Claude vs Martin

Agent access

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

   weight 2 · round to Martin
   Claude✓fullprobed7/10

   A probe confirms Claude's support site serves a working llms.txt (HTTP 200) listing topic links, and numerous individual documentation pages are available in clean .md format (e.g. claude-docs-1 through 63 all resolve as .md URLs), making the docs directly consumable by an agent. Missing for 10: confirmation that llms.txt/agent-readable docs exist on the main claude.com domain (only support.claude.com was probed), and independent/community evidence that agents actually consume these successfully rather than just first-party doc structure.

   • [probe] “PROBE llms.txt: HTTP 200 at https://support.claude.com/llms.txt # Claude Help Center > Search for answers or browse by topic ## English #…”
   • [claimed-docs] “You can prompt Claude to search through your previous conversations to find and reference relevant information in new chats.”
   • [claimed-docs] “This article explains how chat search and memory work, what Claude does and doesn’t remember, how to review and edit what’s saved, and how t…”
   • [probe] “PROBE docs-md: HTTP 404 at https://support.claude.com/en/.md”

   proof ↗⚑ flag

   Martin✓fullprobed9/10

   martin-probe-1 confirms a live llms.txt at docs.trymartin.com/llms.txt returning HTTP 200 with a structured index of docs, and the .md-suffixed doc URLs throughout the evidence pack (e.g. martin-docs-1 through martin-docs-24) show agent-oriented markdown documentation is directly accessible. Missing for 10: no independent/hands-on confirmation that an agent successfully consumed llms.txt to complete a task.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.trymartin.com/llms.txt # Martin ## Docs - [Introduction](https://docs.trymartin.com/introduction.…”
   • [claimed-docs] “Have Martin read, create, and update events in your calendar.”
   • [claimed-docs] “Martin is reachable through all your communication channels, including phone, SMS, WhatsApp, email, and Slack.”

   proof ↗⚑ flag

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

   weight 3 · round to Claude
   Claude✓fullprobed9/10

   Claude documents connecting to both remote MCP servers via custom connectors and installing local MCP servers on Claude Desktop as easily as browser extensions, plus a unified directory for finding/installing connectors, letting Claude use their tools. Missing for 10: independent/hands-on verification of MCP tool usage reliability beyond vendor docs.

   • [claimed-docs] “Build your own remote MCP servers to connect with any tool.”
   • [claimed-docs] “You can: Connect Claude to existing remote MCP servers. Build your own remote MCP servers to connect with any tool.”
   • [claimed-docs] “You can: - Connect Claude to existing remote MCP servers. - Build your own remote MCP servers to connect with any tool.”
   • [claimed-docs] “installing and managing local MCP servers has become significantly easier... install local MCP servers on your computer as easily as browser…”
   • [claimed-docs] “you can now install local MCP servers on your computer as easily as browser extensions”
   • [claimed-docs] “Our unified directory brings skills, connectors, and plugins together in one place so you can find and install everything that customizes Cl…”
   • [probe] “official MCP server documented at https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp”

   proof ↗⚑ flag

   Martin—none0/10

   Martin's docs describe a fixed set of built-in integrations (calendar, email, Slack, todos, notes) but there is no mention of MCP protocol support or any way for users to plug in arbitrary MCP servers for Martin to use as tools.

   • [claimed-docs] “Have Martin read, create, and update events in your calendar.”
   • [claimed-docs] “Have Martin read, draft, and reply to emails in your inbox.”
   • [claimed-docs] “Have Martin read and send messages in Slack from your account.”
   • [claimed-docs] “You can tell Martin to add, edit, and check off your to-dos on your behalf from any interface.”
   • [claimed-docs] “You can tell Martin to read, add, and edit your notes from any interface.”

   proof ↗⚑ flag

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

   weight 3 · round to Claude
   Claude~partialprobed3/10

   Evidence only hints at API-like surfaces (an Enterprise Compliance API for audit/chat data access, and references to using the Claude API/Console to power products) but never surfaces the actual general-purpose public API documentation for driving Claude's core capabilities; automated probes for an OpenAPI/swagger spec on the docs site returned 404s. Missing for 10: direct citation of the main Claude API reference docs, authentication/quickstart guides, and confirmation of comprehensive public API coverage beyond compliance/audit data.

   • [claimed-docs] “Audit logs: capture key information about user actions, system events, and data access. ... Compliance API: programmatically access Claude u…”
   • [claimed-docs] “Audit logs: capture key information about user actions, system events, and data access.”
   • [claimed-docs] “Enterprise includes everything in the Team plan, plus the following: - Security features to ensure the safety and compliance of your organiz…”
   • [claimed-docs] “You can use the prompt improver in the Claude Console to automatically adapt prompts that were originally written for other AI models.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.cl…”

   proof ↗⚑ flag

   Martin—none0/10

   Martin is a personal-assistant product controlled via chat/email/Slack/phone interfaces, but there is no evidence of a documented public API for developers to programmatically drive it — probes for OpenAPI/Swagger specs all returned 404. missing for 10: a documented public API, SDK, or endpoint reference; any developer-facing API authentication or usage docs.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.trymartin.com/openapi.json, https://docs.trymartin.com/swagger.json, https://docs.tryma…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Claude—none0/10

   No evidence describes scoped or least-privilege API credential issuance for agents; enterprise features mention audit logs and compliance API access but nothing about creating scoped/restricted API keys or credentials for agent use. Missing for 10: any documentation of API key scoping, permission tiers, or least-privilege credential management for agents.

   ⚑ flag

   Martin—none0/10

   Martin is a personal assistant that connects to full-access integrations (email, calendar, Slack) but there is no evidence of scoped or least-privilege credential issuance, API key management, or granular permissioning for agent access — no OpenAPI/API docs even exist per probe results.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.trymartin.com/openapi.json, https://docs.trymartin.com/swagger.json, https://docs.tryma…”
   • [claimed-docs] “Once connected, you can tell Martin to read, draft, and reply to emails on your behalf.”
   • [claimed-docs] “Once connected, you can tell Martin to read, send, and reply to Slack messages on your behalf.”

   proof ↗⚑ flag

5. ai-native userBuild against official SDKs

   weight 2 · round drawn
   Claude—none0/10

   The evidence pack covers Claude's consumer/enterprise features (Cowork, Projects, connectors, MCP, Chrome extension, file handling) but contains no documentation of official language SDKs (e.g., Python/TypeScript client libraries) for building applications against the Claude API. Missing for 10: any first-party SDK docs, API reference, or code samples showing programmatic API usage.

   ⚑ flag

   Martin—none0/10

   Martin's evidence pack covers only end-user integrations (calendar, email, Slack, etc.) and consumer interfaces, with no mention of an SDK, API, or developer library; probes for an OpenAPI/Swagger spec all returned 404s, indicating no public API/SDK surface exists to build against.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.trymartin.com/openapi.json, https://docs.trymartin.com/swagger.json, https://docs.tryma…”
   • [claimed-docs] “Martin is reachable through all your communication channels, including phone, SMS, WhatsApp, email, and Slack.”

   proof ↗⚑ flag

Agentic features

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

   weight 2 · round to Claude
   Claude✓fullclaimed8/10

   Claude can ingest user data (files, connectors to Gmail/Drive/Calendar, Projects knowledge bases) and generate AI-driven insights, analysis, visualizations, and reports directly from that data, including agentic multi-step research that synthesizes findings with citations. This is well documented across file analysis, Research mode, Cowork task automation, and artifact/document generation features. Missing for 10: independent hands-on benchmarking specifically validating insight quality/accuracy from user data (community evidence is mixed/general rather than about this specific data-insight capability).

   • [claimed-docs] “Claude can work with the following document types: - PDF - DOCX - CSV - TXT - HTML - ODT - RTF - EPUB - JSON - XLSX”
   • [claimed-docs] “Prompt Claude using natural language to generate Excel spreadsheets, PowerPoint presentations, Word documents, and PDF files that you can do…”
   • [claimed-docs] “Projects allow you to create self-contained workspaces with their own chat histories and knowledge bases.”
   • [claimed-docs] “With research, Claude delivers thorough answers in minutes, complete with easy-to-check citations so you can trust Claude's findings.”
   • [claimed-docs] “Research transforms how Claude finds and analyzes information. Claude operates agentically, conducting multiple searches that build on each …”
   • [claimed-docs] “Claude operates agentically, conducting multiple searches that build on each other while determining exactly what to investigate next.”
   • [claimed-docs] “produce reports with charts and visualizations, and generate presentations from your documents—all without specialized software skills”
   • [claimed-docs] “Connect your Gmail, Google Calendar, and Google Drive to Claude so you can search and send emails, manage your calendar, work with documents…”
   • [claimed-docs] “Files can be uploaded to individual chats or uploaded to a project's Files section for persistent reference across conversations.”

   proof ↗⚑ flag

   Martin~partialclaimed6/10

   Martin generates daily/weekly briefings synthesized from your calendar and inbox data, proactively drafts emails, and triages/labels emails with follow-up suggestions—all forms of AI-generated insights/suggestions surfaced inside the product. However, these are framed as autonomous actions rather than an explicit 'insights' or analytics layer, and there's no dedicated dashboard-style insight generation from broader personal data. Missing for 10: no independent/hands-on evidence corroborating quality of the 'insight' content itself, and no explicit analytics/trend-surfacing feature distinct from task-execution suggestions.

   • [claimed-docs] “Martin can send you daily or weekly briefings via email.”
   • [claimed-docs] “Martin can proactively draft emails for you and send them on your behalf.”
   • [claimed-docs] “Martin can automatically label your emails and take follow up actions on your behalf.”
   • [claimed-docs] “Martin syncs with multiple search engines to find you the most relevant information.”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Claude✓fullclaimed8/10

   Claude Cowork's scheduled tasks let users describe a task once and have Claude execute it autonomously on a recurring or on-demand basis, delivering finished outputs like reports and briefings without further user input, which directly matches background automation. Missing for 10: independent/hands-on verification of scheduled task reliability and no detail on failure handling or notification mechanisms.

   • [claimed-docs] “Instead of starting each task from scratch, you describe it once and Claude handles it on your schedule—delivering finished outputs like rep…”
   • [claimed-docs] “Scheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.”
   • [claimed-docs] “you describe it once and Claude handles it on your schedule—delivering finished outputs like reports, briefings, and summaries every time”
   • [claimed-docs] “With Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized resear…”
   • [claimed-docs] “Claude can take on complex, multi-step tasks and execute them on your behalf.”
   • [claimed-docs] “brings Claude Code's agentic capabilities to knowledge work beyond coding”

   proof ↗⚑ flag

   Martin✓fullcommunity8/10

   Martin's docs describe multiple always-on background automations—daily/weekly briefings, proactive email drafting, email triage, wake-up calls, cc-to-schedule meeting booking, and custom multi-step shortcuts—all of which run without direct user prompting, and community reports (e.g., using Martin as a persistent background agent for todos) corroborate real autonomous use. Missing for 10: independent verification of scheduling/configuration UI for these background jobs and long-term reliability data beyond one HN comment about failure rates improving.

   • [claimed-docs] “Create custom shortcuts that trigger multi-step actions.”
   • [claimed-docs] “Martin can send you daily or weekly briefings via email.”
   • [claimed-docs] “Martin can proactively draft emails for you and send them on your behalf.”
   • [claimed-docs] “Martin can automatically label your emails and take follow up actions on your behalf.”
   • [claimed-docs] “Martin can call you at a specific time every morning to wake you up with the weather and your schedule.”
   • [claimed-docs] “Cc Martin on an email to schedule a meeting.”
   • [community] “oh, martin desktop is finally here! I use Martin to manage my todo list while i'm coding (on an hourly basis) - having it aside VSC is so ha…”
   • [community] “A big piece of product feedback we got was 'I don't trust AI to take actions like sending texts/emails on my behalf if it's not 100% reliabl…”

   proof ↗⚑ flag

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

   weight 3 · round to Claude
   Claude✓fullclaimed9/10

   Claude's built-in Cowork feature explicitly lets users delegate multi-step tasks ('describe an outcome, step away, come back to finished work'), with agentic execution including browser/computer use, scheduling, and research that autonomously plans next steps. This is well-documented first-party functionality directly matching task delegation to a built-in assistant. Missing for 10: independent hands-on verification of Cowork's delegation reliability (community evidence covers Claude Code/coding use more than Cowork specifically).

   • [claimed-docs] “With Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized resear…”
   • [claimed-docs] “Instead of starting each task from scratch, you describe it once and Claude handles it on your schedule—delivering finished outputs like rep…”
   • [claimed-docs] “Claude can take on complex, multi-step tasks and execute them on your behalf.”
   • [claimed-docs] “Scheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.”
   • [claimed-docs] “brings Claude Code's agentic capabilities to knowledge work beyond coding”
   • [claimed-docs] “Research transforms how Claude finds and analyzes information. Claude operates agentically, conducting multiple searches that build on each …”
   • [claimed-docs] “Claude operates agentically, conducting multiple searches that build on each other while determining exactly what to investigate next.”

   proof ↗⚑ flag

   Martin✓fullcommunity8/10

   Martin IS the built-in AI assistant, and users delegate tasks to it across calendar, email, Slack, reminders, todos, notes, and multi-step shortcuts via chat, phone, SMS, email, or Slack, with hands-on community accounts confirming real task delegation and reliability improvements. missing for 10: independent quality/reliability benchmarking beyond anecdotal HN comments, and no evidence of failure-mode transparency or task-success metrics.

   • [claimed-docs] “Have Martin read, create, and update events in your calendar.”
   • [claimed-docs] “You can tell Martin to add, edit, and check off your to-dos on your behalf from any interface.”
   • [claimed-docs] “You can tell Martin to read, add, and edit your notes from any interface.”
   • [claimed-docs] “Create custom shortcuts that trigger multi-step actions.”
   • [claimed-docs] “Martin is reachable through all your communication channels, including phone, SMS, WhatsApp, email, and Slack.”
   • [community] “I’m impressed. I’ll probably cancel ChatGPT Pro subscription and switch to this... it’s handling some complicated requests correctly the fir…”
   • [community] “oh, martin desktop is finally here! I use Martin to manage my todo list while i'm coding (on an hourly basis) - having it aside VSC is so ha…”
   • [community] “A big piece of product feedback we got was 'I don't trust AI to take actions like sending texts/emails on my behalf if it's not 100% reliabl…”

   proof ↗⚑ flag

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

   weight 2 · round to Claude
   Claude✓fullcommunity9/10

   Claude's entire interface is natural-language chat/voice, and documentation shows this extends to agentic actions—generating files, browsing/clicking the web, using the computer, scheduling recurring tasks, and building artifacts—all triggered by describing the desired outcome in plain language (claude-docs-4,6,7,15,37,38,54). Community evidence corroborates real-world agentic use (claude-comm-1,10,12), though some report friction with CLI usability. Missing for 10: independent benchmark of NL command reliability across all surfaces, and no rebuttal to the CLI unresponsiveness anecdote being addressed.

   • [claimed-docs] “With Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized resear…”
   • [claimed-docs] “Claude opens sites, reads pages, clicks, types, and fills forms while you watch, with no need to switch windows.”
   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would.”
   • [claimed-docs] “Prompt Claude using natural language to generate Excel spreadsheets, PowerPoint presentations, Word documents, and PDF files that you can do…”
   • [claimed-docs] “Claude can take on complex, multi-step tasks and execute them on your behalf.”
   • [claimed-docs] “Scheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.”
   • [claimed-docs] “build tools, visualizations, and experiences by simply describing what you need”
   • [community] “I've been running Opus 4.8 for agentic coding and I don't see it being significantly better than Sonnet 4.5. I find that pairing Google Gemi…”
   • [community] “Anecdotal, but it 1 shot fixed a UI bug that neither Opus 4.5/Codex 5.2-high could fix.”
   • [community] “Claude is significantly better than other models at code assistant tasks, or at least in the way I use it.”

   proof ↗⚑ flag

   Martin✓fullcommunity8/10

   Martin is explicitly designed around natural-language commands across calendar, email, Slack, reminders, todos, notes, shortcuts, and phone/SMS interfaces, with docs and taglines like 'Text Jon my arrival time' or 'Cc Martin on an email to schedule a meeting' showing conversational control, and community feedback (HN) corroborates real usage of natural-language task delegation. missing for 10: independent hands-on benchmarking of NL command breadth/accuracy beyond anecdotal HN praise, and no formal API/spec confirming NLU robustness.

   • [claimed-docs] “Have Martin read, create, and update events in your calendar.”
   • [claimed-docs] “Tell Martin to remind you to do something, and he will ping you when the time comes.”
   • [claimed-docs] “You can tell Martin to add, edit, and check off your to-dos on your behalf from any interface.”
   • [claimed-docs] “Cc Martin on an email to schedule a meeting.”
   • [claimed-docs] “Text Jon my arrival time.”
   • [claimed-docs] “Martin is reachable through all your communication channels, including phone, SMS, WhatsApp, email, and Slack.”
   • [community] “I’m impressed. I’ll probably cancel ChatGPT Pro subscription and switch to this... it’s handling some complicated requests correctly the fir…”
   • [community] “oh, martin desktop is finally here! I use Martin to manage my todo list while i'm coding (on an hourly basis) - having it aside VSC is so ha…”

   proof ↗⚑ flag

Api quality

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

   weight 2 · round drawn
   Claude—none0/10

   This evidence pack is entirely about Claude's consumer/product features (Cowork, connectors, memory, artifacts, etc.); there is no evidence of an interactive API reference with runnable examples. The probe explicitly found no OpenAPI spec at the checked endpoints, and no docs page describing an interactive API playground is present.

   • [probe] “PROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.cl…”
   • [probe] “PROBE docs-md: HTTP 404 at https://support.claude.com/en/.md”

   proof ↗⚑ flag

   Martin—none0/10

   Martin is a personal assistant product with docs pages but no evidence of any interactive API reference or runnable examples; probes explicitly show no OpenAPI/swagger spec found at any candidate path. missing for 10: interactive API reference UI, runnable code examples, OpenAPI spec availability.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.trymartin.com/openapi.json, https://docs.trymartin.com/swagger.json, https://docs.tryma…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Claude—none0/10

   The evidence pack includes explicit probes checking for a machine-readable API spec (openapi.json, swagger.json, etc.) on Claude's support domain, all returning 404, and no docs item anywhere references an OpenAPI/Swagger spec or downloadable schema for the Claude API. Nothing in the docs list an API reference format for AI-native consumption.

   • [probe] “PROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.cl…”
   • [probe] “PROBE docs-md: HTTP 404 at https://support.claude.com/en/.md”

   proof ↗⚑ flag

   Martin—none0/10

   Martin is a personal assistant product, not a developer API platform, but the axis of publishing a machine-readable API spec still applies as a fair question; the probe explicitly checked all standard OpenAPI/swagger paths and found only 404s, with no evidence of any downloadable spec.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.trymartin.com/openapi.json, https://docs.trymartin.com/swagger.json, https://docs.tryma…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Claude—none0/10

   The evidence pack covers Claude's consumer features, connectors, Cowork, and MCP integrations, but contains no mention of API versioning schemes or a documented deprecation policy for any Claude/Anthropic API. Since Claude does expose developer-facing APIs (e.g., for Console, Claude Code, MCP), this axis is applicable, but no evidence supports it.

   ⚑ flag

   Martin—none0/10

   Martin is a personal-assistant product with no evidence of any public API, versioning scheme, or deprecation policy; the openapi probe returned 404 on all candidate paths and no docs mention API versioning. missing for 10: any public API reference, version numbers, changelog, deprecation policy documentation.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.trymartin.com/openapi.json, https://docs.trymartin.com/swagger.json, https://docs.tryma…”

   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 Claude
   Claude✓fullclaimed8/10

   Claude Cowork is documented as letting users describe a multi-step outcome, step away, and return to finished work, with scheduled/recurring tasks and background agentic execution (browser/computer use, file generation) explicitly designed for delegation and later review. Missing for 10: independent hands-on validation of Cowork's reliability/quality for complex delegated tasks and clearer detail on review/approval workflow beyond docs.

   • [claimed-docs] “With Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized resear…”
   • [claimed-docs] “Instead of starting each task from scratch, you describe it once and Claude handles it on your schedule—delivering finished outputs like rep…”
   • [claimed-docs] “Claude can take on complex, multi-step tasks and execute them on your behalf.”
   • [claimed-docs] “Scheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.”
   • [claimed-docs] “you describe it once and Claude handles it on your schedule—delivering finished outputs like reports, briefings, and summaries every time”
   • [claimed-docs] “This article explains how to use Claude Cowork, which brings Claude Code's agentic capabilities to knowledge work beyond coding.”
   • [claimed-docs] “Claude opens sites, reads pages, clicks, types, and fills forms while you watch, with no need to switch windows.”
   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would.”

   proof ↗⚑ flag

   Martin~partialcommunity7/10

   Martin's docs describe multiple background/autonomous capabilities (proactive email drafts, email triage with follow-up actions, cc-to-schedule meeting booking, custom multi-step shortcuts, daily briefings) that match delegating a task for autonomous background work with results delivered back to the user, and community posts corroborate real usage of the cloud-based agent for ongoing tasks (todos) across sessions. However, evidence doesn't clearly show a distinct 'review before finalizing' step for these autonomous actions (e.g., whether drafts are held for approval vs. auto-sent), and independent hands-on validation of the full delegate→work→review loop is thin. Missing for 10: explicit review/approval workflow evidence, and richer independent hands-on accounts of multi-step autonomous task completion.

   • [claimed-docs] “Create custom shortcuts that trigger multi-step actions.”
   • [claimed-docs] “Martin can send you daily or weekly briefings via email.”
   • [claimed-docs] “Martin can proactively draft emails for you and send them on your behalf.”
   • [claimed-docs] “Martin can automatically label your emails and take follow up actions on your behalf.”
   • [claimed-docs] “Cc Martin on an email to schedule a meeting.”
   • [community] “oh, martin desktop is finally here! I use Martin to manage my todo list while i'm coding (on an hourly basis) - having it aside VSC is so ha…”
   • [community] “A big piece of product feedback we got was 'I don't trust AI to take actions like sending texts/emails on my behalf if it's not 100% reliabl…”

   proof ↗⚑ flag

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

   weight 3 · round to Claude
   Claude✓fullclaimed8/10

   Claude has multiple documented browser-control capabilities: the built-in browser in Cowork that opens sites, reads pages, clicks, types, and fills forms autonomously (claude-docs-6/67), the Claude in Chrome extension that reads/clicks/navigates websites (claude-docs-63), and computer-use navigation for on-screen actions (claude-docs-7/22/59), enabling research and task completion on websites. Missing for 10: independent hands-on validation of browser-task success rates and reliability under real-world site complexity.

   • [claimed-docs] “Claude opens sites, reads pages, clicks, types, and fills forms while you watch, with no need to switch windows.”
   • [claimed-docs] “Claude opens sites, reads pages, clicks, types, and fills forms while you watch, with no need to swit”
   • [claimed-docs] “Claude in Chrome is a browser extension that allows Claude to read, click, and navigate websites alongside you.”
   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would.”
   • [claimed-docs] “When computer use is enabled and Claude doesn't have a connector or tool for what you need, it may navigate to your screen directly—clicking…”
   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would”
   • [claimed-docs] “Claude can take on complex, multi-step tasks and execute them on your behalf.”

   proof ↗⚑ flag

   Martin—none0/10

   Martin's documented capabilities cover calendar, email, Slack, notes, reminders, todos, and search-engine lookups, but nothing in the evidence describes it operating a web browser, navigating websites, or completing multi-step tasks on arbitrary sites on the user's behalf.

   • [claimed-docs] “Martin syncs with multiple search engines to find you the most relevant information.”
   • [claimed-docs] “Have Martin read, create, and update events in your calendar.”
   • [claimed-docs] “Have Martin read, draft, and reply to emails in your inbox.”
   • [claimed-docs] “Have Martin read and send messages in Slack from your account.”
   • [claimed-docs] “Martin is reachable through all your communication channels, including phone, SMS, WhatsApp, email, and Slack.”

   proof ↗⚑ flag

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

   weight 2 · round to Claude
   Claude✓fullclaimed8/10

   Claude Cowork/computer use lets Claude navigate directly to the user's screen—clicking, typing, opening apps, filling forms—while the user watches, plus a built-in browser for opening sites and interacting with pages, directly matching the story of operating applications to complete work. Community evidence corroborates agentic coding/task use though notes mixed quality perceptions unrelated to this specific capability. Missing for 10: independent hands-on verification of computer-use reliability/accuracy and broader third-party benchmarking beyond vendor docs.

   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would.”
   • [claimed-docs] “When computer use is enabled and Claude doesn't have a connector or tool for what you need, it may navigate to your screen directly—clicking…”
   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would”
   • [claimed-docs] “Claude opens sites, reads pages, clicks, types, and fills forms while you watch, with no need to switch windows.”
   • [claimed-docs] “Claude opens sites, reads pages, clicks, types, and fills forms while you watch, with no need to swit”
   • [claimed-docs] “With Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized resear…”
   • [claimed-docs] “Claude can take on complex, multi-step tasks and execute them on your behalf.”
   • [claimed-docs] “Claude in Chrome is a browser extension that allows Claude to read, click, and navigate websites alongside you.”

   proof ↗⚑ flag

   Martin~partialcommunity5/10

   Martin can act inside specific applications via integrations (calendar, email, Slack, notes, to-dos) rather than through general screen/GUI-level control of arbitrary desktop apps — it operates named services via API-like connections, not a computer-use style visual agent. A desktop app exists (martin-comm-4) but evidence only shows it syncing to-dos, not controlling arbitrary programs. Missing for 10: evidence of generic screen/vision-based computer control, ability to operate arbitrary (non-integrated) applications, and independent hands-on proof of this broader 'operate any app' capability.

   • [claimed-docs] “Have Martin read, create, and update events in your calendar.”
   • [claimed-docs] “Have Martin read, draft, and reply to emails in your inbox.”
   • [claimed-docs] “Have Martin read and send messages in Slack from your account.”
   • [claimed-docs] “You can tell Martin to read, add, and edit your notes from any interface.”
   • [community] “oh, martin desktop is finally here! I use Martin to manage my todo list while i'm coding (on an hourly basis) - having it aside VSC is so ha…”

   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 Claude
   Claude✓fullclaimed8/10

   Claude Cowork explicitly supports scheduled tasks that run on a recurring or one-off basis and deliver finished outputs like reports and summaries back to the user, matching the story closely. Missing for 10: independent/hands-on validation of scheduling reliability and no detail on notification/delivery mechanisms beyond docs.

   • [claimed-docs] “Scheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.”
   • [claimed-docs] “you describe it once and Claude handles it on your schedule—delivering finished outputs like reports, briefings, and summaries every time”
   • [claimed-docs] “Instead of starting each task from scratch, you describe it once and Claude handles it on your schedule—delivering finished outputs like rep…”
   • [claimed-docs] “With Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized resear…”
   • [claimed-docs] “Claude can take on complex, multi-step tasks and execute them on your behalf.”

   proof ↗⚑ flag

   Martin~partialcommunity6/10

   Martin supports recurring background tasks (daily/weekly briefings, wake-up calls, email triage) and one-off scheduled reminders that ping the user via chosen interface, matching the core of the story. However, there's no unified 'task scheduler' concept with arbitrary custom recurring workflows beyond the specific built-in background tasks listed, and no independent verification of reliability for scheduled/recurring runs. missing for 10: evidence of general-purpose custom recurring task scheduling (not just fixed briefings/wake-up-calls), independent hands-on confirmation of reminder/briefing reliability, and any dashboard/management UI for viewing scheduled tasks.

   • [claimed-docs] “Tell Martin to remind you to do something, and he will ping you when the time comes.”
   • [claimed-docs] “Martin can send you daily or weekly briefings via email.”
   • [claimed-docs] “Martin can automatically label your emails and take follow up actions on your behalf.”
   • [claimed-docs] “Martin can call you at a specific time every morning to wake you up with the weather and your schedule.”
   • [claimed-docs] “Tell Martin to remind you to do something, and he will ping you at the specified time, via the specified interface.”
   • [community] “A big piece of product feedback we got was 'I don't trust AI to take actions like sending texts/emails on my behalf if it's not 100% reliabl…”

   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 to Claude
   Claude~partialclaimed5/10

   Claude ships an official desktop app (Mac, Windows, Linux via apt) and a Cowork/computer-use feature that lets Claude 'navigate to your screen directly—clicking, typing, and opening apps' while the user watches, which shows real screen access. However there is no evidence of dedicated OS-level keyboard shortcuts (e.g., a global hotkey to invoke Claude with current screen context) — the screen access described is agentic task automation rather than a power-user shortcut workflow. Missing for 10: documented OS-level global shortcuts/hotkeys, and evidence that a user can quickly summon Claude to see the current screen via keypress rather than launching a Cowork/computer-use task.

   • [claimed-docs] “you can install Claude Desktop from Anthropic's apt repository rather than as a downloaded .deb file so that updates arrive through your sys…”
   • [claimed-docs] “The Claude desktop apps bring Claude's capabilities directly to your computer, allowing for seamless integration with your workflow.”
   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would.”
   • [claimed-docs] “When computer use is enabled and Claude doesn't have a connector or tool for what you need, it may navigate to your screen directly—clicking…”
   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would”
   • [claimed-docs] “This article explains how to use Claude Cowork, which brings Claude Code's agentic capabilities to knowledge work beyond coding.”

   proof ↗⚑ flag

   Martin—none0/10

   Community evidence confirms a Martin desktop app exists (martin-comm-4), and docs mention in-app 'shortcuts' for multi-step actions (martin-docs-7), but there is no evidence of OS-level global keyboard shortcuts or any capability for Martin to read/access what's on the user's screen. missing for 10: evidence of OS-level hotkey integration, evidence of screen-reading/context capture, any documentation describing desktop-native system integration beyond a generic app shell.

   • [community] “oh, martin desktop is finally here! I use Martin to manage my todo list while i'm coding (on an hourly basis) - having it aside VSC is so ha…”
   • [claimed-docs] “Create custom shortcuts that trigger multi-step actions.”

   proof ↗⚑ flag

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

   weight 2 · round to Claude
   Claude✓fullclaimed8/10

   Official iOS and Android apps are documented (App Store install instructions, Chrome/mobile chat parity across web/iOS/Android/desktop, voice mode explicitly available on Claude Mobile), indicating full-featured mobile apps rather than a bare wrapper. Missing for 10: no independent hands-on review of mobile app feature parity/quality, and no detail on which advanced features (Cowork, computer use) are available on mobile vs desktop-only.

   • [claimed-docs] “You can install the Claude app onto your iOS device by navigating to the App Store and searching for “Claude by Anthropic””
   • [claimed-docs] “You can install the Claude app onto your iOS device by navigating to the App Store and searching for "Claude by Anthropic"”
   • [claimed-docs] “Chat on web, iOS, Android, and on your desktop ... Memory across conversations”
   • [claimed-docs] “Chat on web, iOS, Android, and on your desktop”
   • [claimed-docs] “Voice mode is a beta feature available to all plans (Free, Pro, Max, Team, and Enterprise) on Claude Mobile (iOS and Android), Claude Deskto…”

   proof ↗⚑ flag

   Martin—none0/10

   Martin's docs describe channel-based access (phone, SMS, WhatsApp, email, Slack, desktop) but no evidence of dedicated, full-featured native iOS/Android apps; a community comment explicitly asks 'I would try this if it had Android support! Is that planned?' indicating no Android app exists, and no iOS app is mentioned anywhere.

   • [claimed-docs] “Martin is reachable through all your communication channels, including phone, SMS, WhatsApp, email, and Slack.”
   • [community] “oh, martin desktop is finally here! I use Martin to manage my todo list while i'm coding (on an hourly basis) - having it aside VSC is so ha…”
   • [community] “I would try this if it had Android support! Is that planned?”

   proof ↗⚑ flag

Custom bots

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

   weight 2 · round to Claude
   Claude~partialclaimed6/10

   Claude supports Projects (self-contained workspaces with custom knowledge bases/files) and Skills (teach Claude repeatable instructions like brand guidelines), which together let a power-user build a persona-like assistant with instructions and knowledge; Projects can be shared with team members. However, there's no dedicated 'custom GPT'-style public sharing/marketplace for assistants, and no independent evidence of end-to-end sharing outside an org. missing for 10: evidence of public/marketplace sharing of custom assistants, explicit persona/system-instruction configuration UI, and independent hands-on confirmation of building and sharing such assistants.

   • [claimed-docs] “Projects allow you to create self-contained workspaces with their own chat histories and knowledge bases.”
   • [claimed-docs] “whether that's creating documents with your company's brand guidelines, analyzing data using your organization's specific workflows”
   • [claimed-docs] “Skills teach Claude how to complete specific tasks in a repeatable way, whether that's creating documents with your company's brand guidelin…”
   • [claimed-docs] “Files can be uploaded to individual chats or uploaded to a project's Files section for persistent reference across conversations.”

   proof ↗⚑ flag

   Martin—none0/10

   Martin is a personal AI assistant with fixed integrations (calendar, email, Slack, todos, notes, reminders) and shortcuts, but there is no evidence of a feature to build a custom assistant with its own distinct instructions/persona and knowledge base, nor any sharing mechanism for such an assistant. missing for 10: custom assistant creation with configurable instructions/persona, custom knowledge base attachment, and sharing/publishing of a built assistant.

   ⚑ flag

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

   weight 2 · round to Martin
   Claude—none0/10

   The evidence pack documents agentic task automation (Cowork, scheduled tasks, Research) and single-document file handling, but no feature is described for processing or acting on many items at once (e.g., batch file processing, bulk edit across records, or a batch API). Automation-depth stories like this are plausible for Claude given its agentic tooling, but nothing in the pack shows bulk/multi-item operation support.

   ⚑ flag

   Martin~partialclaimed4/10

   Martin's docs show a few multi-item behaviors — e.g. forwarding an email with several events and having 'all of them' added to the calendar (martin-docs-23), and automatic email labeling/triage across an inbox (martin-docs-11) — which imply some batch-like processing, but there is no explicit bulk-operations feature (e.g. batch todo updates, mass note edits, multi-item scheduling command) described anywhere in the docs. missing for 10: explicit bulk-action tooling/API for operating on many items at once, first-party documentation of bulk operations, and independent confirmation of bulk-scale reliability.

   • [claimed-docs] “Got an email with events coming up? Forward it to Martin, and he'll add them all to your calendar.”
   • [claimed-docs] “Martin can automatically label your emails and take follow up actions on your behalf.”

   proof ↗⚑ flag

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

   weight 3 · round to Martin
   Claude~partialclaimed4/10

   Claude Cowork supports scheduled/recurring tasks that run automatically on a time-based schedule or on demand (claude-docs-38, claude-docs-58), which is a form of automation, but there's no evidence of user-defined rules triggered by external events (e.g., 'when an email arrives' or 'when a file changes, do X') as opposed to calendar/time-based scheduling. missing for 10: event-driven trigger conditions (webhooks, connector-based event listeners), a rules engine for conditional automation, and any documentation of non-time-based triggers.

   • [claimed-docs] “Scheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.”
   • [claimed-docs] “you describe it once and Claude handles it on your schedule—delivering finished outputs like reports, briefings, and summaries every time”
   • [claimed-docs] “Instead of starting each task from scratch, you describe it once and Claude handles it on your schedule—delivering finished outputs like rep…”
   • [claimed-docs] “Claude can take on complex, multi-step tasks and execute them on your behalf.”

   proof ↗⚑ flag

   Martin~partialclaimed6/10

   Martin ships several automatic, event-triggered behaviors (email triage that auto-labels and follows up, cc-to-schedule meeting creation, forwarded-email calendar parsing, proactive drafts, wake-up calls, briefings) which act like predefined automation rules, and 'custom shortcuts' let users define multi-step action sequences. However, there's no evidence of a general user-defined rule/trigger engine (e.g., 'if email from X arrives then do Y' configurable conditions) — the automations shown are fixed built-in behaviors rather than arbitrary user-authored event rules. Missing for 10: a documented custom rule/condition builder, evidence of arbitrary event-trigger definitions beyond built-in background tasks, and independent confirmation these automations fire reliably in practice.

   • [claimed-docs] “Create custom shortcuts that trigger multi-step actions.”
   • [claimed-docs] “Martin can automatically label your emails and take follow up actions on your behalf.”
   • [claimed-docs] “Cc Martin on an email to schedule a meeting.”
   • [claimed-docs] “Martin can proactively draft emails for you and send them on your behalf.”
   • [claimed-docs] “Martin can call you at a specific time every morning to wake you up with the weather and your schedule.”
   • [claimed-docs] “Got an email with events coming up? Forward it to Martin, and he'll add them all to your calendar.”

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round to Claude
   Claude✓fullclaimed8/10

   Claude Cowork explicitly supports scheduled recurring tasks, letting users describe a workflow once and have Claude execute it automatically on a recurring or on-demand basis, delivering outputs like reports and briefings — this directly matches the story. Missing for 10: independent/hands-on verification of scheduling reliability and details on scheduling granularity/limits beyond vendor docs.

   • [claimed-docs] “Instead of starting each task from scratch, you describe it once and Claude handles it on your schedule—delivering finished outputs like rep…”
   • [claimed-docs] “Scheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.”
   • [claimed-docs] “you describe it once and Claude handles it on your schedule—delivering finished outputs like reports, briefings, and summaries every time”
   • [claimed-docs] “With Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized resear…”

   proof ↗⚑ flag

   Martin~partialclaimed6/10

   Martin ships several built-in recurring background jobs — daily/weekly briefings, daily wake-up calls, and automatic email triage — which are documented recurring workflows, and shortcuts allow custom multi-step actions. However, there's no evidence of a general-purpose, user-defined recurring job scheduler (e.g., custom cadence for arbitrary tasks/workflows beyond the fixed built-in recurring features). Missing for 10: user-configurable custom recurring schedules beyond the fixed briefing/wake-up-call cadence, and independent confirmation these recurring jobs run reliably at scale.

   • [claimed-docs] “Martin can send you daily or weekly briefings via email.”
   • [claimed-docs] “Martin can call you at a specific time every morning to wake you up with the weather and your schedule.”
   • [claimed-docs] “Martin can automatically label your emails and take follow up actions on your behalf.”
   • [claimed-docs] “Create custom shortcuts that trigger multi-step actions.”
   • [claimed-docs] “Tell Martin to remind you to do something, and he will ping you at the specified time, via the specified interface.”

   proof ↗⚑ flag

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

   weight 1 · round drawn
   Claude—none0/10

   No evidence describes versioning, reviewing, or rolling back automations like scheduled Cowork tasks or Skills; docs cover creating/scheduling tasks but not history, diffs, or rollback capability.

   ⚑ flag

   Martin—none0/10

   Martin is a personal assistant agent (email, calendar, reminders, shortcuts) with no evidence of version history, review workflows, or rollback for its automations/shortcuts; docs describe creating shortcuts but nothing about versioning or undoing them. Missing for 10: version history UI, review/approval workflow, rollback mechanism.

   • [claimed-docs] “Create custom shortcuts that trigger multi-step actions.”

   proof ↗⚑ flag

Connectors

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

   weight 2 · round to Claude
   Claude✓fullclaimed9/10

   Claude documents a unified directory that brings skills, connectors, and plugins together in one place to find and install everything that customizes Claude, plus specific connectors like Google Workspace and remote/local MCP servers to extend the assistant. Missing for 10: no independent hands-on review confirming the browsing/discovery UX of the directory itself.

   • [claimed-docs] “Our unified directory brings skills, connectors, and plugins together in one place so you can find and install everything that customizes Cl…”
   • [claimed-docs] “Our unified directory brings skills, connectors, and plugins together in one place so you can find and install everything that customizes Cl…”
   • [claimed-docs] “Connect your Gmail, Google Calendar, and Google Drive to Claude so you can search and send emails, manage your calendar, work with documents…”
   • [claimed-docs] “Connect your Gmail, Google Calendar, and Google Drive to Claude so you can search and send emails, manage your calendar, work with documents…”
   • [claimed-docs] “installing and managing local MCP servers has become significantly easier... install local MCP servers on your computer as easily as browser…”
   • [claimed-docs] “you can now install local MCP servers on your computer as easily as browser extensions”
   • [claimed-docs] “You can: Connect Claude to existing remote MCP servers. Build your own remote MCP servers to connect with any tool.”

   proof ↗⚑ flag

   Martin—none0/10

   Evidence shows Martin ships a small fixed set of first-party integrations (Calendar, Inbox, Slack) rather than a browsable directory/marketplace of third-party apps and connectors that a power-user can explore and add. No docs, UI, or community mentions describe an app directory or connector marketplace.

   • [claimed-docs] “Have Martin read, create, and update events in your calendar.”
   • [claimed-docs] “Have Martin read, draft, and reply to emails in your inbox.”
   • [claimed-docs] “Have Martin read and send messages in Slack from your account.”

   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 Claude
   Claude✓fullclaimed9/10

   Claude has a documented Google Workspace connector letting users connect Gmail, Google Calendar, and Google Drive so Claude can search emails, manage calendar, and work with documents/files directly in conversation, plus a privacy commitment not to train on this data. This directly satisfies the story's cloud drive/email/calendar connection use case. Missing for 10: no independent hands-on report corroborating real-world reliability of these specific connectors.

   • [claimed-docs] “Connect your Gmail, Google Calendar, and Google Drive to Claude so you can search and send emails, manage your calendar, work with documents…”
   • [claimed-docs] “Connect your Gmail, Google Calendar, and Google Drive to Claude so you can search and send emails, manage your calendar, work with documents…”
   • [claimed-docs] “We do not train our models on your Gmail, Drive, or Calendar connector data, ensuring your private information remains private.”
   • [claimed-docs] “Our unified directory brings skills, connectors, and plugins together in one place so you can find and install everything that customizes Cl…”

   proof ↗⚑ flag

   Martin~partialclaimed5/10

   Martin has well-documented calendar and email (inbox) integrations letting it read, draft, reply, and add events on the user's behalf, plus a general search capability across connected sources. However, no evidence mentions a cloud drive (e.g., Google Drive/Dropbox) connector, so the story's full connector set is only partially covered. missing for 10: cloud drive integration, independent verification that search actually spans all connected sources.

   • [claimed-docs] “Have Martin read, create, and update events in your calendar.”
   • [claimed-docs] “Have Martin read, draft, and reply to emails in your inbox.”
   • [claimed-docs] “Martin syncs with multiple search engines to find you the most relevant information.”
   • [claimed-docs] “Once connected, you can tell Martin to add an event to your calendar, and he will add it at the specified time with the specified details.”
   • [claimed-docs] “Once connected, you can tell Martin to read, draft, and reply to emails on your behalf.”
   • [claimed-docs] “Got an email with events coming up? Forward it to Martin, and he'll add them all to your calendar.”

   proof ↗⚑ flag

Files

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

   weight 3 · round to Claude
   Claude✓fullclaimed9/10

   Docs confirm Claude supports uploading PDFs, DOCX, CSV, XLSX, TXT, HTML, ODT, RTF, EPUB, JSON, with analysis of both text and visual elements in PDFs up to 100 pages, plus persistent Project file storage for cross-conversation reference and generation of derived documents/reports. Missing for 10: independent hands-on benchmarking of analysis accuracy across large/complex spreadsheets or long PDFs beyond the 100-page limit.

   • [claimed-docs] “Claude can work with the following document types: - PDF - DOCX - CSV - TXT - HTML - ODT - RTF - EPUB - JSON - XLSX”
   • [claimed-docs] “Claude can work with the following document types: PDF DOCX CSV TXT HTML ODT RTF EPUB JSON XLSX”
   • [claimed-docs] “Claude analyzes both text and visual elements (like images, charts, and graphics) in PDFs of 100 pages or fewer”
   • [claimed-docs] “Files can be uploaded to individual chats or uploaded to a project's Files section for persistent reference across conversations.”
   • [claimed-docs] “Prompt Claude using natural language to generate Excel spreadsheets, PowerPoint presentations, Word documents, and PDF files that you can do…”
   • [claimed-docs] “produce reports with charts and visualizations, and generate presentations from your documents—all without specialized software skills”

   proof ↗⚑ flag

   Martin—none0/10

   Martin is a personal-assistant product focused on calendar, email, Slack, reminders, notes, and todos; no evidence anywhere in the pack mentions document, spreadsheet, or PDF upload/analysis capabilities. This is a plausible axis for an AI assistant but there's no supporting documentation or community mention of file/document analysis features.

   ⚑ flag

Memory

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

   weight 3 · round to Claude
   Claude✓fullclaimed8/10

   Claude has explicit first-party memory/chat-search docs: it can search previous conversations and "remember context from your chats and carry it into new conversations and Cowork tasks," plus a dedicated article on how memory works, what's remembered, and how to review/edit it; the product page also advertises "Memory across conversations" as a core feature. This directly matches the story of remembering context across chats and applying it in new ones. Missing for 10: independent/hands-on corroboration of memory quality or limitations in practice beyond vendor docs.

   • [claimed-docs] “You can prompt Claude to search through your previous conversations to find and reference relevant information in new chats.”
   • [claimed-docs] “Chat on web, iOS, Android, and on your desktop ... Memory across conversations”
   • [claimed-docs] “This article explains how chat search and memory work, what Claude does and doesn’t remember, how to review and edit what’s saved, and how t…”
   • [claimed-docs] “Claude can also remember context from your chats and carry it into new conversations and Cowork tasks.”

   proof ↗⚑ flag

   Martin~partialclaimed4/10

   Martin's notes, to-dos, and reminders (martin-docs-6, martin-docs-22, martin-docs-5) provide persistent storage that Martin can read back across interfaces, giving it some ability to carry information forward. However, there is no explicit documentation of the assistant automatically recalling relevant context from prior conversations and applying it in new, unrelated chats — memory here is user-invoked (explicit notes) rather than an automatic contextual-memory feature. Missing for 10: explicit memory/context-recall feature description, evidence of automatic application of past-conversation context in new sessions, independent confirmation of this behavior.

   • [claimed-docs] “You can tell Martin to read, add, and edit your notes from any interface.”
   • [claimed-docs] “Call Martin and say "Note down everything we talked about on this call and call it 'Brain Dump'."”
   • [claimed-docs] “You can tell Martin to add, edit, and check off your to-dos on your behalf from any interface.”
   • [claimed-docs] “Tell Martin to remind you to do something, and he will ping you at the specified time, via the specified interface.”

   proof ↗⚑ flag

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

   weight 1 · round to Claude
   Claude~partialclaimed6/10

   Claude supports persistent memory/context (chat search and memory, Projects with knowledge bases, custom instructions implied via Skills and Projects) that carries into new conversations, but there is no explicit documented feature for setting global 'custom instructions' that shape every response the way ChatGPT's system prompt does. missing for 10: dedicated persistent custom-instructions/preferences UI applying to all chats, independent/hands-on verification that memory reliably shapes every response, and clarity on scope/limits of what's remembered.

   • [claimed-docs] “You can prompt Claude to search through your previous conversations to find and reference relevant information in new chats.”
   • [claimed-docs] “This article explains how chat search and memory work, what Claude does and doesn’t remember, how to review and edit what’s saved, and how t…”
   • [claimed-docs] “Claude can also remember context from your chats and carry it into new conversations and Cowork tasks.”
   • [claimed-docs] “Projects allow you to create self-contained workspaces with their own chat histories and knowledge bases.”
   • [claimed-docs] “Skills teach Claude how to complete specific tasks in a repeatable way, whether that's creating documents with your company's brand guidelin…”

   proof ↗⚑ flag

   Martin—none0/10

   No evidence in the pack describes a persistent custom-instructions or preferences feature that shapes all of Martin's responses; the docs cover integrations, reminders, notes, and background tasks but nothing about setting persona/style preferences persistently.

   ⚑ flag

Images

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

   weight 2 · round to Claude
   Claude✓fullclaimed7/10

   Claude's docs confirm native image upload/paste support (JPEG, PNG, GIF, WebP) and clipboard paste, plus PDF analysis that includes visual elements like images and charts, directly supporting screenshot/photo interpretation for knowledge workers. Missing for 10: independent/hands-on evidence validating accuracy of image interpretation, and no explicit mention of screenshot-specific use cases (e.g., UI screenshots, photos of documents) beyond general image/PDF support.

   • [claimed-docs] “Claude analyzes both text and visual elements (like images, charts, and graphics) in PDFs of 100 pages or fewer”
   • [claimed-docs] “Claude supports the following image formats: - JPEG - PNG - GIF - WebP”
   • [claimed-docs] “You can also copy images and paste them from your clipboard into Claude”
   • [claimed-docs] “Claude can work with the following document types: - PDF - DOCX - CSV - TXT - HTML - ODT - RTF - EPUB - JSON - XLSX”

   proof ↗⚑ flag

   Martin—none0/10

   No evidence in the pack mentions image, screenshot, or photo interpretation capabilities; Martin's documented features focus on text-based channels (email, Slack, SMS, calendar, notes, reminders) with no mention of vision/multimodal input handling.

   ⚑ flag

Voice

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

   weight 2 · round to Claude
   Claude✓fullclaimed8/10

   Claude ships an explicit Voice mode enabling complete spoken conversations, available across web, desktop, iOS and Android, positioned to work best on phone. Missing for 10: independent hands-on reviews of voice latency/naturalness and confirmation it's out of beta.

   • [claimed-docs] “Voice mode allows you to have complete spoken conversations with Claude.”
   • [claimed-docs] “Voice mode is a beta feature available to all plans (Free, Pro, Max, Team, and Enterprise) on Claude Mobile (iOS and Android), Claude Deskto…”

   proof ↗⚑ flag

   Martin~partialclaimed6/10

   Martin supports real phone-call interactions — users can call Martin to dictate notes, and Martin can call users for wake-up briefings — indicating a live voice channel exists (martin-docs-22, martin-docs-24, martin-docs-12). However, there is no documentation or independent evidence describing the naturalness, latency, or conversational fluidity of these voice interactions, and community feedback focuses on text/action reliability rather than voice quality. Missing for 10: hands-on/independent evidence of real-time conversational voice quality, documentation of voice-specific features like interruption handling or natural turn-taking.

   • [claimed-docs] “Call Martin and say "Note down everything we talked about on this call and call it 'Brain Dump'."”
   • [claimed-docs] “Martin is reachable through all your communication channels, including phone, SMS, WhatsApp, email, and Slack.”
   • [claimed-docs] “Martin can call you at a specific time every morning to wake you up with the weather and your schedule.”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Claude—none0/10

   The evidence pack details many UI-exclusive Claude.ai features (Cowork, voice mode, computer use, memory/chat search, artifacts, browser extension, scheduled tasks) but contains no documentation that these capabilities are exposed through the Claude API, nor any statement of API/UI feature parity. Enterprise API mentions are limited to a Compliance API for logs, not general feature parity.

   • [claimed-docs] “With Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized resear…”
   • [claimed-docs] “Voice mode allows you to have complete spoken conversations with Claude.”
   • [claimed-docs] “Claude opens sites, reads pages, clicks, types, and fills forms while you watch, with no need to switch windows.”
   • [claimed-docs] “it may navigate to your screen directly—clicking, typing, and opening apps just like you would.”
   • [claimed-docs] “Audit logs: capture key information about user actions, system events, and data access. ... Compliance API: programmatically access Claude u…”
   • [claimed-docs] “Projects allow you to create self-contained workspaces with their own chat histories and knowledge bases.”
   • [claimed-docs] “This article explains how chat search and memory work, what Claude does and doesn’t remember, how to review and edit what’s saved, and how t…”

   proof ↗⚑ flag

   Martin—none0/10

   Martin's documented surface is entirely conversational interfaces (email, Slack, phone, SMS, WhatsApp) with no mention of a public/developer API; explicit probes for an OpenAPI/swagger spec at all standard paths returned 404, indicating no programmatic API exists to mirror these UI capabilities.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.trymartin.com/openapi.json, https://docs.trymartin.com/swagger.json, https://docs.tryma…”
   • [claimed-docs] “Martin is reachable through all your communication channels, including phone, SMS, WhatsApp, email, and Slack.”

   proof ↗⚑ flag

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

   weight 3 · round to Claude
   Claude~partialclaimed6/10

   Claude documents a data-export feature covering conversation and account data, letting users take their data with them ([claude-docs-12], [claude-docs-40]). However, there is no evidence specifying the export format is an open/standard one (e.g., JSON/portable), nor documentation of easy migration/interoperability with other tools, so the 'open format' and full portability aspects of the story are unconfirmed. missing for 10: explicit statement of open/standard export format, evidence of full interoperability/reuse elsewhere, and independent confirmation of export completeness.

   • [claimed-docs] “Individual Claude users can export user information and chat history from Settings > Privacy”
   • [claimed-docs] “Data exports include conversation data and the user data for your account.”

   proof ↗⚑ flag

   Martin—none0/10

   No evidence anywhere in the pack of a data export feature or open-format data portability; Martin's docs focus on integrations, reminders, and briefings but never mention exporting user data or account deletion/export tools.

   ⚑ flag

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

   weight 2 · round drawn
   Claude—none0/10

   Claude is closed-source; there is no evidence of an open-license source release for the model or app, and community evidence even criticizes it as closed/opaque compared to FOSS alternatives like Codex CLI (claude-comm-6).

   • [community] “Codex CLI is FOSS, unlike Claude Code, so Codex is less likely to do things like that, and it's one more reason to avoid Claude Code and Cla…”

   proof ↗⚑ flag

   Martin—none0/10

   No evidence Martin's source code is available under any license; a community comment explicitly calls for Martin to 'make that system open source' as a trust-building step, implying it currently is not.

   • [community] “You should create a system where you cannot access user data, and it can never be shared with third parties. Make that system open source to…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Claude—none0/10

   No evidence in the pack mentions data residency, regional storage options, or geographic controls for where account/chat data is stored; the closest items concern export, audit logs, and training opt-outs, none of which address residency choice.

   ⚑ flag

   Martin—none0/10

   No evidence anywhere in the pack mentions data residency, region selection, or storage location controls; docs focus entirely on assistant features and integrations. Community comments raise general privacy/security concerns but do not address data residency options. missing for 10: any mention of region selection, data residency policy, or storage location controls.

   • [community] “I want this, but very concerned about the security and privacy - you're talking about getting my most personal of personals (email, calendar…”
   • [community] “You should create a system where you cannot access user data, and it can never be shared with third parties. Make that system open source to…”

   proof ↗⚑ flag

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

   weight 3 · round to Claude
   Claude✓fullclaimed8/10

   Claude documents explicit user controls to prevent training use: incognito chats are never used to improve Claude even with Model Improvement enabled, users can toggle the 'Model Improvement' privacy setting, and connector data (Gmail/Drive/Calendar) is explicitly excluded from training. This directly satisfies the ai-native privacy-posture story of preventing data from being used for model training. Missing for 10: independent/third-party verification of these claims and explicit default policy for Enterprise/Team plans beyond connectors.

   • [claimed-docs] “Your incognito chats are not used to improve Claude, even if you have enabled Model Improvement in your privacy settings.”
   • [claimed-docs] “When you allow us to use your chats or coding sessions to help improve Claude, we implement several layers of protection for your privacy.”
   • [claimed-docs] “We do not train our models on your Gmail, Drive, or Calendar connector data, ensuring your private information remains private.”

   proof ↗⚑ flag

   Martin—none0/10

   No evidence pack item addresses AI-training data opt-out or data-usage policy; community comments explicitly raise privacy/trust concerns without any documented answer or control from Martin. Missing for 10: any privacy policy statement, opt-out setting, or documented no-training-data commitment.

   • [community] “I want this, but very concerned about the security and privacy - you're talking about getting my most personal of personals (email, calendar…”
   • [community] “You should create a system where you cannot access user data, and it can never be shared with third parties. Make that system open source to…”

   proof ↗⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round to Claude
   Claude✓fullclaimed8/10

   Claude provides explicit user-facing data controls: exporting chat history/user data (claude-docs-12, 40), reviewing/editing/turning off memory (claude-docs-45), incognito chats excluded from training (claude-docs-46), and enterprise audit logs plus a compliance API for data governance (claude-docs-11, 44). Missing for 10: explicit self-service account/data deletion flow documentation and independent verification that deletion requests are honored.

   • [claimed-docs] “Individual Claude users can export user information and chat history from Settings > Privacy”
   • [claimed-docs] “Data exports include conversation data and the user data for your account.”
   • [claimed-docs] “This article explains how chat search and memory work, what Claude does and doesn’t remember, how to review and edit what’s saved, and how t…”
   • [claimed-docs] “Your incognito chats are not used to improve Claude, even if you have enabled Model Improvement in your privacy settings.”
   • [claimed-docs] “When you allow us to use your chats or coding sessions to help improve Claude, we implement several layers of protection for your privacy.”
   • [claimed-docs] “Audit logs: capture key information about user actions, system events, and data access. ... Compliance API: programmatically access Claude u…”
   • [claimed-docs] “Enterprise includes everything in the Team plan, plus the following: - Security features to ensure the safety and compliance of your organiz…”

   proof ↗⚑ flag

   Martin—none0/10

   No evidence describes data retention policies, deletion controls, export tools, or privacy settings; community comments even raise unaddressed concerns about lack of transparency around data handling. Missing for 10: any documentation of data retention periods, user-initiated deletion mechanism, or privacy controls.

   • [community] “I want this, but very concerned about the security and privacy - you're talking about getting my most personal of personals (email, calendar…”
   • [community] “You should create a system where you cannot access user data, and it can never be shared with third parties. Make that system open source to…”

   proof ↗⚑ flag

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

   weight 2 · round to Claude
   Claude~partialclaimed6/10

   Claude documents a 'Model Improvement' privacy setting that can be toggled off and 'incognito chats' that are excluded from training even if Model Improvement is enabled, giving users control over whether their conversations are used to improve the model (claude-docs-46, claude-docs-47). This addresses opt-out of usage-for-training, and data export/deletion options exist (claude-docs-12, claude-docs-40), but there is no explicit documentation of a broader telemetry/analytics opt-out (e.g., product usage metrics, crash reporting) beyond model-training data use. missing for 10: explicit telemetry/analytics tracking opt-out settings, independent confirmation that toggling actually stops all usage tracking, documentation of what non-training telemetry data is collected.

   • [claimed-docs] “Your incognito chats are not used to improve Claude, even if you have enabled Model Improvement in your privacy settings.”
   • [claimed-docs] “When you allow us to use your chats or coding sessions to help improve Claude, we implement several layers of protection for your privacy.”
   • [claimed-docs] “Individual Claude users can export user information and chat history from Settings > Privacy”
   • [claimed-docs] “Data exports include conversation data and the user data for your account.”

   proof ↗⚑ flag

   Martin—none0/10

   No evidence of any telemetry opt-out, privacy settings, or data collection controls; community comments even raise unresolved privacy/trust concerns (martin-comm-2, martin-comm-3) with no documented response or opt-out mechanism.

   • [community] “I want this, but very concerned about the security and privacy - you're talking about getting my most personal of personals (email, calendar…”
   • [community] “You should create a system where you cannot access user data, and it can never be shared with third parties. Make that system open source to…”

   proof ↗⚑ flag

Research

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

   weight 3 · round to Claude
   Claude✓fullcommunity8/10

   Claude's Research feature is well documented: it operates agentically running multiple searches that build on each other, determines what to investigate next, and delivers thorough answers in minutes with easy-to-check citations. Community evidence is mixed on research depth (some say it lags ChatGPT/Gemini), which caps quality but the core capability is clearly delivered. Missing for 10: independent hands-on benchmark showing citation accuracy/report quality, and clearer detail on breadth of sources searched.

   • [claimed-docs] “With research, Claude delivers thorough answers in minutes, complete with easy-to-check citations so you can trust Claude's findings.”
   • [claimed-docs] “Research transforms how Claude finds and analyzes information. Claude operates agentically, conducting multiple searches that build on each …”
   • [claimed-docs] “Claude operates agentically, conducting multiple searches that build on each other while determining exactly what to investigate next.”
   • [claimed-docs] “Claude delivers thorough answers in minutes, complete with easy-to-check citations so you can trust Claude's findings.”
   • [community] “Meanwhile, Claude's general use cases are... fine. For generic research topics, I find that ChatGPT and Gemini run circles around it: in the…”
   • [community] “Works pretty nicely for research still, not seeing a substantial qualitative improvement over Opus 4.5.”

   proof ↗⚑ flag

   Martin—none0/10

   Martin's docs mention a basic search capability that 'syncs with multiple search engines to find relevant information' (martin-docs-8), but there is no evidence of an autonomous multi-source deep-research mode that returns a structured, cited report — no mention of citation formatting, report generation, or a dedicated 'deep research' feature.

   • [claimed-docs] “Martin syncs with multiple search engines to find you the most relevant information.”

   proof ↗⚑ flag

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

   weight 2 · round to Claude
   Claude~partialcommunity7/10

   Claude's Research feature is documented to perform agentic multi-step web searches and deliver answers with 'easy-to-check citations' (claude-docs-20, 27, 39, 68), directly matching the story. However, independent community feedback suggests mixed real-world quality—commenters say Claude's general research 'is fine' but that ChatGPT and Gemini 'run circles around it' in depth and presentation (claude-comm-8, claude-comm-9), tempering confidence in how well-grounded/comprehensive the citations truly are. missing for 10: independent hands-on verification of citation accuracy/source quality, and confirmation research draws from live/current web data versus stale index.

   • [claimed-docs] “With research, Claude delivers thorough answers in minutes, complete with easy-to-check citations so you can trust Claude's findings.”
   • [claimed-docs] “Research transforms how Claude finds and analyzes information. Claude operates agentically, conducting multiple searches that build on each …”
   • [claimed-docs] “Claude operates agentically, conducting multiple searches that build on each other while determining exactly what to investigate next.”
   • [claimed-docs] “Claude delivers thorough answers in minutes, complete with easy-to-check citations so you can trust Claude's findings.”
   • [community] “Meanwhile, Claude's general use cases are... fine. For generic research topics, I find that ChatGPT and Gemini run circles around it: in the…”
   • [community] “Works pretty nicely for research still, not seeing a substantial qualitative improvement over Opus 4.5.”

   proof ↗⚑ flag

   Martin~partialclaimed4/10

   Martin claims to sync with multiple search engines to find relevant information (martin-docs-8), suggesting web-grounded answers, but there is no evidence of citation formatting, source linking, or hands-on verification that answers include traceable citations back to web sources. Missing for 10: documentation or examples showing inline citations/source links, independent corroboration of search-grounded answer quality, and detail on which search engines/sources are used.

   • [claimed-docs] “Martin syncs with multiple search engines to find you the most relevant information.”

   proof ↗⚑ flag

Admin

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

   weight 2 · round to Claude
   Claude~partialclaimed4/10

   Evidence confirms Enterprise plan admin/security features like audit logs and a Compliance API for programmatic access to usage data, implying some org-level governance, but there is no documentation of member management, role/permission assignment, or granular data policy controls for team admins. missing for 10: member invitation/removal workflows, role-based permission management, workspace-level data retention/policy settings, and independent corroboration of admin console functionality.

   • [claimed-docs] “Audit logs: capture key information about user actions, system events, and data access. ... Compliance API: programmatically access Claude u…”
   • [claimed-docs] “Audit logs: capture key information about user actions, system events, and data access.”
   • [claimed-docs] “Enterprise includes everything in the Team plan, plus the following: - Security features to ensure the safety and compliance of your organiz…”

   proof ↗⚑ flag

   Martin—none0/10

   Martin's evidence pack is entirely about individual personal-assistant features (calendar, email, Slack, reminders, to-dos) with no mention of organization workspaces, member management, permission controls, or data-policy settings for teams. missing for 10: any admin console, member/role management, workspace-level permissions, or data governance policy documentation.

   ⚑ flag

Data controls

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

   weight 1 · round to Claude
   Claude✓fullclaimed9/10

   Claude's docs explicitly state individual users can export user information and chat history from Settings > Privacy, and that exports include both conversation data and account/user data; Enterprise adds a Compliance API for programmatic access to chat histories and file content. Missing for 10: independent/hands-on confirmation of export completeness or format details beyond first-party docs.

   • [claimed-docs] “Individual Claude users can export user information and chat history from Settings > Privacy”
   • [claimed-docs] “Data exports include conversation data and the user data for your account.”
   • [claimed-docs] “Audit logs: capture key information about user actions, system events, and data access. ... Compliance API: programmatically access Claude u…”

   proof ↗⚑ flag

   Martin—none0/10

   No evidence in the pack mentions data export, chat history download, or account data portability features; community comments even raise privacy concerns without any mention of export tools. Missing for 10: any documentation or feature reference to exporting chat history or account data, data portability API, or GDPR-style export mechanism.

   ⚑ flag

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

   weight 3 · round to Claude
   Claude✓fullclaimed8/10

   Claude provides explicit privacy controls: incognito chats are excluded from model training even with Model Improvement enabled, a 'Model Improvement' opt-in/out toggle exists, and connector data (Gmail/Drive/Calendar) is explicitly excluded from training. Missing for 10: independent/hands-on verification that the training opt-out is actually honored in practice, and clearer documentation of the toggle's exact location/scope for all plan tiers.

   • [claimed-docs] “Your incognito chats are not used to improve Claude, even if you have enabled Model Improvement in your privacy settings.”
   • [claimed-docs] “When you allow us to use your chats or coding sessions to help improve Claude, we implement several layers of protection for your privacy.”
   • [claimed-docs] “We do not train our models on your Gmail, Drive, or Calendar connector data, ensuring your private information remains private.”

   proof ↗⚑ flag

   Martin—none0/10

   No evidence in the pack mentions any setting, policy, or statement about whether user conversations/data are used for model training; community comments explicitly raise privacy/trust concerns without any documented opt-out or training-control mechanism (martin-comm-2, martin-comm-3).

   • [community] “I want this, but very concerned about the security and privacy - you're talking about getting my most personal of personals (email, calendar…”
   • [community] “You should create a system where you cannot access user data, and it can never be shared with third parties. Make that system open source to…”

   proof ↗⚑ flag