Muse vs Poke

Agent access

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

   weight 3 · round to Poke
   Muse—none0/10

   No evidence Muse supports plugging in external MCP servers; it only describes its agent building its own tools internally, which is a different mechanism.

   • [claimed-docs] “If a task needs a tool that doesn't exist, your agent builds it for you.”
   • [claimed-docs] “Muse has its own computer, with a file system and a terminal, so it can write its own code and build the tools a task needs.”

   proof ↗⚑ flag

   Poke✓fullprobed8/10

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

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

   proof ↗⚑ flag

2. ai-native userUse an official CLI

   weight 2 · round to Poke
   Muse—none0/10

   No evidence of an official CLI for Muse; all evidence describes a consumer app/avatar/chat interface with an internal terminal for the agent itself, not a CLI for AI-native users to interact with Muse.

   ⚑ flag

   Poke~partialclaimed6/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round to Poke
   Muse—none0/10

   No evidence of a documented public API for developers to programmatically drive Muse; all evidence describes end-user chat/app features and internal agent behavior, not an external API surface.

   ⚑ flag

   Poke~partialprobed6/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Muse—none0/10

   Evidence shows Muse has approval cards, activity logs, and permission tracking for connected accounts, but nothing about issuing scoped or least-privilege API credentials/tokens for an agent to use with external services — this is a consumer personal-agent product, not a developer credential-management tool.

   ⚑ flag

   Poke—none0/10

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

   ⚑ flag

5. ai-native userBuild against official SDKs

   weight 2 · round to Poke
   Muse—none0/10

   No evidence of any official SDK for developers to build against; evidence only covers end-user features (avatars, goals, side chats, agent building its own tools) rather than a developer-facing SDK.

   ⚑ flag

   Poke~partialprobed4/10

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

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

   proof ↗⚑ flag

6. ai-native userSubscribe to events via webhooks

   weight 2 · round to Poke
   Muse—none0/10

   No evidence in the pack mentions webhooks or any event-subscription API for developers; Muse's documented features focus on agent tasks, permissions, and integrations, not outbound webhook subscriptions. missing for 10: any webhook/event API documentation, developer subscription mechanism, or third-party confirmation of webhook support.

   ⚑ flag

   Poke~partialclaimed4/10

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

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

   proof ↗⚑ flag

Agentic features

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

   weight 2 · round to Muse
   Muse~partialclaimed5/10

   Muse links personal data sources (email, calendar, social, health, finances) and proactively tracks tasks/goals, implying some data-driven suggestions, but the evidence never explicitly describes AI-generated insights or recommendations derived from that data—most documentation focuses on agentic task execution and tool-building rather than analytic insight generation. missing for 10: explicit description of insight/recommendation generation from user data, independent hands-on validation of this specific capability.

   • [claimed-docs] “Link your email, calendar, Instagram, Facebook, health and fitness data, and finances.”
   • [claimed-docs] “The Goals tab is where Muse keeps track of all this for you, and you can interact directly there or talk to it about these tasks in chat.”
   • [claimed-docs] “If a task needs a tool that doesn't exist, your agent builds it for you.”

   proof ↗⚑ flag

   Poke~partialclaimed4/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round to Poke
   Muse!disputedcontradicted5/10

   Muse's Goals tab, activity log, and approval-card workflow (muse-docs-5, muse-docs-8, muse-docs-13) show first-party support for autonomous background task tracking and execution, and muse-docs-7 explicitly describes agents building tools for unattended tasks. However, an independent hands-on stress test found the agent's control plane starts timing out under load, exposing concrete failure points in its background-automation architecture (muse-comm-1), directly undercutting reliability claims for autonomous operation. missing for 10: independent confirmation that background automations run reliably at scale, more detail on scheduling/triggering mechanisms for autonomous runs.

   • [claimed-docs] “The Goals tab is where Muse keeps track of all this for you, and you can interact directly there or talk to it about these tasks in chat.”
   • [claimed-docs] “If a task needs a tool that doesn't exist, your agent builds it for you.”
   • [claimed-docs] “Tapping on your Muse avatar will show you its full activity log as well as permissions you’ve approved.”
   • [claimed-docs] “Muse shows people a complete audit trail of everything it has done and plans to do.”
   • [community] “Blog post title/finding: the author stress-tested Meta Muse until its agent control plane started timing out, exposing failure points in the…”

   proof ↗⚑ flag

   Poke~partialprobed5/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round drawn
   Muse✓fullclaimed8/10

   Muse is explicitly a built-in AI agent with its own compute, terminal, and file system to build tools and complete delegated tasks (goals, side chats, autonomous tool creation), with approval flows and activity logs for oversight. Missing for 10: independent hands-on verification of delegation quality beyond stress-test edge cases and more detail on task breadth/reliability at scale.

   • [claimed-docs] “Muse has its own computer, with a file system and a terminal, so it can write its own code and build the tools a task needs.”
   • [claimed-docs] “The Goals tab is where Muse keeps track of all this for you, and you can interact directly there or talk to it about these tasks in chat.”
   • [claimed-docs] “If a task needs a tool that doesn't exist, your agent builds it for you.”
   • [claimed-docs] “Tapping on your Muse avatar will show you its full activity log as well as permissions you’ve approved.”
   • [claimed-docs] “Muse shows people a complete audit trail of everything it has done and plans to do.”

   proof ↗⚑ flag

   Poke✓fullprobed8/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round to Poke
   Muse✓fullcommunity7/10

   Muse is designed around a chat interface where users talk to it in natural language to manage goals, tasks, and tool-building ('talk to it about these tasks in chat', side chats for topic-specific NL interaction). This is corroborated by first-party docs describing conversational control as the primary interface. missing for 10: independent hands-on confirmation of broad natural-language command coverage beyond goals/chat, and detail on command reliability at scale (comm-1 notes control-plane timeouts under stress).

   • [claimed-docs] “The Goals tab is where Muse keeps track of all this for you, and you can interact directly there or talk to it about these tasks in chat.”
   • [claimed-docs] “some people still wanted separate context for certain topics — which made sense as projects grew more complex. So we built side chats.”
   • [claimed-docs] “Tapping on your Muse avatar will show you its full activity log as well as permissions you’ve approved.”
   • [community] “Blog post title/finding: the author stress-tested Meta Muse until its agent control plane started timing out, exposing failure points in the…”

   proof ↗⚑ flag

   Poke✓fullprobed8/10

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

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

   proof ↗⚑ flag

Api quality

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

   weight 2 · round drawn
   Muse—none0/10

   No evidence Muse publishes any machine-readable API spec (OpenAPI or equivalent) for developers; all evidence concerns end-user agent features, not a documented API surface.

   ⚑ flag

   Poke—none0/10

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

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

   proof ↗⚑ flag

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 Poke
   Muse!disputedcontradicted6/10

   Muse's docs describe autonomous background task handling via the Goals tab, self-built tools, activity logs and approval cards for review — matching the delegate-and-review story [muse-docs-5][muse-docs-7][muse-docs-8][muse-docs-13][muse-docs-10]. However, an independent hands-on stress test found the agent's control plane timing out under load, exposing failure points in the very autonomous-task architecture being claimed [muse-comm-1], and another commenter notes the assistant is less capable than power-user expectations for building/using tools [muse-comm-2]. Missing for 10: reproducible evidence of reliable long-running multi-step task completion, and resolution/acknowledgment of the reported control-plane timeout issue.

   • [claimed-docs] “The Goals tab is where Muse keeps track of all this for you, and you can interact directly there or talk to it about these tasks in chat.”
   • [claimed-docs] “If a task needs a tool that doesn't exist, your agent builds it for you.”
   • [claimed-docs] “Tapping on your Muse avatar will show you its full activity log as well as permissions you’ve approved.”
   • [claimed-docs] “Muse shows people a complete audit trail of everything it has done and plans to do.”
   • [claimed-docs] “structured approval cards with clear accept/reject actions, and secure storage for your credentials.”
   • [community] “Blog post title/finding: the author stress-tested Meta Muse until its agent control plane started timing out, exposing failure points in the…”
   • [community] “"I, too, have a personal agent but my friends using Muse or Instinct approach the functionality I use mine for quite easily... a sophisticat…”

   proof ↗⚑ flag

   Poke~partialprobed5/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round drawn
   Muse—none0/10

   Evidence describes Muse having its own computer/terminal to build tools, task tracking (Goals tab), and permissions/approval cards, but nothing in the pack mentions browser automation or web navigation on the user's behalf. Missing for 10: any mention of browser control, web research execution, or site-task completion capability.

   ⚑ flag

   Poke—none0/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round to Muse
   Muse~partialclaimed4/10

   Muse describes having its own computer/terminal to build tools and links external accounts (email, calendar, social, health, finance) via structured approvals, which lets it act on the user's behalf across services, but the evidence never shows it seeing or directly operating applications on the user's own device (e.g., screen/GUI control) — it operates its own sandboxed environment, not the user's computer. Missing for 10: evidence of direct screen/GUI control of the user's local applications, and independent confirmation that this cross-app automation reliably works beyond linked-account integrations.

   • [claimed-docs] “Muse has its own computer, with a file system and a terminal, so it can write its own code and build the tools a task needs.”
   • [claimed-docs] “If a task needs a tool that doesn't exist, your agent builds it for you.”
   • [claimed-docs] “structured approval cards with clear accept/reject actions, and secure storage for your credentials.”
   • [claimed-docs] “Link your email, calendar, Instagram, Facebook, health and fitness data, and finances.”

   proof ↗⚑ flag

   Poke—none0/10

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

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

   proof ↗⚑ flag

Tasks

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

   weight 2 · round to Muse
   Muse~partialcommunity5/10

   Muse's Goals tab and activity log suggest it can track and manage ongoing tasks with an audit trail of completed/planned actions, implying some form of persistent task tracking, but there is no explicit documentation of recurring/scheduled triggers or a scheduling UI. Community evidence also shows the agent's control plane can time out under stress, raising doubts about reliability for automated recurring runs. missing for 10: explicit scheduling/recurrence configuration docs, evidence of one-off vs recurring task setup, and independent confirmation that scheduled tasks reliably complete and report back.

   • [claimed-docs] “The Goals tab is where Muse keeps track of all this for you, and you can interact directly there or talk to it about these tasks in chat.”
   • [claimed-docs] “Muse shows people a complete audit trail of everything it has done and plans to do.”
   • [claimed-docs] “If a task needs a tool that doesn't exist, your agent builds it for you.”
   • [community] “Blog post title/finding: the author stress-tested Meta Muse until its agent control plane started timing out, exposing failure points in the…”

   proof ↗⚑ flag

   Poke—none0/10

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

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

   proof ↗⚑ flag

Apps

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

   weight 2 · round to Muse
   Muse~partialclaimed4/10

   There is clear evidence of an iOS app (App Store reviews cited via apps.apple.com), but no evidence at all of an Android app, and no detailed description of feature parity between platforms. missing for 10: Android app existence, feature-completeness claims for either platform, independent verification of app quality.

   • [claimed-docs] “I find it more pleasant than Gemini or ChatGPT which is my default for this type of work.”
   • [claimed-docs] “I’d been curious to try OpenClaw, but didn’t want to deal with the security concerns or headache of setting it up.”

   proof ↗⚑ flag

   Poke—none0/10

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

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

   proof ↗⚑ flag

Custom bots

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

   weight 2 · round to Poke
   Muse—none0/10

   Evidence shows Muse supports personal customization (avatar naming/style, side chats for separate contexts) but nothing about creating a distinct 'assistant' with its own instructions/knowledge base that can be shared with other users, which is the core of this story.

   ⚑ flag

   Poke~partialclaimed5/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Muse—none0/10

   No evidence describes Muse performing bulk operations across many items; docs mention goals tracking, avatars, side chats, and tool-building, but nothing about batch/bulk processing of items. The community stress-test post even highlights the agent timing out under load rather than handling bulk tasks smoothly.

   ⚑ flag

   Poke—none0/10

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

   ⚑ flag

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

   weight 3 · round to Poke
   Muse—none0/10

   The evidence describes Muse's goal tracking, tool-building, and approval workflows, but there is no mention of user-defined conditional rules or event-triggered automations (e.g., 'when X happens, do Y'). Missing for 10: any documentation of a rules/trigger engine, event-based automation configuration, or examples of users setting conditional actions.

   • [claimed-docs] “The Goals tab is where Muse keeps track of all this for you, and you can interact directly there or talk to it about these tasks in chat.”
   • [claimed-docs] “If a task needs a tool that doesn't exist, your agent builds it for you.”

   proof ↗⚑ flag

   Poke~partialclaimed5/10

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

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

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round drawn
   Muse—none0/10

   While Muse has a Goals tab that tracks ongoing tasks and an activity log, there is no evidence describing recurring/scheduled job execution, cron-like automation, or repeat-workflow triggers. missing for 10: explicit scheduling/recurrence feature, evidence of periodic execution, workflow automation configuration.

   ⚑ flag

   Poke—none0/10

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

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

   proof ↗⚑ flag

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

   weight 1 · round to Muse
   Muse~partialclaimed4/10

   Muse provides an activity log/audit trail and approval cards that support reviewing what the agent has done and plans to do (muse-docs-8, muse-docs-13, muse-docs-10), which covers the 'review' portion of the story. However, there is no evidence of explicit versioning of automations/skills or a rollback mechanism to revert an automation to a prior state — the 'Forget' skill only removes stored information, not automation history. missing for 10: explicit versioning of automations, a rollback/undo feature for agent actions, independent confirmation these review tools work reliably in practice.

   • [claimed-docs] “Tapping on your Muse avatar will show you its full activity log as well as permissions you’ve approved.”
   • [claimed-docs] “Muse shows people a complete audit trail of everything it has done and plans to do.”
   • [claimed-docs] “structured approval cards with clear accept/reject actions, and secure storage for your credentials.”
   • [claimed-docs] “You can also use the Forget skill to have Muse forget information about specific topics or people.”

   proof ↗⚑ flag

   Poke—none0/10

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

   ⚑ flag

Connectors

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

   weight 2 · round to Poke
   Muse~partialclaimed3/10

   Muse lets users link specific third-party data sources like email, calendar, Instagram, Facebook, health and finance data (muse-docs-11), which shows some connector-adding capability, but there is no evidence of a browsable directory or marketplace of third-party apps/connectors to explore and add. Missing for 10: an actual app/connector directory UI, discovery/browsing mechanism, and independent confirmation of a marketplace beyond ad-hoc account linking.

   • [claimed-docs] “Link your email, calendar, Instagram, Facebook, health and fitness data, and finances.”

   proof ↗⚑ flag

   Poke✓fullclaimed7/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round to Muse
   Muse~partialclaimed6/10

   Muse docs explicitly support linking email and calendar (and other data sources) with approval/permission controls, but no evidence mentions a cloud drive connector (e.g., Google Drive/Dropbox), and there's no hands-on confirmation that these connected sources are actually searched/used in answers beyond permission approval cards. missing for 10: explicit cloud drive integration, independent evidence of search/use in answers.

   • [claimed-docs] “Link your email, calendar, Instagram, Facebook, health and fitness data, and finances.”
   • [claimed-docs] “structured approval cards with clear accept/reject actions, and secure storage for your credentials.”
   • [claimed-docs] “Tapping on your Muse avatar will show you its full activity log as well as permissions you’ve approved.”

   proof ↗⚑ flag

   Poke~partialclaimed3/10

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

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

   proof ↗⚑ flag

Analysis

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

   weight 3 · round drawn
   Muse~partialcommunity4/10

   Muse's docs claim it 'has its own computer, with a file system and a terminal' and can 'write its own code and build the tools a task needs,' which supports general code-execution capability, but there's no explicit mention of producing charts, computed answers, or downloadable files for user data analysis. A community stress-test report also notes the agent's control plane can time out under load, raising doubts about reliability for heavier computational tasks. Missing for 10: explicit documentation or examples of chart generation, data analysis outputs, downloadable file creation, and independent verification of successful code-execution results.

   • [claimed-docs] “Muse has its own computer, with a file system and a terminal, so it can write its own code and build the tools a task needs.”
   • [claimed-docs] “If a task needs a tool that doesn't exist, your agent builds it for you.”
   • [community] “Blog post title/finding: the author stress-tested Meta Muse until its agent control plane started timing out, exposing failure points in the…”

   proof ↗⚑ flag

   Poke~partialclaimed4/10

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

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

   proof ↗⚑ flag

Artifacts

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

   weight 2 · round drawn
   Muse—none0/10

   Muse's evidence focuses on its file system/terminal, tool-building, goals, avatars, and privacy controls, but nothing describes creating or iteratively editing documents, presentations, or exportable files for knowledge-work tasks. missing for 10: any mention of document/presentation creation, editing UI, or export functionality.

   ⚑ flag

   Poke—none0/10

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

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

   proof ↗⚑ flag

Files

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

   weight 3 · round to Poke
   Muse—none0/10

   No evidence in the pack describes Muse handling document/spreadsheet/PDF uploads or analyzing their contents; the material focuses on agent features like avatars, goals, side chats, permissions, and tool-building, not file ingestion or analysis accuracy.

   ⚑ flag

   Poke~partialclaimed3/10

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

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

   proof ↗⚑ flag

Memory

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

   weight 3 · round drawn
   Muse~partialclaimed5/10

   Muse's docs imply persistent memory (a 'Forget skill' to remove remembered info about topics/people, plus 'side chats' for separate context threads and a Goals tab tracking ongoing tasks) suggesting it retains and reuses context across conversations, but there is no first-party or hands-on description of how memory is surfaced or applied in new chats. Missing for 10: explicit documentation of cross-chat memory recall/application, independent verification that remembered context actually surfaces in new conversations, and detail on memory scope/limits.

   • [claimed-docs] “You can also use the Forget skill to have Muse forget information about specific topics or people.”
   • [claimed-docs] “some people still wanted separate context for certain topics — which made sense as projects grew more complex. So we built side chats.”
   • [claimed-docs] “So we built side chats.”
   • [claimed-docs] “The Goals tab is where Muse keeps track of all this for you, and you can interact directly there or talk to it about these tasks in chat.”

   proof ↗⚑ flag

   Poke~partialclaimed5/10

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

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

   proof ↗⚑ flag

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

   weight 1 · round to Poke
   Muse—none0/10

   No evidence describes a persistent custom-instructions or preference-setting feature that shapes all responses; docs mention forget skill, avatars, side chats, and permissions but nothing about setting standing instructions/preferences.

   ⚑ flag

   Poke~partialclaimed3/10

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

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

   proof ↗⚑ flag

Projects

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

   weight 2 · round to Muse
   Muse~partialclaimed4/10

   Muse offers 'side chats' for separate context on topics as work grows complex and a Goals tab for tracking tasks, suggesting some contextual organization, but there is no explicit 'project/space' construct that bundles chats+files+shared instructions together. Missing for 10: explicit project/workspace container, file-attachment grouping, shared custom instructions across chats, and independent verification of how side chats share or isolate context.

   • [claimed-docs] “The Goals tab is where Muse keeps track of all this for you, and you can interact directly there or talk to it about these tasks in chat.”
   • [claimed-docs] “some people still wanted separate context for certain topics — which made sense as projects grew more complex. So we built side chats.”
   • [claimed-docs] “So we built side chats.”

   proof ↗⚑ flag

   Poke—none0/10

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

   ⚑ flag

Images

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

   weight 2 · round drawn
   Muse—none0/10

   The evidence pack contains no mention of image generation, editing, or any visual/multimodal content creation capability for Muse; it focuses on agent/task automation, avatars, chat organization, and privacy controls. missing for 10: any documentation of image generation from prompts, image editing tools, or multimodal output examples.

   ⚑ flag

   Poke—none0/10

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

   ⚑ flag

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

   weight 2 · round to Poke
   Muse—none0/10

   No evidence in the pack discusses image, screenshot, or photo interpretation capabilities of Muse; all citations focus on agent architecture, avatars, goals, side chats, and privacy controls. Missing for 10: any mention of image/vision input support, screenshot sharing, or accuracy of visual interpretation.

   ⚑ flag

   Poke~partialclaimed5/10

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

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

   proof ↗⚑ flag

Voice

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

   weight 2 · round drawn
   Muse—none0/10

   No evidence describes real-time voice conversation capability for Muse; the evidence pack focuses on agent tool-building, goals, side chats, avatar, and privacy features, with no mention of voice interaction or speech interface. Missing for 10: any documentation of voice input/output, real-time conversational voice mode, or hands-on account of speaking with Muse.

   ⚑ flag

   Poke—none0/10

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

   ⚑ flag

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

   weight 2 · round to Poke
   Muse—none0/10

   No evidence pack mentions a public API for Muse at all; all evidence describes UI features (avatars, Goals tab, side chats, activity log) with no mention of programmatic access. Absence of evidence for an applicable capability is 'none'.

   ⚑ flag

   Poke~partialprobed4/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round drawn
   Muse—none0/10

   There is no evidence of a data export feature or open-format data portability in Muse; the pack only mentions a 'Forget' privacy skill and audit trail, not export/download of user data.

   ⚑ flag

   Poke—none0/10

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

   ⚑ flag

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

   weight 2 · round drawn
   Muse—none0/10

   No evidence indicates Muse's source code is published under any open license; all evidence describes product features and community discussion, not source availability.

   ⚑ flag

   Poke—none0/10

   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

4. ai-native userSelf-host the core product

   weight 3 · round drawn
   Muse—none0/10

   No evidence anywhere in the pack indicates Muse can be self-hosted; it's described as a cloud/app-based agent product with no mention of open-source release or self-hosting options.

   ⚑ flag

   Poke—none0/10

   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

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

   weight 2 · round drawn
   Muse—none0/10

   No evidence in the pack mentions data residency, region selection, or storage location controls for Muse users.

   ⚑ flag

   Poke—none0/10

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

   ⚑ flag

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

   weight 3 · round drawn
   Muse—none0/10

   The evidence pack covers Muse's agent features, permissions, forget skill, and audit trail, but contains no mention of any opt-out or control over whether user data is used to train AI models. missing for 10: explicit opt-out/consent setting for model training, any privacy policy language addressing training-data usage.

   ⚑ flag

   Poke—none0/10

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

   ⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round to Muse
   Muse~partialclaimed6/10

   Muse offers a 'Forget' skill to remove information about specific topics/people and provides an activity log/audit trail of actions, giving users some visibility and control, but there's no documentation of full account/data deletion, export, or granular retention policy settings. Missing for 10: explicit data export/deletion controls, retention period settings, and independent verification that 'Forget' fully purges underlying data rather than just suppressing recall.

   • [claimed-docs] “You can also use the Forget skill to have Muse forget information about specific topics or people.”
   • [claimed-docs] “Muse shows people a complete audit trail of everything it has done and plans to do.”
   • [claimed-docs] “Tapping on your Muse avatar will show you its full activity log as well as permissions you’ve approved.”

   proof ↗⚑ flag

   Poke—none0/10

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

   ⚑ flag

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

   weight 2 · round drawn
   Muse—none0/10

   No evidence pack items mention a telemetry/usage-tracking opt-out setting; there is a 'Forget skill' for topic memory and privacy page references, but nothing about disabling telemetry or usage analytics collection. Missing for 10: any documentation of a telemetry/analytics opt-out toggle, privacy policy language on usage data collection, or user reports confirming such a control exists.

   • [claimed-docs] “You can also use the Forget skill to have Muse forget information about specific topics or people.”
   • [claimed-docs] “Muse shows people a complete audit trail of everything it has done and plans to do.”

   proof ↗⚑ flag

   Poke—none0/10

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

   ⚑ flag

Research

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

   weight 3 · round drawn
   Muse—none0/10

   No evidence describes Muse performing a deep research run that autonomously searches multiple sources and returns a cited report; the pack focuses on avatar personalization, goals/side chats, permissions, and tool-building, none of which document a research/citation workflow. Missing for 10: any mention of multi-source search, report generation, or citation output.

   ⚑ flag

   Poke—none0/10

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

   ⚑ flag

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

   weight 2 · round drawn
   Muse—none0/10

   No evidence in the pack describes Muse performing web search with cited sources for research answers; the material focuses on agent architecture, avatars, permissions, and goals rather than grounded citation-backed answers.

   ⚑ flag

   Poke—none0/10

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

   ⚑ flag

Data controls

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

   weight 1 · round drawn
   Muse—none0/10

   Evidence shows a 'Forget' skill and audit trail/activity log, but there is no mention of a data export or account data download feature for chat history or account data. missing for 10: export/download tool for chat history, account data export functionality, documentation of data portability process.

   • [claimed-docs] “You can also use the Forget skill to have Muse forget information about specific topics or people.”
   • [claimed-docs] “Muse shows people a complete audit trail of everything it has done and plans to do.”

   proof ↗⚑ flag

   Poke—none0/10

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

   ⚑ flag

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

   weight 3 · round drawn
   Muse—none0/10

   The evidence pack shows privacy-adjacent features like a 'Forget skill' for memory and audit trails/permissions, but nothing addresses whether users can opt their conversations out of model training specifically. This is a fair axis for a personal AI agent product, but no evidence documents a training-data control. Missing for 10: any documentation of a training opt-out setting, data-usage policy toggle, or explicit statement about whether conversations are used for model training.

   • [claimed-docs] “You can also use the Forget skill to have Muse forget information about specific topics or people.”
   • [claimed-docs] “Muse shows people a complete audit trail of everything it has done and plans to do.”

   proof ↗⚑ flag

   Poke—none0/10

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

   ⚑ flag