Grok vs Muse

Agent access

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

   weight 3 · round to Grok
   Grok✓fullclaimed7/10

   xAI docs explicitly describe adding custom MCP connectors and tunneling a local MCP server so Grok can reach it and use its tools, alongside built-in OAuth connectors for other tools (grok-docs-2, grok-docs-3, grok-docs-38, grok-docs-19). Missing for 10: independent/hands-on confirmation that custom MCP tool-calling works reliably in practice, and more detail on protocol/version compatibility.

   • [claimed-docs] “Expose any internal API, database, or SaaS tool to Grok. Define your own tools with custom schemas and logic.”
   • [claimed-docs] “A tunneling service solves this by exposing your local server through a public URL that Grok can connect to.”
   • [claimed-docs] “When you add a custom MCP connector, Grok's servers need to reach your MCP server over the public internet.”
   • [claimed-docs] “Built-in connectors are maintained by xAI and integrate natively with Grok. Each one authenticates via OAuth, so you connect once and Grok c…”

   proof ↗⚑ flag

   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

2. ai-native userUse an official CLI

   weight 2 · round to Grok
   Grok~partialcommunity3/10

   There's no official CLI documentation for Grok, but a community comment references a terminal-based interface for 'Grok Build' ('terminal is nice but codex desktop app is very useful'), suggesting some CLI-like coding tool exists even though it isn't documented in the official docs pack. missing for 10: official CLI documentation/reference, installation instructions, and command examples confirming a first-party CLI product.

   • [community] “still waiting for a proper gui for grok build - terminal is nice but codex desktop app is very useful”
   • [claimed-docs] “Send a coding prompt to Grok Build (`grok-4.6`) and get a response.”

   proof ↗⚑ flag

   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

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

   weight 3 · round to Grok
   Grok✓fullprobed9/10

   xAI publishes a full public REST API with documented endpoints for text, image, video, tool use, structured outputs, and an OpenAPI spec confirmed live by probe, plus a quickstart guide, satisfying the AI-native/agentic driving story. missing for 10: independent third-party benchmarking of API reliability/completeness beyond xAI's own docs and anecdotal community chatter about tool-calling quirks.

   • [claimed-docs] “Generate text, have conversations, use tools, and build AI-powered applications.”
   • [claimed-docs] “Send a coding prompt to Grok Build (`grok-4.6`) and get a response.”
   • [claimed-docs] “Expose any internal API, database, or SaaS tool to Grok. Define your own tools with custom schemas and logic.”
   • [claimed-docs] “Structured Outputs lets the API return responses in a specific format, for example, a JSON object matching a schema you define”
   • [claimed-docs] “Streaming outputs is **supported by all models with text output capability**”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.x.ai/openapi.json — contains "openapi" key”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.x.ai/llms.txt # SpaceXAI API Documentation > Official SpaceXAI (xAI) developer documentation at ht…”

   proof ↗⚑ flag

   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

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

   weight 2 · round drawn
   Grok—none0/10

   The xAI API is a developer product with API keys, so scoped/least-privilege credential issuance is a fair capability to expect, but the evidence pack contains no mention of API key scopes, roles, granular permissions, or least-privilege credential controls — only OAuth-based connector authentication (grok-docs-19) for built-in tools, which is about connecting Grok to external services, not issuing scoped agent credentials.

   • [claimed-docs] “Built-in connectors are maintained by xAI and integrate natively with Grok. Each one authenticates via OAuth, so you connect once and Grok c…”
   • [claimed-docs] “Expose any internal API, database, or SaaS tool to Grok. Define your own tools with custom schemas and logic.”

   proof ↗⚑ flag

   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

5. ai-native userBuild against official SDKs

   weight 2 · round to Grok
   Grok~partialprobed3/10

   The evidence shows an official xAI developer API with a published OpenAPI spec, quickstart docs, and text-generation/tool-use guides (grok-docs-20, grok-docs-27, grok-probe-3), which implies programmatic access an AI-native builder could use, but none of the evidence explicitly names or documents an official SDK (e.g., Python/JS client library) as opposed to raw REST/OpenAPI usage. Missing for 10: explicit documentation of a first-party SDK package, install instructions, or code samples showing SDK usage, plus any independent/community confirmation of SDK quality or adoption.

   • [claimed-docs] “Generate text, have conversations, use tools, and build AI-powered applications.”
   • [claimed-docs] “Send a coding prompt to Grok Build (`grok-4.6`) and get a response.”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.x.ai/openapi.json — contains "openapi" key”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.x.ai/llms.txt # SpaceXAI API Documentation > Official SpaceXAI (xAI) developer documentation at ht…”

   proof ↗⚑ flag

   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

6. ai-native userSubscribe to events via webhooks

   weight 2 · round drawn
   Grok—none0/10

   No evidence of any webhook subscription mechanism for Grok events; the docs describe connectors, tools, image/video generation, and inbound MCP tunneling, but nothing about outbound event notifications or webhook endpoints. Missing for 10: any webhook subscription API, event types, or delivery/registration mechanism.

   ⚑ flag

   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

Agentic features

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

   weight 2 · round to Grok
   Grok~partialcommunity6/10

   Grok's connectors (Gmail/Calendar, Google Drive, Microsoft Teams, Salesforce, custom APIs/MCP) let it read and act on a user's own data inside the chat, and features like Realtime Multi-agent Research suggest Grok can analyze and synthesize that data into insights. However, the evidence is mostly first-party docs describing data access rather than concrete examples of proactive 'insights and suggestions,' and one hands-on report notes Grok has 'real trouble with agentic tool calling,' undercutting confidence in reliable in-context analysis. Missing for 10: independent hands-on demonstration of Grok surfacing unprompted insights/suggestions from connected data, and confirmation that tool-calling reliability issues don't undermine this in practice.

   • [claimed-docs] “Connect your tools so Grok can reach your email, files, and calendar right inside a chat.”
   • [claimed-docs] “Built-in connectors are maintained by xAI and integrate natively with Grok. Each one authenticates via OAuth, so you connect once and Grok c…”
   • [claimed-docs] “Search emails using Gmail search operators (`from:`, `to:`, `subject:`, `newer_than:`, `has:attachment`, etc.).”
   • [claimed-docs] “The Google Drive connector lets Grok search, read, and manage files in your Google Drive.”
   • [claimed-docs] “Search across channels and chats, read messages, send new messages, reply to threads, and create chats — all without leaving Grok.”
   • [claimed-docs] “Realtime Multi-agent Research enables Grok to orchestrate multiple AI agents that work together in real time to perform deep, multi-step res…”
   • [community] “I experimented with Grok 4 for openclaw... It was more verbally fluid than 5.5, but had real trouble with agentic tool calling - the model f…”

   proof ↗⚑ flag

   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

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

   weight 2 · round to Grok
   Grok~partialclaimed4/10

   Grok Bot is described as an AI teammate running on a 'persistent cloud computer' and Grok supports multi-agent orchestration for research tasks, hinting at some background/autonomous agent capability, but there is no documentation of scheduling, triggers, or recurring/timed automation setup. Missing for 10: explicit scheduling/trigger mechanism, details on how automations run without user prompting, and independent confirmation of autonomous background execution.

   • [claimed-docs] “Grok Bot — hand real work to AI teammates on a persistent cloud computer.”
   • [claimed-docs] “Realtime Multi-agent Research enables Grok to orchestrate multiple AI agents that work together in real time to perform deep, multi-step res…”

   proof ↗⚑ flag

   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

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

   weight 3 · round to Muse
   Grok!disputedcontradicted6/10

   xAI docs describe strong built-in agentic delegation — Grok Bot hands work to 'AI teammates on a persistent cloud computer,' Realtime Multi-agent Research orchestrates multiple agents for research tasks, and connectors let Grok act on email/calendar/Salesforce from chat (grok-docs-15, grok-docs-26, grok-docs-11, grok-docs-16, grok-docs-19). However, hands-on community testing directly contradicts smooth agentic delegation: a user reports Grok 'had real trouble with agentic tool calling - the model felt like it hadn't been trained to think of tool calling as one of its primary modalities' (grok-comm-6), and another notes the lack of a proper GUI for Grok Build limiting usability (grok-comm-7). Missing for 10: independent verification that Grok Bot/multi-agent research reliably completes delegated tasks end-to-end, and resolution of the reported tool-calling weakness.

   • [claimed-docs] “Grok Bot — hand real work to AI teammates on a persistent cloud computer.”
   • [claimed-docs] “Realtime Multi-agent Research enables Grok to orchestrate multiple AI agents that work together in real time to perform deep, multi-step res…”
   • [claimed-docs] “Connect your tools so Grok can reach your email, files, and calendar right inside a chat.”
   • [claimed-docs] “Create new records - Add Leads, Opportunities, Accounts, Cases, or records on custom objects directly from chat.”
   • [claimed-docs] “Built-in connectors are maintained by xAI and integrate natively with Grok. Each one authenticates via OAuth, so you connect once and Grok c…”
   • [community] “I experimented with Grok 4 for openclaw... It was more verbally fluid than 5.5, but had real trouble with agentic tool calling - the model f…”
   • [community] “still waiting for a proper gui for grok build - terminal is nice but codex desktop app is very useful”

   proof ↗⚑ flag

   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

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

   weight 2 · round to Muse
   Grok~partialcommunity6/10

   Grok's docs describe a chat/voice interface where natural-language input drives text generation, image/video creation, and connector actions like creating Salesforce records or searching email 'directly from chat' (grok-docs-11, grok-docs-16, grok-docs-35, grok-docs-40), which is core evidence for NL-command operation. However, hands-on community testing reports real trouble with agentic tool calling, saying the model 'hadn't been trained to think of tool calling as one of its primary modalities' (grok-comm-6), which tempers confidence that NL commands reliably trigger tool/connector actions. Missing for 10: independent benchmarks or user reports specifically confirming reliable NL-to-action execution across the built-in connectors, and no clear resolution of the tool-calling reliability concern.

   • [claimed-docs] “Connect your tools so Grok can reach your email, files, and calendar right inside a chat.”
   • [claimed-docs] “Create new records - Add Leads, Opportunities, Accounts, Cases, or records on custom objects directly from chat.”
   • [claimed-docs] “Search emails using Gmail search operators (`from:`, `to:`, `subject:`, `newer_than:`, `has:attachment`, etc.).”
   • [claimed-docs] “Talk to Grok hands-free with voice.”
   • [claimed-docs] “Built-in connectors are maintained by xAI and integrate natively with Grok. Each one authenticates via OAuth, so you connect once and Grok c…”
   • [community] “I experimented with Grok 4 for openclaw... It was more verbally fluid than 5.5, but had real trouble with agentic tool calling - the model f…”

   proof ↗⚑ flag

   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

Api quality

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

   weight 2 · round to Grok
   Grok✓fullprobed9/10

   A direct probe confirms https://docs.x.ai/openapi.json returns HTTP 200 and contains an 'openapi' key, i.e., a downloadable, machine-readable OpenAPI spec for the xAI API, and this is corroborated by extensive first-party API docs describing the full endpoint surface (text, images, video, tools). Missing for 10: independent/community confirmation that developers actually consume this spec (e.g., via SDK codegen) beyond the automated probe.

   • [probe] “PROBE openapi: HTTP 200 at https://docs.x.ai/openapi.json — contains "openapi" key”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.x.ai/llms.txt # SpaceXAI API Documentation > Official SpaceXAI (xAI) developer documentation at ht…”
   • [claimed-docs] “Generate text, have conversations, use tools, and build AI-powered applications.”

   proof ↗⚑ flag

   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

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 Grok
   Grok~partialcommunity6/10

   Docs describe 'Grok Bot' as handing 'real work to AI teammates on a persistent cloud computer' and a 'Realtime Multi-agent Research' feature that orchestrates multi-step research autonomously, directly matching the story's core idea of background delegation and review. However, evidence is vendor-doc only with no independent confirmation of the async review workflow (notifications, task state, resuming), and community feedback (grok-comm-6) notes real trouble with agentic tool calling, suggesting reliability caveats. Missing for 10: independent hands-on validation of the background-task lifecycle, detail on how results are surfaced for review, and confirmation tool-calling reliability issues don't undermine multi-step autonomy.

   • [claimed-docs] “Grok Bot — hand real work to AI teammates on a persistent cloud computer.”
   • [claimed-docs] “Realtime Multi-agent Research enables Grok to orchestrate multiple AI agents that work together in real time to perform deep, multi-step res…”
   • [community] “I experimented with Grok 4 for openclaw... It was more verbally fluid than 5.5, but had real trouble with agentic tool calling - the model f…”
   • [claimed-docs] “Generate text, have conversations, use tools, and build AI-powered applications.”

   proof ↗⚑ flag

   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

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

   weight 3 · round drawn
   Grok—none0/10

   The evidence shows connectors for APIs, email, calendar, Salesforce, and a vague 'Grok Bot' cloud computer teammate, but nothing documents Grok actually driving a web browser to navigate sites or complete tasks (no browsing/computer-use agent feature is described). Multi-agent research (grok-docs-26) is about research orchestration, not website interaction, so this applicable-but-unevidenced capability is 'none'.

   • [claimed-docs] “Grok Bot — hand real work to AI teammates on a persistent cloud computer.”
   • [claimed-docs] “Built-in connectors are maintained by xAI and integrate natively with Grok. Each one authenticates via OAuth, so you connect once and Grok c…”
   • [claimed-docs] “Realtime Multi-agent Research enables Grok to orchestrate multiple AI agents that work together in real time to perform deep, multi-step res…”

   proof ↗⚑ flag

   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

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

   weight 2 · round to Muse
   Grok—none0/10

   Grok offers connectors (Gmail, Drive, Teams, Salesforce, custom MCP) and a 'Grok Bot' that operates on a persistent *cloud* computer, but there is no evidence of Grok seeing or controlling applications running on the user's own local machine/desktop (e.g., screen/GUI control akin to computer-use agents). Missing for 10: any documented local-computer screen/GUI control, first-party or hands-on evidence of operating a user's own desktop apps.

   • [claimed-docs] “Grok Bot — hand real work to AI teammates on a persistent cloud computer.”
   • [claimed-docs] “Connect your tools so Grok can reach your email, files, and calendar right inside a chat.”
   • [claimed-docs] “Built-in connectors are maintained by xAI and integrate natively with Grok. Each one authenticates via OAuth, so you connect once and Grok c…”
   • [claimed-docs] “When you add a custom MCP connector, Grok's servers need to reach your MCP server over the public internet.”

   proof ↗⚑ flag

   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

Tasks

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

   weight 2 · round to Muse
   Grok—none0/10

   The evidence pack shows connectors, tool integrations, and a 'Grok Bot' persistent cloud agent for handing off work, but no mention of scheduling recurring or one-off tasks that run automatically and report back results.

   ⚑ flag

   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

Apps

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

   weight 2 · round drawn
   Grok—none0/10

   The evidence pack shows only cross-platform sign-in sync and hands-free voice, but no mention of an official desktop app with OS-level shortcuts or screen-reading/access capability; a community comment even notes the lack of a proper GUI for Grok's coding product ('still waiting for a proper gui for grok build ... codex desktop app is very useful'), suggesting no such desktop tool exists.

   • [claimed-docs] “Sign in once and your conversations, settings, and subscription stay in sync across every platform.”
   • [claimed-docs] “Talk to Grok hands-free with voice.”
   • [community] “still waiting for a proper gui for grok build - terminal is nice but codex desktop app is very useful”

   proof ↗⚑ flag

   Muse—none0/10

   Evidence describes Muse as an AI agent with its own computer/file system, chat, and permission tracking, but there is no mention of an official desktop app, OS-level keyboard shortcuts, or screen access/observation capability. This appears to be a mobile/app-based assistant rather than a desktop tool with screen access.

   ⚑ flag

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

   weight 2 · round drawn
   Grok~partialclaimed4/10

   Docs mention voice mode ('Talk to Grok hands-free with voice') and cross-platform sync of conversations/settings/subscriptions, implying mobile app support, but there is no explicit confirmation of dedicated full-featured iOS and Android apps, no app-store links, and no community/hands-on feedback about mobile app quality or feature parity with desktop/web. Missing for 10: explicit iOS/Android app documentation, feature-parity details, and independent user reviews of the mobile apps themselves.

   • [claimed-docs] “Talk to Grok hands-free with voice.”
   • [claimed-docs] “Sign in once and your conversations, settings, and subscription stay in sync across every platform.”

   proof ↗⚑ flag

   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

Custom bots

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

   weight 2 · round drawn
   Grok—none0/10

   The evidence pack covers connectors, tool integrations, MCP, image/video generation, and enterprise features, but there is no mention of a feature to create and share custom assistants/personas with their own instructions and knowledge base (akin to OpenAI's GPTs or Claude Projects).

   ⚑ flag

   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

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

   weight 2 · round to Grok
   Grok~partialclaimed4/10

   The docs mention batch generation of multiple images and support for up to 5 source images in a single edit, which is a narrow form of bulk operation, but there's no evidence of general-purpose bulk operations (e.g., bulk file processing, bulk record updates, batch text API) across many items or arbitrary data types. Missing for 10: a true batch/bulk API for text or file processing, bulk actions on connector data (e.g., mass email/calendar updates), and independent confirmation that these batch features work reliably at scale.

   • [claimed-docs] “Generate images from text prompts with Grok Imagine models. The API supports batch generation of multiple images, and control over aspect ra…”
   • [claimed-docs] “Image editing now accepts up to 5 source images per request (was 3).”
   • [claimed-docs] “Use up to five source images for a single image edit.”

   proof ↗⚑ flag

   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

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

   weight 3 · round drawn
   Grok—none0/10

   Grok's docs describe connectors, tool integrations, and a persistent 'Grok Bot' cloud agent, but nothing describes user-defined rules that trigger actions automatically on external events (e.g., webhooks, triggers, if-this-then-that automations, or scheduled event listeners). The axis is plausible for an AI-native product with tool/connector access, so this is 'none' rather than 'na'.

   • [claimed-docs] “Grok Bot — hand real work to AI teammates on a persistent cloud computer.”
   • [claimed-docs] “Built-in connectors are maintained by xAI and integrate natively with Grok. Each one authenticates via OAuth, so you connect once and Grok c…”
   • [claimed-docs] “Expose any internal API, database, or SaaS tool to Grok. Define your own tools with custom schemas and logic.”

   proof ↗⚑ flag

   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

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round drawn
   Grok—none0/10

   No evidence of scheduling, cron-like recurrence, or persistent recurring workflow features anywhere in the docs; Grok Bot ('persistent cloud computer') and connectors describe on-demand agents/tools, not scheduled recurring jobs.

   ⚑ flag

   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

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

   weight 1 · round to Muse
   Grok—none0/10

   No evidence describes any versioning, review, diffing, or rollback mechanism for automations/agents/connectors built with Grok; the docs cover connectors, generation capabilities, and workspace management but nothing about tracking or reverting automation history.

   ⚑ flag

   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

Connectors

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

   weight 2 · round to Grok
   Grok~partialclaimed6/10

   Docs show Grok exposes a set of built-in, OAuth-authenticated connectors (Salesforce, Gmail, Google Calendar, Google Drive, Microsoft Teams) plus custom/MCP connectors that a user can add to reach external tools (grok-docs-16,19,35,36,37,2,3). This matches the 'add third-party apps/connectors' part of the story, but there's no explicit evidence of a browsable directory/marketplace UI, ratings, or a curated catalog page for discovering connectors. missing for 10: a documented directory/marketplace UI for browsing connectors, independent user confirmation of the browse experience.

   • [claimed-docs] “Built-in connectors are maintained by xAI and integrate natively with Grok. Each one authenticates via OAuth, so you connect once and Grok c…”
   • [claimed-docs] “Create new records - Add Leads, Opportunities, Accounts, Cases, or records on custom objects directly from chat.”
   • [claimed-docs] “Search emails using Gmail search operators (`from:`, `to:`, `subject:`, `newer_than:`, `has:attachment`, etc.).”
   • [claimed-docs] “The Google Drive connector lets Grok search, read, and manage files in your Google Drive.”
   • [claimed-docs] “Search across channels and chats, read messages, send new messages, reply to threads, and create chats — all without leaving Grok.”
   • [claimed-docs] “Expose any internal API, database, or SaaS tool to Grok. Define your own tools with custom schemas and logic.”
   • [claimed-docs] “A tunneling service solves this by exposing your local server through a public URL that Grok can connect to.”

   proof ↗⚑ flag

   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

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

   weight 3 · round to Grok
   Grok✓fullclaimed8/10

   Grok docs explicitly describe built-in OAuth connectors for Gmail, Google Calendar, and Google Drive that let it search emails, read files, and manage calendar items right inside chat, plus a broader connectors framework for other SaaS tools. This directly matches the story of connecting cloud drive, email, and calendar for search/use in answers. Missing for 10: independent/hands-on confirmation of these specific connectors working reliably in practice (community evidence largely covers coding/chat quality, not connector behavior).

   • [claimed-docs] “Connect your tools so Grok can reach your email, files, and calendar right inside a chat.”
   • [claimed-docs] “Built-in connectors are maintained by xAI and integrate natively with Grok. Each one authenticates via OAuth, so you connect once and Grok c…”
   • [claimed-docs] “Search emails using Gmail search operators (`from:`, `to:`, `subject:`, `newer_than:`, `has:attachment`, etc.).”
   • [claimed-docs] “The Google Drive connector lets Grok search, read, and manage files in your Google Drive.”

   proof ↗⚑ flag

   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

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 Muse
   Grok—none0/10

   The evidence describes Grok's coding assistant (Grok Build), connectors for email/calendar/files, image/video generation, and multi-agent research, but nothing documents a code-interpreter style capability where Grok writes and executes code against user-supplied data to produce charts, computed answers, or downloadable output files. Community comments discuss coding quality and agentic tool-calling issues but not this specific data-analysis/file-output workflow.

   • [claimed-docs] “Send a coding prompt to Grok Build (`grok-4.6`) and get a response.”
   • [claimed-docs] “Connect your tools so Grok can reach your email, files, and calendar right inside a chat.”
   • [claimed-docs] “The Google Drive connector lets Grok search, read, and manage files in your Google Drive.”
   • [community] “I experimented with Grok 4 for openclaw... It was more verbally fluid than 5.5, but had real trouble with agentic tool calling - the model f…”

   proof ↗⚑ flag

   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

Artifacts

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

   weight 2 · round drawn
   Grok—none0/10

   The evidence pack shows Grok connectors for reading/searching Google Drive, Gmail, Calendar, and Salesforce, plus image/video generation and coding via Grok Build, but nothing describes a document/presentation authoring or iterative-editing feature (e.g., a canvas-style doc editor) with export to file formats like Word/PowerPoint/PDF.

   • [claimed-docs] “The Google Drive connector lets Grok search, read, and manage files in your Google Drive.”
   • [claimed-docs] “Grok Bot — hand real work to AI teammates on a persistent cloud computer.”
   • [claimed-docs] “Send a coding prompt to Grok Build (`grok-4.6`) and get a response.”
   • [claimed-docs] “Connect your tools so Grok can reach your email, files, and calendar right inside a chat.”

   proof ↗⚑ flag

   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

Files

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

   weight 3 · round to Grok
   Grok~partialclaimed5/10

   Docs show Grok can ingest images and connect to Google Drive/Gmail to search and read files, and boasts a 500k context window for knowledge work, implying some document handling, but there is no explicit documentation of native PDF or spreadsheet upload/parsing in the core chat UI, nor any accuracy benchmarks or hands-on validation of document analysis. Missing for 10: explicit PDF/spreadsheet upload feature docs, accuracy testing/validation, independent user reports confirming reliable document analysis.

   • [claimed-docs] “Grok 4.6, SpaceXAI's frontier model for coding, agentic tasks, and knowledge work, is now available on the xAI API. It has a 500k context wi…”
   • [claimed-docs] “Connect your tools so Grok can reach your email, files, and calendar right inside a chat.”
   • [claimed-docs] “Some models allow images in the input. The model will consider the image context when generating the response.”
   • [claimed-docs] “The Google Drive connector lets Grok search, read, and manage files in your Google Drive.”

   proof ↗⚑ flag

   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

Memory

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

   weight 3 · round to Muse
   Grok—none0/10

   The evidence pack shows conversation storage (grok-docs-21) and cross-device sync of conversations/settings (grok-docs-41), but nothing describing a memory feature that recalls relevant context from past chats and applies it to new, unrelated conversations. No docs or community reports confirm persistent cross-chat memory recall.

   ⚑ flag

   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

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

   weight 1 · round drawn
   Grok—none0/10

   No evidence pack items describe a settings feature for persistent custom instructions or personality/preference profiles that shape all future responses; only per-request system prompts, connectors, and server-side storage of past prompts/responses are documented.

   ⚑ flag

   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

Projects

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

   weight 2 · round to Muse
   Grok—none0/10

   The evidence describes team 'workspaces' for licensing, SSO, and sharing conversations among teammates, plus connectors for external tools, but there is no mention of a project/space construct that groups related chats and files together with shared custom instructions or context, unlike dedicated 'Projects' features in other chat products.

   • [claimed-docs] “In your team workspace, enjoy enterprise-grade privacy protections... Additionally, unlock the full capabilities of SuperGrok, including hig…”
   • [claimed-docs] “Share conversations only with team members who have active licenses.”
   • [claimed-docs] “Switch between workspaces to access team-specific features and ensure your conversations are protected under business plan terms.”
   • [claimed-docs] “Built-in connectors are maintained by xAI and integrate natively with Grok. Each one authenticates via OAuth, so you connect once and Grok c…”

   proof ↗⚑ flag

   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

Images

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

   weight 2 · round to Grok
   Grok✓fullclaimed9/10

   Grok Imagine and the API both explicitly support text-to-image generation and image editing (including multi-image edits up to 5 sources, aspect ratio control) with docs describing prompt-driven creation and editing directly relevant to knowledge-worker use. Missing for 10: independent hands-on community corroboration specifically of image generation/editing quality (community evidence pack focuses on coding/text/voice, not images).

   • [claimed-docs] “Create images and video with Grok Imagine.”
   • [claimed-docs] “Generate images from text prompts with Grok Imagine models. The API supports batch generation of multiple images, and control over aspect ra…”
   • [claimed-docs] “Edit an existing image by providing a source image along with your prompt. The model understands the image content and applies your requeste…”
   • [claimed-docs] “Use up to five source images for a single image edit.”
   • [claimed-docs] “Image editing now accepts up to 5 source images per request (was 3).”
   • [claimed-docs] “New aspect ratios. Image generation and editing accept 21:9 (cinematic widescreen) and 5:2 (wide banners).”
   • [claimed-docs] “Requests to the slug will be served by grok-imagine-image-2.0 with quality set to low, with no change to the request or response shape”

   proof ↗⚑ flag

   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

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

   weight 2 · round to Grok
   Grok✓fullclaimed7/10

   Docs confirm image understanding is a first-class capability: models accept image input and 'consider the image context when generating the response' (grok-docs-25), plus related image editing docs show the model 'understands the image content' (grok-docs-29). No independent hands-on report specifically tests screenshot/photo interpretation accuracy. missing for 10: independent/community corroboration of accuracy on real screenshots or photos, detail on multi-image or OCR-style interpretation limits.

   • [claimed-docs] “Some models allow images in the input. The model will consider the image context when generating the response.”
   • [claimed-docs] “Edit an existing image by providing a source image along with your prompt. The model understands the image content and applies your requeste…”
   • [claimed-docs] “Use up to five source images for a single image edit.”

   proof ↗⚑ flag

   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

Voice

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

   weight 2 · round to Grok
   Grok✓fullcommunity6/10

   xAI documents hands-free voice conversations directly in Grok ('Talk to Grok hands-free with voice') and separately documents real-time streaming speech-to-text with VAD tuning, indicating a live voice-conversation feature exists. However, missing for 10: independent/hands-on corroboration of voice conversation naturalness or latency, and no detail on turn-taking/interruption handling beyond the VAD parameter.

   • [claimed-docs] “Talk to Grok hands-free with voice.”
   • [claimed-docs] “Speech to Text now accepts a vad_threshold parameter (streaming query param and batch multipart field) to tune the voice-activity gate”
   • [community] “I am excited for the voice mode promised in 'a week' or so. ChatGPT Advanced Voice has been a big disappointment for me... If Grok 3 voice m…”

   proof ↗⚑ flag

   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

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

   weight 2 · round to Grok
   Grok~partialprobed5/10

   The xAI API exposes core Grok model capabilities (text, images, video, tools, structured outputs, multi-agent research, connectors) documented alongside an OpenAPI spec, so much of the UI functionality is API-accessible. However, UI-only features like Grok Bot persistent cloud computer, team workspace/SSO/billing management, and built-in OAuth connectors (Gmail, Calendar, Teams, Salesforce) appear tied to the consumer/business app rather than exposed as general API endpoints, and there's no evidence of full parity. Missing for 10: confirmation that workspace/team management, SSO, billing, and native connector orchestration are API-accessible rather than UI-exclusive, plus independent corroboration of full feature parity.

   • [claimed-docs] “Generate text, have conversations, use tools, and build AI-powered applications.”
   • [claimed-docs] “Expose any internal API, database, or SaaS tool to Grok. Define your own tools with custom schemas and logic.”
   • [claimed-docs] “Built-in connectors are maintained by xAI and integrate natively with Grok. Each one authenticates via OAuth, so you connect once and Grok c…”
   • [claimed-docs] “Grok Bot — hand real work to AI teammates on a persistent cloud computer.”
   • [claimed-docs] “Secure and streamline logins by integrating Single Sign-On (SSO) with your preferred Identity Provider (IdP).”
   • [claimed-docs] “Visit grok.com/?_s=billing while logged in to manage your billing directly from the website (change plan, update payment, or cancel).”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.x.ai/openapi.json — contains "openapi" key”

   proof ↗⚑ flag

   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

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

   weight 3 · round drawn
   Grok—none0/10

   No evidence pack item mentions any data export feature, open format (e.g., JSON/Markdown conversation export) or account data portability tool for Grok; documentation covers connectors, models, and billing but never data export/leave-with-your-data capability.

   ⚑ flag

   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

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

   weight 2 · round drawn
   Grok—none0/10

   The evidence pack contains only proprietary API/product documentation and community commentary; there is no mention of any open-source license, public source repository, or open-weights release for Grok. As a mainstream capability question applicable to AI products, absence of evidence yields 'none' rather than 'na'.

   ⚑ flag

   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

4. ai-native userSelf-host the core product

   weight 3 · round drawn
   Grok—none0/10

   Grok is a closed, proprietary API/cloud service; no evidence anywhere in the pack of open-sourced weights or a self-hostable core model/product, only hosted APIs, connectors, and SaaS features. Absence of any self-hosting capability for an applicable axis (models can in principle be released for self-hosting, as some competitors do) yields none rather than na.

   • [claimed-docs] “Generate text, have conversations, use tools, and build AI-powered applications.”
   • [claimed-docs] “previous input prompts, reasoning content, and model responses are saved and stored on xAI's servers”
   • [claimed-docs] “Visit grok.com/?_s=billing while logged in to manage your billing directly from the website (change plan, update payment, or cancel).”

   proof ↗⚑ flag

   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

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

   weight 2 · round drawn
   Grok—none0/10

   No evidence in the pack mentions data residency, region selection, or storage location choices for Grok; docs only confirm data is stored on xAI's servers without any residency options (grok-docs-21). Missing for 10: any mention of regional data storage options, residency controls, or compliance certifications tied to geography.

   • [claimed-docs] “previous input prompts, reasoning content, and model responses are saved and stored on xAI's servers”

   proof ↗⚑ flag

   Muse—none0/10

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

   ⚑ flag

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

   weight 3 · round drawn
   Grok—none0/10

   The evidence pack documents data retention (prompts and responses stored on xAI's servers, grok-docs-21) and vague 'enterprise-grade privacy protections' for team workspaces (grok-docs-13), but nowhere mentions an opt-out toggle, training-data exclusion setting, or policy statement about excluding user conversations from model training. This axis clearly applies to a consumer/enterprise AI chat product, so absence of evidence yields 'none' rather than 'na'.

   • [claimed-docs] “previous input prompts, reasoning content, and model responses are saved and stored on xAI's servers”
   • [claimed-docs] “In your team workspace, enjoy enterprise-grade privacy protections... Additionally, unlock the full capabilities of SuperGrok, including hig…”
   • [claimed-docs] “Switch between workspaces to access team-specific features and ensure your conversations are protected under business plan terms.”

   proof ↗⚑ flag

   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

3. ai-native userControl data retention and deletion

   weight 2 · round to Muse
   Grok—none0/10

   Docs confirm that inputs, reasoning, and responses are stored on xAI's servers (grok-docs-21) and mention vague 'enterprise-grade privacy protections' for team workspaces (grok-docs-13), but there is no documented mechanism for users to view, control, or delete their stored data/conversation history. Missing for 10: explicit data retention settings, a user-facing deletion/export tool, and any policy detailing retention periods or opt-out controls.

   • [claimed-docs] “previous input prompts, reasoning content, and model responses are saved and stored on xAI's servers”
   • [claimed-docs] “In your team workspace, enjoy enterprise-grade privacy protections... Additionally, unlock the full capabilities of SuperGrok, including hig…”

   proof ↗⚑ flag

   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

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

   weight 2 · round drawn
   Grok—none0/10

   The evidence pack confirms xAI stores prompts, reasoning, and responses on its servers (grok-docs-21) but contains no documentation of any telemetry/usage-tracking opt-out setting, privacy toggle, or data-collection preference control for individual or ai-native users.

   • [claimed-docs] “previous input prompts, reasoning content, and model responses are saved and stored on xAI's servers”

   proof ↗⚑ flag

   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

Research

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

   weight 3 · round to Grok
   Grok~partialclaimed6/10

   Grok's docs describe a dedicated 'Realtime Multi-agent Research' capability that orchestrates multiple AI agents to perform deep, multi-step research tasks, matching the core of the story [grok-docs-26]. However, the docs don't explicitly describe the output format (a cited report with sources) and there is no independent/hands-on corroboration of this specific feature in the evidence pack. Missing for 10: explicit documentation of citation/report formatting in the research output, and independent user validation that the feature works as described.

   • [claimed-docs] “Realtime Multi-agent Research enables Grok to orchestrate multiple AI agents that work together in real time to perform deep, multi-step res…”

   proof ↗⚑ flag

   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

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

   weight 2 · round to Grok
   Grok~partialcommunity4/10

   Evidence shows Grok has a 'Realtime Multi-agent Research' capability for deep, multi-step research tasks and community notes suggest it can discuss current events from live X/web data, implying some grounding, but nothing in the pack explicitly documents inline citations or source links back to web results in Grok's answers. missing for 10: explicit documentation of citation formatting/source links, first-party description of real-time web search grounding, and independent verification that citations are reliably attached to responses.

   • [claimed-docs] “Realtime Multi-agent Research enables Grok to orchestrate multiple AI agents that work together in real time to perform deep, multi-step res…”
   • [community] “I am excited for the voice mode promised in 'a week' or so. ChatGPT Advanced Voice has been a big disappointment for me... If Grok 3 voice m…”

   proof ↗⚑ flag

   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

Data controls

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

   weight 1 · round drawn
   Grok—none0/10

   No evidence in the pack mentions a data export or account-data download feature for Grok; docs cover connectors, models, billing, SSO, and workspace features but never a 'export my chat history/data' capability. This is a fair trust-controls axis for a consumer chat product, so absence of evidence yields 'none' rather than 'na'.

   ⚑ flag

   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

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

   weight 3 · round drawn
   Grok—none0/10

   Docs mention 'enterprise-grade privacy protections' for team workspaces and that prompts are stored on xAI servers, but there is no documented setting or toggle letting a knowledge-worker control whether their conversations are used to train models. Community commentary raises general distrust but does not confirm or deny a specific training opt-out control.

   • [claimed-docs] “In your team workspace, enjoy enterprise-grade privacy protections... Additionally, unlock the full capabilities of SuperGrok, including hig…”
   • [claimed-docs] “previous input prompts, reasoning content, and model responses are saved and stored on xAI's servers”
   • [community] “Musk already has too much power, won't trust him with my AI conversations.”

   proof ↗⚑ flag

   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