actions, like editing and managing your content in other apps.”
                • [claimed-docs] “You can change or add other sources, like your personal Gmail or Drive, for your research. You can also upload files and add NotebookLM note…”
                • [claimed-docs] “Boost productivity: Summarize emails from Gmail, create events in Google Calendar or third-party apps, or search for content across a variet…”
                • [claimed-docs] “Get started with Connected Apps in Gemini **Important:** For now, Gemini can’t use Connected Apps in Gemini in Google Messages.”
                proof ↗⚑ flag
                Pokepartialclaimed3/10

                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

              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 Poke
                Gemininone0/10

                The evidence pack shows Gemini can import/upload code folders and GitHub repos and get 'insights' from uploaded documents/spreadsheets, but there is no evidence of an actual code-execution/sandbox feature that writes and runs code to produce charts, computed answers, or downloadable output files. No docs or community reports describe this specific data-analysis-with-code-execution workflow.

                • [claimed-docs] “To add a GitHub repository: More Uploads Import Code and enter the GitHub repository or branch URL.”
                • [claimed-docs] “To add a code folder: click More Uploads Import Code Upload folder.”
                • [claimed-docs] “You can upload documents, spreadsheets, notebooks, photos, videos, and more to Gemini Apps to get answers, summaries, and insights about you…”
                proof ↗⚑ flag
                Pokepartialclaimed4/10

                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 Gemini
                Geminipartialclaimed4/10

                Evidence documents Gemini's ability to generate and iteratively edit images (Nano Banana) with export/download at set resolutions, and general writing assistance, but there is no evidence of a dedicated document or presentation creation/editing workflow (e.g., a canvas-style doc/slide editor) with export to file formats. Missing for 10: explicit documentation of creating/iterating on text documents or slide decks, and exporting them to standard file formats (docx/pptx/pdf).

                • [claimed-docs] “You can create captivating images in seconds with Nano Banana 2. From work, play, or anything in between, Gemini Apps can help you generate …”
                • [claimed-docs] “Local edits: Making quick and specific changes to parts of an image.”
                • [claimed-docs] “Character consistency: Maintain the look of a person or character across various generated images, including the ability to combine multiple…”
                • [claimed-docs] “Download images at at 2K resolution with a Google AI plan or at 1K without an AI plan.”
                • [claimed-docs] “Blend text, images, and video to bring your ideas to life.”
                • [claimed-docs] “The Gemini app provides quick access to AI features, allowing you to get help with writing, brainstorming, coding, and more, without needing…”
                proof ↗⚑ flag
                Pokenone0/10

                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 Gemini
                Geminifullcommunity8/10

                First-party docs explicitly state users can upload documents, spreadsheets, and more to get answers, summaries, and insights (gemini-docs-25), and independent hands-on evidence corroborates accurate document/PDF analysis (a fintech user reporting 96% OCR accuracy on PDFs, comm-17) plus praise for NotebookLM's ability to comprehend large source corpora (comm-19). Missing for 10: dedicated evidence on spreadsheet-specific accuracy and broader independent benchmarking across document types beyond the single fintech PDF case.

                • [claimed-docs] “You can upload documents, spreadsheets, notebooks, photos, videos, and more to Gemini Apps to get answers, summaries, and insights about you…”
                • [community] “I work in fintech and we replaced an OCR vendor with Gemini at work for ingesting some PDFs... Processing time went from something like 12 m…”
                • [community] “I've been using NotebookLM powered by Gemini 2.0 for three projects and it is really powerful for comprehending large corpuses you can't pos…”
                proof ↗⚑ flag
                Pokepartialclaimed3/10

                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 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 Gemini
                Geminifullclaimed8/10

                Gemini docs explicitly describe a personalization feature where 'the memory of your past Gemini chats' informs new conversations, plus user controls to review/delete that activity, confirming both the capability and its persistence across sessions. Missing for 10: independent hands-on validation of cross-chat memory recall accuracy and more detail on scope/duration of retained context.

                • [claimed-docs] “You can get a personalized experience in Gemini Apps based on: The memory of your past Gemini chats”
                • [claimed-docs] “You can review your prompts, delete your Gemini Apps activity, and turn off Keep Activity in My Activity at any time.”
                proof ↗⚑ flag
                Pokepartialclaimed5/10

                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 Gemini
                Geminipartialclaimed5/10

                Gemini offers a 'memory of past chats' personalization feature (gemini-docs-18) and custom Gems that let users pre-set instructions/goals (gemini-docs-9), which together approximate persistent customization, but there's no documented single 'custom instructions' setting that explicitly shapes every response across all chats. Missing for 10: explicit persistent instruction/preference settings applied globally to every response, independent verification of memory consistency, and detail on how memory interacts with different chat sessions.

                • [claimed-docs] “You can get a personalized experience in Gemini Apps based on: The memory of your past Gemini chats”
                • [claimed-docs] “To create a custom Gem to meet your goals, provide info about your request and requirements.”
                • [claimed-docs] “Start your day with a personalized digest from Gemini. Your Daily Brief understands your rhythms and personal preferences to deliver your to…”
                proof ↗⚑ flag
                Pokepartialclaimed3/10

                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 Gemini
                Geminifullcommunity7/10

                Gemini's 'Notebooks' feature explicitly provides a continuous, focused space that remembers sources, instructions, and ongoing chat history, and lets users upload documents, code, and other files into that same organized context (gemini-docs-11, gemini-docs-24, gemini-docs-25, gemini-docs-29). Custom Gems (gemini-docs-9) further let users set persistent instructions for recurring tasks, and independent commentary confirms NotebookLM/Notebooks are genuinely useful for organizing large source sets into a coherent project workspace (gemini-comm-19), though that same source flags UI/display shortcomings. Missing for 10: no first-party doc detailing multi-chat organization within one persistent 'project' the way competitors define it, and no hands-on evidence of shared-instruction consistency across many chats in the same notebook.

                • [claimed-docs] “Notebooks provide a continuous chat experience that remembers your sources, instructions, and ongoing discussions.”
                • [claimed-docs] “you can use notebooks to organize your projects in a dedicated, focused space.”
                • [claimed-docs] “You can upload documents, spreadsheets, notebooks, photos, videos, and more to Gemini Apps to get answers, summaries, and insights about you…”
                • [claimed-docs] “You can change or add other sources, like your personal Gmail or Drive, for your research. You can also upload files and add NotebookLM note…”
                • [claimed-docs] “To create a custom Gem to meet your goals, provide info about your request and requirements.”
                • [community] “I've been using NotebookLM powered by Gemini 2.0 for three projects and it is really powerful for comprehending large corpuses you can't pos…”
                proof ↗⚑ flag
                Pokenone0/10

                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

                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 Gemini
                  Geminifullclaimed8/10

                  Gemini docs explicitly describe generating and editing images via natural-language prompts (Nano Banana 2), including local edits, character consistency, blending images, and resolution export options. missing for 10: independent hands-on corroboration of image editing quality and no community evidence testing this specific feature.

                  • [claimed-docs] “You can create captivating images in seconds with Nano Banana 2. From work, play, or anything in between, Gemini Apps can help you generate …”
                  • [claimed-docs] “Local edits: Making quick and specific changes to parts of an image.”
                  • [claimed-docs] “Character consistency: Maintain the look of a person or character across various generated images, including the ability to combine multiple…”
                  • [claimed-docs] “You can create captivating images in seconds with Nano Banana 2.”
                  • [claimed-docs] “Download images at at 2K resolution with a Google AI plan or at 1K without an AI plan.”
                  • [claimed-docs] “Blend text, images, and video to bring your ideas to life.”
                  proof ↗⚑ flag
                  Pokenone0/10

                  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

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

                    weight 2 · round to Poke
                    Geminidisputedcontradicted4/10

                    Docs confirm users can upload photos/screenshots and get insights (gemini-docs-25) and get screen-context help via 'Hey Google' (gemini-docs-6), but hands-on reports show real accuracy failures: Gemini generated 'wildly inaccurate bounding boxes' on images (gemini-comm-18) and failed to correctly interpret a manipulated photo, missing key details even in the latest version (gemini-comm-12). A positive OCR use case exists (gemini-comm-17) but that's for PDFs, not general screenshot/photo scene interpretation, so the core 'accurately interpret' claim is contradicted by concrete hands-on failures. Missing for 10: independent benchmarks specifically on screenshot/UI interpretation accuracy, and resolution of the documented bounding-box/detail-recognition failures.

                    • [claimed-docs] “You can upload documents, spreadsheets, notebooks, photos, videos, and more to Gemini Apps to get answers, summaries, and insights about you…”
                    • [claimed-docs] “On Android, say “Hey Google” to ask Gemini for help with what’s on your screen”
                    • [community] “Unfortunately Gemini really seems to struggle on this, and no matter how we tried prompting it, it would generate wildly inaccurate bounding…”
                    • [community] “It still failed my image identification test (a photoshopped picture of a dog with 5 legs)... Gemini 3 however, while still failing, at leas…”
                    • [community] “I work in fintech and we replaced an OCR vendor with Gemini at work for ingesting some PDFs... Processing time went from something like 12 m…”
                    proof ↗⚑ flag
                    Pokepartialclaimed5/10

                    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 Gemini
                    Geminifullclaimed8/10

                    Gemini Live is explicitly documented to support natural, free-flowing, interruptible voice conversations where Gemini talks back verbally in real time, directly matching the story. Missing for 10: independent/hands-on community corroboration specifically validating the voice conversation experience (community evidence covers other Gemini features/models but not Live voice interactions).

                    • [claimed-docs] “With Gemini Live, you can have a natural, free-flowing conversation with Gemini. You can even interrupt it like when you want to add more de…”
                    • [claimed-docs] “With Gemini Live, you can have a natural, free-flowing conversation with Gemini.”
                    • [claimed-docs] “With Gemini Live, you can: * **Talk back and forth:** Talk to Gemini without typing, and Gemini will respond back verbally.”
                    • [claimed-docs] “you can have a natural, free-flowing conversation with Gemini. You can even interrupt it like when you want to add more details or change th…”
                    proof ↗⚑ flag
                    Pokenone0/10

                    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

                    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 Poke
                      Gemininone0/10

                      The evidence pack details many Gemini Apps UI-only features (Gems, Deep Research, Connected Apps, Daily Brief, Live conversations, Notebooks, scheduling) with no corresponding API documentation showing these are exposed programmatically. Community evidence (e.g., gemini-comm-11) even notes the API/AI Studio path is more restricted (capped temperature, hidden top_k) than the full product, reinforcing that API and UI capability sets are not equivalent.

                      • [claimed-docs] “You can conduct in-depth and real-time research on almost any subject with Deep Research in Gemini Apps.”
                      • [claimed-docs] “To create a custom Gem to meet your goals, provide info about your request and requirements.”
                      • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses. With your permission, Gemini can also he…”
                      • [claimed-docs] “With Gemini Live, you can have a natural, free-flowing conversation with Gemini. You can even interrupt it like when you want to add more de…”
                      • [claimed-docs] “Start your day with a personalized digest from Gemini. Your Daily Brief understands your rhythms and personal preferences to deliver your to…”
                      • [community] “Temperature continues to be gated to maximum of 0.2, and there's still the hidden top_k of 64 that you can't turn off. I love the google AI …”
                      proof ↗⚑ flag
                      Pokepartialprobed4/10

                      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
                      Gemininone0/10

                      Evidence covers activity deletion/review (gemini-docs-31) but no mention of exporting data in open/portable formats or data-export tooling for leaving the platform. Missing for 10: any documentation of a data export/download feature (e.g., Google Takeout integration), open-format export options, or independent confirmation of data portability.

                      • [claimed-docs] “You can review your prompts, delete your Gemini Apps activity, and turn off Keep Activity in My Activity at any time.”
                      proof ↗⚑ flag
                      Pokenone0/10

                      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

                      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
                        Gemininone0/10

                        The evidence pack covers Gemini's features and privacy/data-use settings (e.g., activity retention, human review opt-outs) but contains no mention of data residency or regional storage controls for AI-native/enterprise users. missing for 10: any documentation of region selection, data residency guarantees, or enterprise data-location controls.

                          ⚑ flag
                          Pokenone0/10

                          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

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

                            weight 3 · round to Gemini
                            Geminipartialclaimed7/10

                            Google's support docs state that chats and uploaded files in Gemini Apps are not reviewed by humans or used to improve generative AI models, and users can manage/delete their activity via 'My Activity' and toggle 'Keep Activity' off (gemini-docs-38, gemini-docs-31). However, a separate doc notes that audio/video from Gemini Live can be used to train models unless the user opts out, showing the training-data control is feature-specific rather than a single unified setting (gemini-docs-37). Missing for 10: a clear, centralized opt-out control covering all Gemini surfaces (not just chat text), independent/hands-on verification that opted-out data is truly excluded from training, and clarity for enterprise/Workspace accounts.

                            • [claimed-docs] “Your chats and uploaded files in Gemini Apps won’t be reviewed by human reviewers or otherwise used to improve generative AI models.”
                            • [claimed-docs] “You can let Google use your audio and Gemini Live videos and screenshares to improve and develop its services, including training generative…”
                            • [claimed-docs] “You can review your prompts, delete your Gemini Apps activity, and turn off Keep Activity in My Activity at any time.”
                            proof ↗⚑ flag
                            Pokenone0/10

                            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

                            • ai-native userControl data retention and deletion

                              weight 2 · round to Gemini
                              Geminifullclaimed8/10

                              Google's support docs explicitly describe controls to review prompts, delete Gemini Apps activity, and turn off 'Keep Activity' (gemini-docs-31), plus explicit statements that chats/files are not used for model training by default (gemini-docs-38) while audio/video in Gemini Live can be opted in/out of training use (gemini-docs-37) — directly matching retention/deletion control for an AI-native user. Missing for 10: independent/hands-on verification that deletion actually removes data, and detail on data export or full account-level deletion workflows.

                              • [claimed-docs] “You can review your prompts, delete your Gemini Apps activity, and turn off Keep Activity in My Activity at any time.”
                              • [claimed-docs] “You can let Google use your audio and Gemini Live videos and screenshares to improve and develop its services, including training generative…”
                              • [claimed-docs] “Your chats and uploaded files in Gemini Apps won’t be reviewed by human reviewers or otherwise used to improve generative AI models.”
                              proof ↗⚑ flag
                              Pokenone0/10

                              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

                              • ai-native userOpt out of telemetry and usage tracking

                                weight 2 · round to Gemini
                                Geminipartialclaimed6/10

                                Docs show Gemini provides some privacy controls: reviewing/deleting prompts and turning off 'Keep Activity' (gemini-docs-31), and settings around whether audio/video/chats are used to improve models (gemini-docs-37, gemini-docs-38). This addresses usage-history and training-data opt-out but not a full 'telemetry/usage tracking' opt-out (e.g., diagnostic/product analytics separate from chat history) and there's no independent verification of these controls' effectiveness. Missing for 10: explicit documentation of a general telemetry/analytics opt-out toggle beyond activity/training-data settings, and independent/hands-on confirmation that opting out actually stops tracking.

                                • [claimed-docs] “You can review your prompts, delete your Gemini Apps activity, and turn off Keep Activity in My Activity at any time.”
                                • [claimed-docs] “You can let Google use your audio and Gemini Live videos and screenshares to improve and develop its services, including training generative…”
                                • [claimed-docs] “Your chats and uploaded files in Gemini Apps won’t be reviewed by human reviewers or otherwise used to improve generative AI models.”
                                proof ↗⚑ flag
                                Pokenone0/10

                                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 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 Gemini
                                  Geminifullclaimed7/10

                                  Gemini Apps has a documented Deep Research feature that conducts in-depth, real-time research across sources and allows adding personal sources (Gmail, Drive, uploads, NotebookLM notebooks) for the research, matching the autonomous multi-source research story. missing for 10: explicit documentation of citation formatting in the final report and independent hands-on evidence of report quality/citation accuracy from third parties.

                                  • [claimed-docs] “You can conduct in-depth and real-time research on almost any subject with Deep Research in Gemini Apps.”
                                  • [claimed-docs] “You can change or add other sources, like your personal Gmail or Drive, for your research. You can also upload files and add NotebookLM note…”
                                  proof ↗⚑ flag
                                  Pokenone0/10

                                  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

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

                                    weight 2 · round to Gemini
                                    Geminipartialclaimed6/10

                                    Gemini's Deep Research feature explicitly supports 'in-depth and real-time research on almost any subject,' implying grounded, current-web-based answers, and users can add further sources for research context. However, the evidence pack never explicitly documents inline citation links back to specific web sources, nor independent confirmation that citations are reliably shown. Missing for 10: explicit documentation of citation/source-linking UI, independent verification that citations are accurate and consistently displayed.

                                    • [claimed-docs] “You can conduct in-depth and real-time research on almost any subject with Deep Research in Gemini Apps.”
                                    • [claimed-docs] “You can change or add other sources, like your personal Gmail or Drive, for your research. You can also upload files and add NotebookLM note…”
                                    proof ↗⚑ flag
                                    Pokenone0/10

                                    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

                                    Trust controls — stories about trust controls in this arenaTrust controls

                                    Stories about trust controls in this arena

                                    Data controls

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

                                      weight 1 · round drawn
                                      Gemininone0/10

                                      The evidence only covers reviewing and deleting Gemini activity via My Activity (gemini-docs-31) and privacy settings for Live audio (gemini-docs-37, gemini-docs-38), but there is no mention of exporting chat history or account data (e.g., via Google Takeout or a dedicated export tool). missing for 10: any documentation of an export/download feature for chat history or account data, independent confirmation of export completeness.

                                      • [claimed-docs] “You can review your prompts, delete your Gemini Apps activity, and turn off Keep Activity in My Activity at any time.”
                                      proof ↗⚑ flag
                                      Pokenone0/10

                                      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

                                      • knowledge-workerControl whether my conversations are used to train models

                                        weight 3 · round to Gemini
                                        Geminifullclaimed8/10

                                        Google's own support docs state that by default chats/uploaded files aren't used to improve generative AI models unless a user opts in via 'Keep Activity', and that users can review, delete activity, or turn off Keep Activity at any time; separately, users must explicitly consent to let Google use Gemini Live audio/video for model training. This gives knowledge-workers clear, documented control over whether conversations feed model training. Missing for 10: independent/hands-on verification that these settings work as described and clarity on enterprise/Workspace account defaults.

                                        • [claimed-docs] “You can review your prompts, delete your Gemini Apps activity, and turn off Keep Activity in My Activity at any time.”
                                        • [claimed-docs] “You can let Google use your audio and Gemini Live videos and screenshares to improve and develop its services, including training generative…”
                                        • [claimed-docs] “Your chats and uploaded files in Gemini Apps won’t be reviewed by human reviewers or otherwise used to improve generative AI models.”
                                        proof ↗⚑ flag
                                        Pokenone0/10

                                        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

                                        Not comparable on these axes

                                        1. ai-native userConnect an agent via an official MCP server

                                          weight 3 · not comparable
                                          Geminin/a

                                          Gemini is itself an AI assistant/agent product; the evidence shows only that it can connect outward to other apps (Connected Apps, code import) as a client, not that it exposes an official MCP server for other agents to connect to it. Per the agent-role exception, this axis does not apply unless Gemini documents running as an MCP server, which no evidence here shows.

                                          • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses. With your permission, Gemini can also he…”
                                          • [claimed-docs] “Gemini Apps can connect to other apps to complete your request and give you more helpful responses.”
                                          • [claimed-docs] “With your permission, Gemini can also help you take actions, like editing and managing your content in other apps.”
                                          • [claimed-docs] “Get started with Connected Apps in Gemini **Important:** For now, Gemini can’t use Connected Apps in Gemini in Google Messages.”
                                          proof ↗⚑ flag
                                          Poken/a

                                          Poke is itself an AI agent product; all MCP evidence (poke-docs-3,4,16) shows Poke acting as an MCP *client*—connecting to or tunneling external MCP servers to extend its own capabilities—not Poke exposing an official MCP server endpoint for other agents to connect to. Per the agent-role rule, this client-side capability does not make the 'official MCP server' axis applicable.

                                            ⚑ flag

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

                                            weight 2 · not comparable
                                            Geminin/a

                                            Gemini is an AI product/app, not a platform issuing API credentials with scoped permissions for agents; the evidence pack covers consumer features (imports, images, connected apps) with no mention of credential scoping or API key/permission management for agents, so this axis is a category error for this product's evidenced role.

                                              ⚑ flag
                                              Pokenone0/10

                                              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

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

                                                weight 2 · not comparable
                                                Geminin/a

                                                This story asks for an interactive API reference with runnable examples, which is a developer-portal/API-docs concern, not a fair axis for Gemini Apps (the consumer product surfaced in this evidence pack). The evidence pack covers Gemini's app features (Gems, Connected Apps, Deep Research, Live) but contains no mention of an interactive API reference, making this a wrong-axis question for the product as evidenced.

                                                  ⚑ flag
                                                  Pokenone0/10

                                                  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

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

                                                  weight 2 · not comparable
                                                  Geminin/a

                                                  Gemini here refers to the consumer AI assistant app/product; the story asks for a downloadable machine-readable API spec (OpenAPI), which is a developer-platform artifact, not a consumer app feature. This axis applies to API/platform products, not to the Gemini Apps experience described in the evidence.

                                                    ⚑ flag
                                                    Pokenone0/10

                                                    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

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

                                                    weight 1 · not comparable
                                                    Geminin/a

                                                    Gemini is a consumer/enterprise assistant product, not a dev platform with sandbox/production data environments; the evidence pack shows no sandbox testing environment concept, making this axis a category error for this product type.

                                                      ⚑ flag
                                                      Pokenone0/10

                                                      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

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

                                                        weight 2 · not comparable
                                                        Geminipartialclaimed5/10

                                                        Docs confirm an official Mac desktop app with a global OS-level keyboard shortcut (Option+Space) to summon Gemini without opening a browser [gemini-docs-15, gemini-docs-36, gemini-docs-20], but the only 'see what's on your screen' capability documented is for the Android mobile app via 'Hey Google' [gemini-docs-6], not the desktop app. Missing for 10: evidence of desktop screen-reading/screenshare capability, and independent/hands-on confirmation of the desktop shortcut and screen access working together.

                                                        • [claimed-docs] “you can also use the keyboard shortcut Option + Space to bring up the Gemini chat window after the app is installed and running”
                                                        • [claimed-docs] “The Gemini app provides quick access to AI features, allowing you to get help with writing, brainstorming, coding, and more, without needing…”
                                                        • [claimed-docs] “What you need to use the Gemini app on Mac * A personal Google Account you manage on your own, or a work or school account that your adminis…”
                                                        • [claimed-docs] “On Android, say “Hey Google” to ask Gemini for help with what’s on your screen”
                                                        proof ↗⚑ flag
                                                        Poken/a

                                                        Poke is a messaging-based AI assistant (WhatsApp/Telegram/Apple Messages/API/MCP integrations), not a desktop application with OS-level shortcuts or screen access; this axis is a category error for its product type.

                                                          ⚑ flag

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

                                                          weight 2 · not comparable
                                                          Geminin/a

                                                          Gemini is a closed, proprietary AI product; no evidence suggests its source code is available under an open license, and open-sourcing the model itself is not a plausible axis for this kind of commercial closed product.

                                                            ⚑ flag
                                                            Pokenone0/10

                                                            No evidence Poke's source code is published under any open license; Poke is presented as a closed SaaS product with docs, APIs, and integrations but no repository or licensing information is mentioned anywhere in the evidence pack.

                                                              ⚑ flag

                                                            • ai-native userSelf-host the core product

                                                              weight 3 · not comparable
                                                              Geminin/a

                                                              Gemini is a closed, proprietary hosted AI service with no evidence of any self-hostable model weights or on-prem deployment option; self-hosting is not a plausible axis for this cloud-only consumer/enterprise product category.

                                                                ⚑ flag
                                                                Pokenone0/10

                                                                Poke is a hosted SaaS assistant with no evidence of any self-hostable core product, open-source release, or on-prem deployment option; all docs describe a cloud service accessed via API/integrations/MCP.

                                                                  ⚑ flag

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

                                                                  weight 2 · not comparable
                                                                  Gemininone0/10

                                                                  Evidence only shows end-user features (image generation, Live conversations, notebooks, connected apps) and passing mentions that a 'work or school account' administrator can 'enable Gemini,' but there is no evidence of an admin console for managing members, setting permissions, or configuring org-wide data policies.

                                                                    ⚑ flag
                                                                    Poken/a

                                                                    Poke is a consumer personal AI assistant (individual account, messaging channels, integrations, recipes) with no evidence of organizational/team workspace concepts like member management, role-based permissions, or org-wide data policies. This is a category mismatch rather than a missing feature.

                                                                      ⚑ flag