Fathom vs Fellow

Agent ops

1. ai-native userAn agent can automatically file each meeting's action items into my project tracker (Linear, Jira, Asana) using the product's API, webhooks, or native automations

   weight 2 · round to Fathom
   Fathom~partialprobed6/10

   Fathom's REST API, webhooks, and SDKs expose AI-generated action items and meeting data (fathom-docs-22, fathom-docs-45, fathom-docs-28) that an agent could use to push items into a project tracker, and the MCP server lets AI assistants query meeting data directly. However there is no evidence of a native/pre-built Linear, Jira, or Asana integration — only CRM field sync is mentioned as a native automation. Missing for 10: documented native connectors to Linear/Jira/Asana, and any example/template showing action items being filed into a project tracker end-to-end.

   • [claimed-docs] “Webhooks will send your meeting data (optionally including the summary, transcript, and action items) to a URL of your choice.”
   • [claimed-docs] “Create a webhook to receive new meeting content. At least one of `include_transcript`, `include_crm_matches`, `include_summary`, or `include…”
   • [claimed-docs] “AI generated action items”
   • [claimed-docs] “CRM field sync, updating records after meetings automatically”
   • [claimed-docs] “Fathom now offers an official MCP (Model Context Protocol) server, allowing you to connect your Fathom meeting data to AI assistants like Ch…”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the official hosted MCP server https://api.fathom.ai/mcp returned H…”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless GET to the documented REST base https://api.fathom.ai/external/v1/meetings returned HTTP 401 ca…”

   proof ↗⚑ flag

   Fellow~partialprobed5/10

   Fellow exposes a Developer API (get_action_items, append_note_agenda), webhooks for real-time event notifications, and an MCP server that could be used by an agent to fetch action items and push them elsewhere, giving the building blocks for this automation. However there is no evidence of a native Linear/Jira/Asana integration or documented reference workflow that actually files action items into those specific trackers. Missing for 10: native connectors/integrations to Linear, Jira, or Asana, and a documented example of an agent automatically creating tickets in those tools via the API/webhooks/MCP.

   • [claimed-docs] “List action items with optional filters and pagination.”
   • [claimed-docs] “Webhooks allow you to receive real-time notifications when events occur in Fellow.”
   • [claimed-docs] “Fellow's Model Context Protocol (MCP) Server allows you to ask your AI Assistant about your meetings, without needing to write any code.”
   • [claimed-docs] “pass transcripts to an LLM for tailored recaps and action plans, the API gives you everything you need to make it happen”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to Fellow's hosted MCP server https://fellow.app/mcp returned HTTP 401…”

   proof ↗⚑ flag

2. ai-native userAn official MCP server lets Claude or any MCP client query my meetings — search, transcripts, action items — with OAuth, no glue code

   weight 3 · round drawn
   Fathom✓fullprobed9/10

   Fathom ships an official hosted MCP server (api.fathom.ai/mcp) documented and installable as an official connector in Claude/ChatGPT via OAuth, with a runtime probe confirming it's live and enforces the MCP OAuth flow (401 + WWW-Authenticate pointing to oauth-protected-resource metadata), matching the story's search/transcript/action-items and no-glue-code OAuth requirements. Missing for 10: independent third-party (non-vendor) hands-on confirmation of query capabilities like search/action-items specifically through the MCP tool surface.

   • [claimed-docs] “Fathom now offers an official MCP (Model Context Protocol) server, allowing you to connect your Fathom meeting data to AI assistants like Ch…”
   • [claimed-docs] “Fathom is available as an **official connector** in Claude”
   • [claimed-docs] “Your meeting data, now inside ChatGPT, Claude, and more”
   • [claimed-docs] “claude mcp add fathom -- npx mcp-remote@latest https://api.fathom.ai/mcp”
   • [claimed-docs] “Claude Code supports adding MCP servers directly from the command line.”
   • [claimed-docs] “Connect Fathom to any MCP-compatible tool using the server URL below, then authenticate to access your meeting data.”
   • [probe] “official MCP server documented at https://developers.fathom.ai/mcp-docs/index”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the official hosted MCP server https://api.fathom.ai/mcp returned H…”

   proof ↗⚑ flag

   Fellow✓fullprobed9/10

   Fellow ships an official, documented MCP server enabling any MCP client (Claude, ChatGPT, Cursor) to query meetings — search, transcripts, action items — without writing code, and admins control which tools are exposed; a runtime probe confirms the hosted endpoint is live and auth-gated (bearer/OAuth-style), matching the docs. missing for 10: independent third-party review of the OAuth flow specifics beyond the probe's bearer-token confirmation.

   • [claimed-docs] “Ask anything about your meetings - Get answers to questions like "What were my action items this week?"”
   • [claimed-docs] “Fellow’s MCP Connector works with any AI tool that supports connectors, so you're never locked into one platform”
   • [claimed-docs] “As a workspace admin, you decide which MCP tools your members’ AI assistants can use.”
   • [claimed-docs] “Fellow's Model Context Protocol (MCP) Server allows you to ask your AI Assistant about your meetings, without needing to write any code.”
   • [claimed-docs] “Your favorite AI chatbot like Claude, ChatGPT, or Cursor can now tap directly into your meeting recaps, notes, and action items”
   • [claimed-docs] “Ask anything about your meetings - Get answers to questions like "What were my action items this week?" or "What did we decide in last month…”
   • [probe] “official MCP server documented at https://developers.fellow.ai/reference/mcp-server”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to Fellow's hosted MCP server https://fellow.app/mcp returned HTTP 401…”

   proof ↗⚑ flag

3. ai-native userMy scripts can pull transcripts, summaries, and action items from every meeting through a documented API with self-serve keys

   weight 3 · round to Fathom
   Fathom✓fullprobed9/10

   Fathom exposes a documented REST API with self-serve API-key generation, dedicated endpoints for transcripts and summaries, and webhook payloads that can include transcript/summary/action items, plus official SDKs and a live runtime-verified API surface with OpenAPI spec. Missing for 10: a clearly documented standalone REST 'get action items' endpoint (action items appear only bundled via webhook payloads) and independent (non-vendor) developer corroboration.

   • [claimed-docs] “Head to the API Access section of your User Settings and generate an API key.”
   • [claimed-docs] “All REST API resources are authenticated with API keys generated via the Fathom website's settings area.”
   • [claimed-docs] “If you send `destination_url`, the endpoint will behave in an asynchronous manner. If you do not send `destination_url`, the endpoint will r…”
   • [claimed-docs] “Get summary ... Either the destination URL for where we'll POST the call summary, or the summary for the recording.”
   • [claimed-docs] “Create a webhook to receive new meeting content. At least one of `include_transcript`, `include_crm_matches`, `include_summary`, or `include…”
   • [claimed-docs] “Get started in minutes with our official SDKs. They handle authentication, pagination, error handling, and all the complex stuff so you can …”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless GET to the documented REST base https://api.fathom.ai/external/v1/meetings returned HTTP 401 ca…”
   • [probe] “PROBE runtime (recorded 2026-09-05): Fathom publishes a machine-readable OpenAPI 3.1.1 spec ('Fathom External API', versioned 1.0.0) at http…”

   proof ↗⚑ flag

   Fellow✓fullprobed8/10

   Fellow documents a REST Developer API with self-serve API key generation (docs-2,15,16) and endpoints for recordings/transcripts, action items, and notes (docs-4,5,6,31), plus webhooks for real-time events. Runtime probe confirms the API/MCP endpoints are live and properly authenticated, not vaporware. missing for 10: no public OpenAPI/swagger spec found (404s), and no independent third-party developer report of building against the API.

   • [claimed-docs] “The Developer API opens that data to you: transcripts, structured notes, and more, all available through standard REST calls.”
   • [claimed-docs] “All API requests must include a valid API key in the Authorization header.”
   • [claimed-docs] “List recordings with optional filters and pagination.”
   • [claimed-docs] “List action items with optional filters and pagination.”
   • [claimed-docs] “Include your API key in the `X-API-KEY` header of every request”
   • [claimed-docs] “Generate a new API key for your application, giving it a descriptive name.”
   • [claimed-docs] “Webhooks allow you to receive real-time notifications when events occur in Fellow.”
   • [claimed-docs] “pass transcripts to an LLM for tailored recaps and action plans, the API gives you everything you need to make it happen”
   • [probe] “PROBE llms.txt: HTTP 200 at https://developers.fellow.ai/llms.txt # Fellow Documentation > Fellow’s API provides access to meeting notes an…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.fellow.ai/openapi.json, https://developers.fellow.ai/swagger.json, https://develo…”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to Fellow's hosted MCP server https://fellow.app/mcp returned HTTP 401…”

   proof ↗⚑ flag

Agent access

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

   weight 2 · round to Fathom
   Fathom✓fullprobed9/10

   Fathom serves a live llms.txt at developers.fathom.ai (HTTP 200, confirmed by probe) that indexes its agent-oriented docs, plus a machine-readable OpenAPI spec and MCP server docs, all directly consumable by an AI agent. missing for 10: no independent/third-party report of an agent successfully consuming llms.txt end-to-end.

   • [probe] “PROBE llms.txt: HTTP 200 at https://developers.fathom.ai/llms.txt # Fathom API - [Introduction](https://developers.fathom.ai/index.md): Wel…”
   • [probe] “PROBE runtime (recorded 2026-09-05): Fathom publishes a machine-readable OpenAPI 3.1.1 spec ('Fathom External API', versioned 1.0.0) at http…”
   • [claimed-docs] “Fathom now offers an official MCP (Model Context Protocol) server, allowing you to connect your Fathom meeting data to AI assistants like Ch…”
   • [claimed-docs] “Connect Fathom to any MCP-compatible tool using the server URL below, then authenticate to access your meeting data.”

   proof ↗⚑ flag

   Fellow✓fullprobed8/10

   A live probe confirms Fellow serves a proper llms.txt file at https://developers.fellow.ai/llms.txt (HTTP 200) summarizing its API for agent consumption, and the broader developer docs (API reference, MCP server docs) are structured for both human and agent use. Missing for 10: no evidence of a companion llms-full.txt or independent third-party confirmation that agents successfully consume this file in practice.

   • [probe] “PROBE llms.txt: HTTP 200 at https://developers.fellow.ai/llms.txt # Fellow Documentation > Fellow’s API provides access to meeting notes an…”
   • [claimed-docs] “pass transcripts to an LLM for tailored recaps and action plans, the API gives you everything you need to make it happen”
   • [probe] “official MCP server documented at https://developers.fellow.ai/reference/mcp-server”

   proof ↗⚑ flag

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

   weight 2 · round to Fathom
   Fathom~partialprobed6/10

   Fathom exposes a documented, live REST API with API-key auth, SDKs, webhooks, and an OpenAPI spec, all of which can be scripted headlessly in CI to pull meeting/transcript/summary data. However, there's no evidence of a CLI tool, official CI/CD templates, or GitHub Actions integration, and Fathom's core value (meeting capture/bot) is not something CI can trigger — automation is limited to data retrieval/webhooks, not the full product experience. missing for 10: dedicated CLI, CI/CD templates or GitHub Actions examples, evidence of automated meeting-capture triggering from CI, independent (non-vendor) confirmation of headless usage.

   • [claimed-docs] “All REST API resources are authenticated with API keys generated via the Fathom website's settings area.”
   • [claimed-docs] “Get started in minutes with our official SDKs. They handle authentication, pagination, error handling, and all the complex stuff so you can …”
   • [claimed-docs] “Get started in minutes with our official SDKs. They handle authentication, pagination, error handling, and all the complex stuff”
   • [claimed-docs] “Create a webhook to receive new meeting content. At least one of `include_transcript`, `include_crm_matches`, `include_summary`, or `include…”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless GET to the documented REST base https://api.fathom.ai/external/v1/meetings returned HTTP 401 ca…”
   • [probe] “PROBE runtime (recorded 2026-09-05): Fathom publishes a machine-readable OpenAPI 3.1.1 spec ('Fathom External API', versioned 1.0.0) at http…”

   proof ↗⚑ flag

   Fellow—none0/10

   The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)

   ⚑ flag

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

   weight 3 · round drawn
   Fathom—none0/10

   All MCP evidence describes Fathom as an MCP *server* that other AI assistants (Claude, ChatGPT) connect to, not Fathom acting as an MCP client that plugs in external MCP servers to use their tools. No evidence shows Fathom's own AI/assistant features consuming external MCP tool servers.

   • [claimed-docs] “Fathom now offers an official MCP (Model Context Protocol) server, allowing you to connect your Fathom meeting data to AI assistants like Ch…”
   • [claimed-docs] “Your meeting data, now inside ChatGPT, Claude, and more”
   • [claimed-docs] “Fathom is available as an official connector in Claude”
   • [claimed-docs] “Connect Fathom to any MCP-compatible tool using the server URL below, then authenticate to access your meeting data.”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the official hosted MCP server https://api.fathom.ai/mcp returned H…”

   proof ↗⚑ flag

   Fellow—none0/10

   All evidence describes Fellow acting as an MCP *server*, exposing its own meeting data/tools to external AI assistants (Claude, ChatGPT, Cursor) — the opposite direction of this story, which asks whether a user can plug external MCP servers into Fellow so Fellow itself can use their tools. No evidence shows Fellow consuming or connecting to third-party MCP servers.

   ⚑ flag

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

   weight 3 · round drawn
   Fathom✓fullprobed9/10

   Fathom ships an official hosted MCP server (api.fathom.ai/mcp) documented for connecting AI assistants like Claude and ChatGPT, with official connector status in Claude and CLI setup instructions, and a runtime probe confirms the endpoint is live and speaks MCP OAuth. Missing for 10: independent third-party (non-vendor) hands-on confirmation of the agent connection working end-to-end.

   • [claimed-docs] “Fathom now offers an official MCP (Model Context Protocol) server, allowing you to connect your Fathom meeting data to AI assistants like Ch…”
   • [claimed-docs] “Fathom is available as an **official connector** in Claude”
   • [claimed-docs] “Your meeting data, now inside ChatGPT, Claude, and more”
   • [claimed-docs] “claude mcp add fathom -- npx mcp-remote@latest https://api.fathom.ai/mcp”
   • [claimed-docs] “Claude Code supports adding MCP servers directly from the command line.”
   • [claimed-docs] “Connect Fathom to any MCP-compatible tool using the server URL below, then authenticate to access your meeting data.”
   • [probe] “official MCP server documented at https://developers.fathom.ai/mcp-docs/index”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the official hosted MCP server https://api.fathom.ai/mcp returned H…”

   proof ↗⚑ flag

   Fellow✓fullprobed9/10

   Fellow ships an official, documented MCP Server (developers.fellow.ai/reference/mcp-server) that lets AI assistants like Claude, ChatGPT, or Cursor query meeting transcripts and action items without code, with admin-level tool controls; a runtime probe confirms the hosted endpoint (fellow.app/mcp) is live and properly bearer-gated as documented. missing for 10: independent third-party/community usage reports beyond the vendor docs and the single runtime probe.

   • [claimed-docs] “Fellow's Model Context Protocol (MCP) Server allows you to ask your AI Assistant about your meetings, without needing to write any code.”
   • [claimed-docs] “Fellow’s MCP Connector works with any AI tool that supports connectors, so you're never locked into one platform”
   • [claimed-docs] “As a workspace admin, you decide which MCP tools your members’ AI assistants can use.”
   • [claimed-docs] “Your favorite AI chatbot like Claude, ChatGPT, or Cursor can now tap directly into your meeting recaps, notes, and action items”
   • [probe] “official MCP server documented at https://developers.fellow.ai/reference/mcp-server”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to Fellow's hosted MCP server https://fellow.app/mcp returned HTTP 401…”

   proof ↗⚑ flag

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

   weight 3 · round to Fathom
   Fathom✓fullprobed9/10

   Fathom publishes a full public REST API with API-key auth, official TypeScript/Python SDKs, webhooks, and a machine-readable OpenAPI 3.1.1 spec, and runtime probes confirm the documented endpoints are live and match the docs exactly. This gives AI-native users a fully documented, verifiable way to drive the product programmatically beyond just MCP/chat connectors. Missing for 10: independent third-party developer reviews/case studies of building against the API.

   • [claimed-docs] “All REST API resources are authenticated with API keys generated via the Fathom website's settings area.”
   • [claimed-docs] “Get started in minutes with our official SDKs. They handle authentication, pagination, error handling, and all the complex stuff so you can …”
   • [claimed-docs] “Get started in minutes with our official SDKs. They handle authentication, pagination, error handling, and all the complex stuff”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless GET to the documented REST base https://api.fathom.ai/external/v1/meetings returned HTTP 401 ca…”
   • [probe] “PROBE runtime (recorded 2026-09-05): Fathom publishes a machine-readable OpenAPI 3.1.1 spec ('Fathom External API', versioned 1.0.0) at http…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.fathom.ai/openapi.json, https://developers.fathom.ai/swagger.json, https://develo…”

   proof ↗⚑ flag

   Fellow✓fullprobed8/10

   Fellow ships a documented Developer API with REST endpoints (recordings, action items, note editing), API-key authentication, and webhooks, giving AI-native users a clear path to programmatic control and even LLM-facing MCP integration. missing for 10: a public OpenAPI/swagger spec (probes returned 404) and independent/third-party developer corroboration beyond vendor docs.

   • [claimed-docs] “The Developer API opens that data to you: transcripts, structured notes, and more, all available through standard REST calls.”
   • [claimed-docs] “All API requests must include a valid API key in the Authorization header.”
   • [claimed-docs] “List recordings with optional filters and pagination.”
   • [claimed-docs] “List action items with optional filters and pagination.”
   • [claimed-docs] “Add Fellow Markdown to the end of a note's agenda, leaving the rest of the content in place.”
   • [claimed-docs] “Webhooks allow you to receive real-time notifications when events occur in Fellow.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.fellow.ai/openapi.json, https://developers.fellow.ai/swagger.json, https://develo…”

   proof ↗⚑ flag

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

   weight 2 · round to Fellow
   Fathom—none0/10

   Fathom's docs describe generating a single account-wide API key in User Settings (fathom-docs-1, fathom-docs-7) and a separate OAuth flow for public apps (fathom-docs-5, fathom-docs-21), but nowhere do the docs describe scopes, roles, or least-privilege permission grants that an AI agent could be issued. The 'users and permissions' endpoint (fathom-docs-9) and admin view-permission controls (fathom-docs-38) govern user-level meeting visibility, not credential scoping for agents. No evidence of restricting an API key/OAuth token to specific resources or actions for agentic use.

   • [claimed-docs] “Head to the API Access section of your User Settings and generate an API key.”
   • [claimed-docs] “All REST API resources are authenticated with API keys generated via the Fathom website's settings area.”
   • [claimed-docs] “Building a **public OAuth app** (for other Fathom users to install)? [Start here](/oauth) instead.”
   • [claimed-docs] “If you're developing a public app that you wish to integrate with Fathom, you should build it using OAuth.”
   • [claimed-docs] “Added users and permissions endpoint.”
   • [claimed-docs] “Admins can access all users' shared meetings by configuring View permissions”

   proof ↗⚑ flag

   Fellow~partialclaimed5/10

   Fellow supports API key auth and lets workspace admins control which MCP tools an AI assistant can access (fellow-docs-10), which is a coarse form of least-privilege control for agents. However there's no documented granular scoping (e.g., read-only vs write, resource-level permissions, expiry) for individual API keys — Super Admin keys in fact grant broad on-behalf-of access across the workspace, the opposite of least privilege. Missing for 10: explicit API key scope/permission levels, token expiration/revocation controls, and fine-grained per-resource credential issuance for agents.

   • [claimed-docs] “As a workspace admin, you decide which MCP tools your members’ AI assistants can use.”
   • [claimed-docs] “Super Admin API keys can make requests on behalf of any user in the workspace using the `X-On-Behalf-Of` header.”
   • [claimed-docs] “Fellow’s Super Admin API lets designated Enterprise‑plan administrators retrieve, export, and delete data across the entire workspace”
   • [claimed-docs] “Generate a new API key for your application, giving it a descriptive name.”
   • [claimed-docs] “All API requests must include a valid API key in the Authorization header.”

   proof ↗⚑ flag

7. ai-native userBuild against official SDKs

   weight 2 · round to Fathom
   Fathom✓fullprobed9/10

   Fathom documents official TypeScript and Python SDKs that handle auth, pagination, error handling, plus webhook verification helpers, backed by a live REST API and OpenAPI spec confirmed via runtime probes. Missing for 10: independent (non-vendor) developer testimonials or hands-on third-party validation of the SDKs.

   • [claimed-docs] “Use our Typescript or Python SDK.”
   • [claimed-docs] “Get started in minutes with our official SDKs. They handle authentication, pagination, error handling, and all the complex stuff so you can …”
   • [claimed-docs] “Get started in minutes with our official SDKs. They handle authentication, pagination, error handling, and all the complex stuff”
   • [claimed-docs] “If you're using our SDK, you can use the verify_webhook helper. Simply call: Fathom.verifyWebhook(webhook_secret, request.headers, request.b…”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless GET to the documented REST base https://api.fathom.ai/external/v1/meetings returned HTTP 401 ca…”
   • [probe] “PROBE runtime (recorded 2026-09-05): Fathom publishes a machine-readable OpenAPI 3.1.1 spec ('Fathom External API', versioned 1.0.0) at http…”

   proof ↗⚑ flag

   Fellow—none0/10

   Fellow documents a REST Developer API with API-key auth, webhooks, and endpoints for recordings/notes/action items, but no evidence names an official SDK (e.g., Python/JS client library); the openapi.json/swagger probe returned 404 across all standard paths, suggesting no formal spec-based SDK generation either.

   • [claimed-docs] “The Developer API opens that data to you: transcripts, structured notes, and more, all available through standard REST calls.”
   • [claimed-docs] “All API requests must include a valid API key in the Authorization header.”
   • [claimed-docs] “Include your API key in the `X-API-KEY` header of every request”
   • [claimed-docs] “Generate a new API key for your application, giving it a descriptive name.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.fellow.ai/openapi.json, https://developers.fellow.ai/swagger.json, https://develo…”

   proof ↗⚑ flag

8. ai-native userSubscribe to events via webhooks

   weight 2 · round to Fathom
   Fathom✓fullprobed9/10

   Fathom offers documented webhook subscription for meeting events (create-a-webhook API, configurable payload fields like transcript/summary/action items/CRM matches), with signature-based verification via headers and an SDK helper (verify_webhook), all corroborated by docs and consistent with the live API surface. missing for 10: no independent third-party hands-on report of webhook delivery reliability beyond first-party docs.

   • [claimed-docs] “Set up a webhook for your meetings.”
   • [claimed-docs] “Webhooks will send your meeting data (optionally including the summary, transcript, and action items) to a URL of your choice.”
   • [claimed-docs] “Create a webhook to receive new meeting content. At least one of `include_transcript`, `include_crm_matches`, `include_summary`, or `include…”
   • [claimed-docs] “Each webhook request sent from Fathom includes a signature in the request headers, which you can use to confirm the authenticity of the payl…”
   • [claimed-docs] “you can use the `verify_webhook` helper”
   • [claimed-docs] “If you're using our SDK, you can use the verify_webhook helper. Simply call: Fathom.verifyWebhook(webhook_secret, request.headers, request.b…”
   • [claimed-docs] “Webhook verification helps ensure that incoming requests to your endpoint are from Fathom and haven't been altered.”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless GET to the documented REST base https://api.fathom.ai/external/v1/meetings returned HTTP 401 ca…”

   proof ↗⚑ flag

   Fellow✓fullclaimed7/10

   Fellow's Developer API explicitly documents webhooks that deliver real-time HTTP POST notifications when events occur, which directly satisfies the subscribe-to-events story. Missing for 10: a list of supported event types/payload schema, and independent/hands-on confirmation of webhook delivery reliability.

   • [claimed-docs] “Fellow sends an HTTP POST request to the URL you specify with details about the event.”
   • [claimed-docs] “Webhooks allow you to receive real-time notifications when events occur in Fellow.”

   proof ↗⚑ flag

Agentic features

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

   weight 2 · round drawn
   Fathom✓fullprobed8/10

   Fathom generates AI summaries, action items, coaching scorecards, and Deal View insights directly from meeting data (docs-13,14,28,40), and surfaces this data conversationally via an official MCP server connected to ChatGPT/Claude (docs-10,19,35, probe-rt-1), confirmed live at runtime. Missing for 10: independent third-party review of insight quality/accuracy and more detail on how suggestions surface in-app beyond summaries/action items.

   • [claimed-docs] “Deal View summarizing insights”
   • [claimed-docs] “Coaching metrics & AI scorecards”
   • [claimed-docs] “AI generated action items”
   • [claimed-docs] “AI summaries instantly available after your call”
   • [claimed-docs] “Your meeting data, now inside ChatGPT, Claude, and more”
   • [claimed-docs] “Connect Fathom to any MCP-compatible tool using the server URL below, then authenticate to access your meeting data.”
   • [claimed-docs] “Fathom now offers an official MCP (Model Context Protocol) server, allowing you to connect your Fathom meeting data to AI assistants like Ch…”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the official hosted MCP server https://api.fathom.ai/mcp returned H…”

   proof ↗⚑ flag

   Fellow✓fullprobed8/10

   Fellow auto-generates AI meeting summaries, action items, decisions, and topic-based minutes for every meeting, plus MCP server and API access to let AI assistants query and reason over that data ('What were my action items this week?'). Runtime probe confirms the MCP server is live and functioning as documented (bearer-gated, not broken). missing for 10: independent third-party review of insight quality/accuracy, and no in-product analytics/dashboard example beyond summaries and action items.

   • [claimed-docs] “You automatically receive a clear meeting summary, suggested AI action items, decisions, and topic-based minutes for every meeting.”
   • [claimed-docs] “Ask anything about your meetings - Get answers to questions like "What were my action items this week?"”
   • [claimed-docs] “Ask anything about your meetings - Get answers to questions like "What were my action items this week?" or "What did we decide in last month…”
   • [claimed-docs] “Your favorite AI chatbot like Claude, ChatGPT, or Cursor can now tap directly into your meeting recaps, notes, and action items”
   • [claimed-docs] “pass transcripts to an LLM for tailored recaps and action plans, the API gives you everything you need to make it happen”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to Fellow's hosted MCP server https://fellow.app/mcp returned HTTP 401…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Fathom~partialprobed5/10

   Fathom offers webhooks, an API/SDK, and an MCP server that let developers build automations reacting to meeting events, which supports background/autonomous workflows, but Fathom itself does not ship a native no-code 'automations' builder or scheduled/autonomous agent runner — users must write their own integration code or use third-party tools (e.g. Zapier) to achieve full autonomy. missing for 10: a first-party no-code automation/workflow builder, evidence of autonomous scheduled or trigger-based agent tasks running natively within Fathom, and independent confirmation of end-to-end automation use in production.

   • [claimed-docs] “Set up a webhook for your meetings.”
   • [claimed-docs] “Webhooks will send your meeting data (optionally including the summary, transcript, and action items) to a URL of your choice.”
   • [claimed-docs] “Create a webhook to receive new meeting content. At least one of `include_transcript`, `include_crm_matches`, `include_summary`, or `include…”
   • [claimed-docs] “Each webhook request sent from Fathom includes a signature in the request headers, which you can use to confirm the authenticity of the payl…”
   • [claimed-docs] “Fathom now offers an official MCP (Model Context Protocol) server, allowing you to connect your Fathom meeting data to AI assistants like Ch…”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the official hosted MCP server https://api.fathom.ai/mcp returned H…”
   • [claimed-docs] “Get started in minutes with our official SDKs. They handle authentication, pagination, error handling, and all the complex stuff so you can …”

   proof ↗⚑ flag

   Fellow~partialclaimed5/10

   Fellow automatically generates summaries, action items, and decisions in the background after every meeting without manual triggering (fellow-docs-23), and its webhook system plus Developer API let external automations fire in real time when events occur (fellow-docs-3, fellow-docs-17, fellow-docs-31). However, there's no evidence of a native automation/workflow builder, scheduled triggers, or rule-based autonomous actions within Fellow itself — automation would need to be built externally using the webhook/API primitives. Missing for 10: a first-party automation/rules engine, scheduling capability, and hands-on evidence of end-to-end autonomous workflows beyond passive notification/data-access APIs.

   • [claimed-docs] “You automatically receive a clear meeting summary, suggested AI action items, decisions, and topic-based minutes for every meeting.”
   • [claimed-docs] “Fellow sends an HTTP POST request to the URL you specify with details about the event.”
   • [claimed-docs] “Webhooks allow you to receive real-time notifications when events occur in Fellow.”
   • [claimed-docs] “pass transcripts to an LLM for tailored recaps and action plans, the API gives you everything you need to make it happen”
   • [claimed-docs] “The Developer API opens that data to you: transcripts, structured notes, and more, all available through standard REST calls.”

   proof ↗⚑ flag

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

   weight 3 · round to Fellow
   Fathom~partialclaimed3/10

   Fathom's pricing page lists a 'Conversational meeting assistant' feature alongside AI summaries and AI-generated action items, suggesting some built-in AI assistant capability, but there is no documentation of what tasks can be delegated to it, how it's invoked, or its scope of autonomy. Most other AI-native evidence (MCP server, API) describes external assistants pulling Fathom's data rather than a built-in assistant acting on the user's behalf inside the product. Missing for 10: detailed docs on the conversational assistant's task-delegation capabilities, examples of it performing actions, and independent/hands-on confirmation.

   • [claimed-docs] “Conversational meeting assistant”
   • [claimed-docs] “AI generated action items”
   • [claimed-docs] “AI summaries instantly available after your call”

   proof ↗⚑ flag

   Fellow~partialclaimed4/10

   Fellow's AI automatically generates meeting summaries, action items, and decisions (fellow-docs-23, fellow-docs-31), which resembles delegated AI task execution, but there is no evidence of a conversational 'built-in assistant' inside the product that a user can direct with arbitrary tasks — the MCP server (fellow-docs-18, fellow-docs-26) instead lets *external* assistants like Claude/ChatGPT query Fellow's data, which is the inverse of a built-in assistant. Missing for 10: an in-app conversational assistant UI, evidence of multi-step task delegation beyond automatic note/action-item generation, and confirmation this assistant runs natively rather than via third-party AI tools.

   • [claimed-docs] “You automatically receive a clear meeting summary, suggested AI action items, decisions, and topic-based minutes for every meeting.”
   • [claimed-docs] “pass transcripts to an LLM for tailored recaps and action plans, the API gives you everything you need to make it happen”
   • [claimed-docs] “Fellow's Model Context Protocol (MCP) Server allows you to ask your AI Assistant about your meetings, without needing to write any code.”
   • [claimed-docs] “Your favorite AI chatbot like Claude, ChatGPT, or Cursor can now tap directly into your meeting recaps, notes, and action items”
   • [claimed-docs] “Ask anything about your meetings - Get answers to questions like "What were my action items this week?" or "What did we decide in last month…”

   proof ↗⚑ flag

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

   weight 2 · round to Fellow
   Fathom~partialprobed6/10

   Fathom ships an official MCP server and official connectors for Claude/ChatGPT, letting users query and interact with meeting data via natural-language prompts in those assistants, and lists a 'Conversational meeting assistant' as a product feature — both are corroborated by live runtime probes of the MCP endpoint. Missing for 10: evidence of a native in-app natural-language command interface (e.g., voice/text commands to control Fathom itself rather than just query data through third-party assistants), and independent user reports of successful conversational task execution beyond data retrieval.

   • [claimed-docs] “Fathom now offers an official MCP (Model Context Protocol) server, allowing you to connect your Fathom meeting data to AI assistants like Ch…”
   • [claimed-docs] “Your meeting data, now inside ChatGPT, Claude, and more”
   • [claimed-docs] “Conversational meeting assistant”
   • [claimed-docs] “Fathom is available as an official connector in Claude”
   • [claimed-docs] “Connect Fathom to any MCP-compatible tool using the server URL below, then authenticate to access your meeting data.”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the official hosted MCP server https://api.fathom.ai/mcp returned H…”

   proof ↗⚑ flag

   Fellow~partialprobed7/10

   Fellow ships an official, documented MCP server that works with AI assistants (Claude, ChatGPT, Cursor) to let users ask natural-language questions like "What were my action items this week?", and a runtime probe confirms the hosted MCP endpoint is live and bearer-gated as documented. However, the evidence shows this is primarily a query/read interface (search meetings, get action items, get transcripts) rather than full natural-language control over write/agentic actions. Missing for 10: evidence of NL-driven write actions (e.g., scheduling, editing notes, assigning action items) executed through natural-language commands rather than just Q&A retrieval.

   • [claimed-docs] “Ask anything about your meetings - Get answers to questions like "What were my action items this week?"”
   • [claimed-docs] “Fellow’s MCP Connector works with any AI tool that supports connectors, so you're never locked into one platform”
   • [claimed-docs] “Fellow's Model Context Protocol (MCP) Server allows you to ask your AI Assistant about your meetings, without needing to write any code.”
   • [claimed-docs] “Your favorite AI chatbot like Claude, ChatGPT, or Cursor can now tap directly into your meeting recaps, notes, and action items”
   • [claimed-docs] “Ask anything about your meetings - Get answers to questions like "What were my action items this week?" or "What did we decide in last month…”
   • [probe] “official MCP server documented at https://developers.fellow.ai/reference/mcp-server”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to Fellow's hosted MCP server https://fellow.app/mcp returned HTTP 401…”

   proof ↗⚑ flag

Api quality

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

   weight 2 · round to Fathom
   Fathom~partialprobed5/10

   Fathom publishes a full API reference with per-endpoint docs (get-transcript, get-summary, create-a-webhook) and a machine-readable OpenAPI 3.1.1 spec confirmed live at runtime, plus SDKs that simplify calling those endpoints — this gives structured, machine-consumable reference material an AI-native user could explore. However, there's no evidence of an interactive 'try-it-now' console or embedded runnable code examples in the docs themselves (the openapi.json/swagger.json UI paths probed 404, suggesting no rendered interactive explorer). Missing for 10: an in-browser interactive API playground/try-it-now widget, evidence of executable/runnable code snippets directly in docs, and independent confirmation of this interactive experience.

   • [claimed-docs] “If you send `destination_url`, the endpoint will behave in an asynchronous manner. If you do not send `destination_url`, the endpoint will r…”
   • [claimed-docs] “Get summary ... Either the destination URL for where we'll POST the call summary, or the summary for the recording.”
   • [claimed-docs] “Get started in minutes with our official SDKs. They handle authentication, pagination, error handling, and all the complex stuff so you can …”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.fathom.ai/openapi.json, https://developers.fathom.ai/swagger.json, https://develo…”
   • [probe] “PROBE runtime (recorded 2026-09-05): Fathom publishes a machine-readable OpenAPI 3.1.1 spec ('Fathom External API', versioned 1.0.0) at http…”

   proof ↗⚑ flag

   Fellow~partialprobed3/10

   Fellow publishes a structured Developer API reference with per-endpoint pages (recordings, action items, note editing, webhooks) suggesting a ReadMe.io-style docs site, but there is no confirmed evidence of a live 'try it' interactive console or runnable code examples — the openapi.json/swagger.json probe returned 404 across all candidate paths, indicating no public machine-readable spec to power an interactive explorer. missing for 10: explicit runnable 'try it' console evidence, public OpenAPI/Swagger spec, and independent confirmation of interactivity.

   • [claimed-docs] “List recordings with optional filters and pagination.”
   • [claimed-docs] “List action items with optional filters and pagination.”
   • [claimed-docs] “Add Fellow Markdown to the end of a note's agenda, leaving the rest of the content in place.”
   • [claimed-docs] “The Developer API opens that data to you: transcripts, structured notes, and more, all available through standard REST calls.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.fellow.ai/openapi.json, https://developers.fellow.ai/swagger.json, https://develo…”

   proof ↗⚑ flag

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

   weight 2 · round to Fathom
   Fathom✓fullprobed8/10

   Fathom publishes a machine-readable OpenAPI 3.1.1 spec at developers.fathom.ai/api-reference/openapi.yaml, confirmed by a runtime fetch, and this URL is advertised in the site's own llms.txt. Missing for 10: discoverability at conventional paths (openapi.json/swagger.json all 404) and independent third-party corroboration beyond the vendor's own runtime probe.

   • [probe] “PROBE runtime (recorded 2026-09-05): Fathom publishes a machine-readable OpenAPI 3.1.1 spec ('Fathom External API', versioned 1.0.0) at http…”
   • [probe] “PROBE llms.txt: HTTP 200 at https://developers.fathom.ai/llms.txt # Fathom API - [Introduction](https://developers.fathom.ai/index.md): Wel…”
   • [claimed-docs] “All REST API resources are authenticated with API keys generated via the Fathom website's settings area.”

   proof ↗⚑ flag

   Fellow—none0/10

   Fellow's developer docs use ReadMe-style reference pages but the probe explicitly found no OpenAPI/Swagger spec at any standard location (all 404), and no evidence of a downloadable machine-readable spec is cited elsewhere.

   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.fellow.ai/openapi.json, https://developers.fellow.ai/swagger.json, https://develo…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Fathom—none0/10

   Fathom publishes an OpenAPI spec (versioned 1.0.0) and a changelog tracking added endpoints, but there is no evidence of a documented API versioning scheme or a deprecation policy for breaking changes.

   • [claimed-docs] “Added download recording endpoint.”
   • [claimed-docs] “Added users and permissions endpoint.”
   • [probe] “PROBE runtime (recorded 2026-09-05): Fathom publishes a machine-readable OpenAPI 3.1.1 spec ('Fathom External API', versioned 1.0.0) at http…”

   proof ↗⚑ flag

   Fellow—none0/10

   Evidence documents API endpoints, auth, and webhooks, but there is no mention anywhere of API versioning scheme or a documented deprecation policy; an openapi spec probe even 404'd, suggesting no formal versioned spec is published.

   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.fellow.ai/openapi.json, https://developers.fellow.ai/swagger.json, https://develo…”
   • [claimed-docs] “The Developer API opens that data to you: transcripts, structured notes, and more, all available through standard REST calls.”
   • [claimed-docs] “All API requests must include a valid API key in the Authorization header.”

   proof ↗⚑ flag

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

   weight 2 · round to Fellow
   Fathom~partialprobed4/10

   Fathom's API supports listing meetings, retrieving transcripts/summaries, and webhooks, which could be scripted to iterate across many meetings, but there is no documented bulk/batch endpoint, no pagination-across-thousands example, and no explicit bulk-operations feature (e.g., bulk export, bulk delete, bulk tagging) called out anywhere. missing for 10: dedicated bulk/batch API endpoints, documented pagination for large-scale iteration, bulk write/update operations, and any hands-on evidence of performing bulk actions across many items.

   • [claimed-docs] “List the 10 most recent meetings recorded by you or shared to your team.”
   • [claimed-docs] “Head to the API Access section of your User Settings and generate an API key... List the 10 most recent meetings recorded by you or shared t…”
   • [claimed-docs] “Get started in minutes with our official SDKs. They handle authentication, pagination, error handling, and all the complex stuff so you can …”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless GET to the documented REST base https://api.fathom.ai/external/v1/meetings returned HTTP 401 ca…”
   • [probe] “PROBE runtime (recorded 2026-09-05): Fathom publishes a machine-readable OpenAPI 3.1.1 spec ('Fathom External API', versioned 1.0.0) at http…”

   proof ↗⚑ flag

   Fellow~partialclaimed5/10

   Fellow's Developer API supports listing recordings/action items with filters and pagination (bulk read), and the Super Admin API explicitly allows retrieving, exporting, and deleting data across the entire workspace, which covers workspace-wide bulk read/delete for admins. However, there's no documented endpoint for bulk create/update/write operations (e.g., batch-editing many action items or notes in one call) — missing for 10: bulk write/update endpoints, batch action-item creation, evidence of true multi-item mutation in a single API call.

   • [claimed-docs] “List recordings with optional filters and pagination.”
   • [claimed-docs] “List action items with optional filters and pagination.”
   • [claimed-docs] “Fellow’s Super Admin API lets designated Enterprise‑plan administrators retrieve, export, and delete data across the entire workspace”
   • [claimed-docs] “Build admin dashboards that display data from a specific user's perspective”

   proof ↗⚑ flag

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

   weight 3 · round to Fathom
   Fathom~partialclaimed5/10

   Fathom supports event-driven automation via webhooks (triggered on new meeting content, with signature verification) and topic monitoring alerts, which act as reactive triggers, but there is no evidence of a user-facing rules engine where AI-native users can define arbitrary conditional logic ('if X then do Y') beyond webhook subscriptions to fixed meeting events. missing for 10: a configurable rules/conditions engine, support for custom trigger logic beyond meeting-completion events, and evidence of chained multi-step automated actions.

   • [claimed-docs] “Set up a webhook for your meetings.”
   • [claimed-docs] “Webhooks will send your meeting data (optionally including the summary, transcript, and action items) to a URL of your choice.”
   • [claimed-docs] “Create a webhook to receive new meeting content. At least one of `include_transcript`, `include_crm_matches`, `include_summary`, or `include…”
   • [claimed-docs] “Each webhook request sent from Fathom includes a signature in the request headers, which you can use to confirm the authenticity of the payl…”
   • [claimed-docs] “Automatically monitor key topics so you never miss critical moments”
   • [claimed-docs] “CRM field sync, updating records after meetings automatically”

   proof ↗⚑ flag

   Fellow~partialclaimed4/10

   Fellow offers webhooks that fire real-time notifications on events, which can be used to build external automations, but there is no evidence of a native rules/trigger builder within Fellow itself that lets a user define 'if event X then action Y' logic. Missing for 10: a documented in-product automation/rules engine, examples of user-configurable triggers-to-actions, and any built-in action execution beyond webhook delivery.

   • [claimed-docs] “Fellow sends an HTTP POST request to the URL you specify with details about the event.”
   • [claimed-docs] “Webhooks allow you to receive real-time notifications when events occur in Fellow.”
   • [claimed-docs] “pass transcripts to an LLM for tailored recaps and action plans, the API gives you everything you need to make it happen”

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round drawn
   Fathom—none0/10

   Fathom is a meeting-notes/transcription product with an API, webhooks, and MCP connector, but nothing in the evidence describes scheduling recurring jobs or automated workflow runs (e.g., cron-like triggers, recurring exports, or repeated automation tasks). Webhooks are event-driven (post-meeting), not scheduled/recurring job execution.

   • [claimed-docs] “Webhooks will send your meeting data (optionally including the summary, transcript, and action items) to a URL of your choice.”
   • [claimed-docs] “Create a webhook to receive new meeting content. At least one of `include_transcript`, `include_crm_matches`, `include_summary`, or `include…”
   • [claimed-docs] “Set up a webhook for your meetings.”

   proof ↗⚑ flag

   Fellow—none0/10

   Fellow is a meeting-notes/AI assistant product with a REST API, webhooks, and MCP server, but nothing in the evidence describes scheduling recurring jobs or automated workflows (e.g., cron-like triggers, scheduled report generation, or recurring automation pipelines). Webhooks are event-driven, not schedule-based, and no docs mention recurring task orchestration.

   ⚑ flag

Calendar

1. product managerI connect Google or Outlook calendar once and control per-meeting-type rules for which meetings get captured automatically

   weight 3 · round to Fellow
   Fathom—none0/10

   The evidence pack contains no mention of connecting a Google/Outlook calendar or configuring per-meeting-type auto-capture rules; it only covers API/webhook/SDK/MCP integration and pricing tiers (bot vs bot-free capture, custom bot) with no calendar-workflow specifics.

   ⚑ flag

   Fellow~partialclaimed3/10

   Fellow's evidence shows organization-wide recording policies and manual per-meeting record/pause control, but there is no explicit mention of connecting a Google or Outlook calendar or of configuring rules that vary automatic capture by meeting type. Missing for 10: explicit calendar OAuth connection flow, documentation of per-meeting-type (e.g. 1:1 vs external) auto-capture rule configuration, and any UI/API evidence tying calendar events to capture policy.

   • [claimed-docs] “Set organization-wide policies for how meetings are recorded, accessed, and retained”
   • [claimed-docs] “Users choose when to record, pause, or resume capture when part of a conversation needs to stay off the record.”
   • [claimed-docs] “Standardize how meetings are captured, managed, and protected across every platform and format your teams use.”
   • [claimed-docs] “Set configurable retention policies, including zero-day retention, so data is handled according to your organization’s requirements.”

   proof ↗⚑ flag

2. founderI walk into each meeting prepped — the tool surfaces past meetings with the same people and a brief of open threads before the call

   weight 1 · round to Fellow
   Fathom—none0/10

   The evidence covers recording, transcription, summaries, search across calls, CRM sync, and MCP/API access, but nothing documents a proactive pre-meeting brief that surfaces past meetings with the same attendees or open threads ahead of a call — that specific calendar-workflow prep feature is absent from the pack.

   ⚑ flag

   Fellow~partialclaimed5/10

   Fellow makes meetings searchable via full transcript search and MCP/API queries like 'what did we decide in last month's standup', which supports surfacing past context with specific people, but there is no documented feature that proactively assembles a pre-meeting brief keyed to attendees or auto-surfaces prior meetings with the same people before a call. missing for 10: a dedicated pre-meeting briefing/prep feature that auto-detects attendees and compiles related past meetings and open action items ahead of the call, plus independent hands-on evidence of this workflow.

   • [claimed-docs] “Every conversation becomes searchable through a full transcript, giving your team instant access to past context whenever they need it.”
   • [claimed-docs] “Ask anything about your meetings - Get answers to questions like "What were my action items this week?" or "What did we decide in last month…”
   • [claimed-docs] “Ask anything about your meetings - Get answers to questions like "What were my action items this week?"”
   • [claimed-docs] “Your favorite AI chatbot like Claude, ChatGPT, or Cursor can now tap directly into your meeting recaps, notes, and action items”
   • [claimed-docs] “pass transcripts to an LLM for tailored recaps and action plans, the API gives you everything you need to make it happen”

   proof ↗⚑ flag

Capture

1. product managerThe notetaker reliably captures Zoom, Google Meet, and Microsoft Teams meetings, with recording where I want it

   weight 2 · round to Fellow
   Fathom~partialclaimed4/10

   Evidence confirms Fathom offers flexible recording capture options (bot-based or bot-free/beta) and a 'custom meeting bot' tier, addressing the 'recording where I want it' part of the story, but the evidence pack never explicitly names Zoom, Google Meet, or Microsoft Teams as supported platforms. Missing for 10: explicit platform-by-platform support confirmation for Zoom/Meet/Teams, reliability/uptime evidence, and independent hands-on corroboration of capture across all three platforms.

   • [claimed-docs] “Choice of bot-free (in beta) or bot capture”
   • [claimed-docs] “Capture notes your way – bot or no bot – so you can stay focused on the meeting”
   • [claimed-docs] “Custom meeting bot”

   proof ↗⚑ flag

   Fellow✓fullclaimed8/10

   Fellow explicitly documents recording capture across Zoom, Google Meet, Microsoft Teams (plus Slack Huddles and in-person), with flexibility to record via visible bot or bot-less desktop audio capture, and user control over when to record/pause/resume. This directly matches the PM's need for reliable, controllable capture across major platforms. Missing for 10: independent/hands-on verification of recording reliability across all three platforms and no third-party reviews confirming real-world capture accuracy.

   • [claimed-docs] “Fellow gives teams the flexibility to record with a visible bot or without one — capturing audio directly from the desktop”
   • [claimed-docs] “Fellow gives teams the flexibility to record with a visible bot or without one — capturing audio directly from the desktop across Zoom, Goog…”
   • [claimed-docs] “Users choose when to record, pause, or resume capture when part of a conversation needs to stay off the record.”
   • [claimed-docs] “Standardize how meetings are captured, managed, and protected across every platform and format your teams use.”

   proof ↗⚑ flag

2. founderCapture and transcribe meetings without a visible bot joining the call — audio is captured from my device so external participants see nothing extra

   weight 3 · round to Fellow
   Fathom~partialclaimed5/10

   Fathom's pricing page explicitly advertises a 'bot-free (in beta)' capture option alongside bot capture, and homepage marketing states "Capture notes your way – bot or no bot – so you can stay focused on the meeting," indicating device-based audio capture without a visible bot joining the call. However, this is labeled beta with no technical documentation on how bot-free capture works, no confirmation it captures external participants' audio without their knowledge, and no independent/hands-on corroboration of the feature working as described. Missing for 10: technical docs on bot-free capture mechanism, confirmation of transcription quality/reliability in bot-free mode, independent user reports validating the beta feature works as claimed.

   • [claimed-docs] “Choice of bot-free (in beta) or bot capture”
   • [claimed-docs] “Capture notes your way – bot or no bot – so you can stay focused on the meeting”

   proof ↗⚑ flag

   Fellow✓fullclaimed8/10

   Fellow explicitly documents botless recording that captures audio directly from the desktop across Zoom, Meet, Teams, Slack Huddles and in-person meetings, giving teams flexibility to record with or without a visible bot, plus transcript generation and search from the captured audio. Missing for 10: independent/hands-on confirmation that external participants truly see nothing extra during botless capture, and detail on how desktop audio capture technically avoids appearing in participant lists.

   • [claimed-docs] “Fellow gives teams the flexibility to record with a visible bot or without one — capturing audio directly from the desktop”
   • [claimed-docs] “Fellow gives teams the flexibility to record with a visible bot or without one — capturing audio directly from the desktop across Zoom, Goog…”
   • [claimed-docs] “Every conversation becomes searchable through a full transcript, giving your team instant access to past context whenever they need it.”
   • [claimed-docs] “Users choose when to record, pause, or resume capture when part of a conversation needs to stay off the record.”

   proof ↗⚑ flag

3. founderRecord and transcribe in-person conversations from a mobile app, and those notes land in the same searchable workspace

   weight 2 · round drawn
   Fathom—none0/10

   Evidence pack describes Fathom as a virtual-meeting recorder (bot or bot-free capture of online calls) with API/webhook/MCP integrations, but nothing mentions a mobile app or capturing in-person, non-virtual conversations.

   • [claimed-docs] “Choice of bot-free (in beta) or bot capture”
   • [claimed-docs] “Capture notes your way – bot or no bot – so you can stay focused on the meeting”
   • [claimed-docs] “Automatically monitor key topics so you never miss critical moments”

   proof ↗⚑ flag

   Fellow—none0/10

   Evidence shows Fellow can capture in-person meetings via desktop audio capture (fellow-docs-20) and makes transcripts searchable (fellow-docs-21), but there is no mention anywhere in the pack of a mobile app for recording conversations — all capture references point to desktop/bot-based capture during scheduled meetings. Missing for 10: any documentation of a Fellow mobile app, mobile recording capability, or evidence that in-person capture happens via phone rather than laptop/desktop.

   • [claimed-docs] “Fellow gives teams the flexibility to record with a visible bot or without one — capturing audio directly from the desktop across Zoom, Goog…”
   • [claimed-docs] “Every conversation becomes searchable through a full transcript, giving your team instant access to past context whenever they need it.”
   • [claimed-docs] “Users choose when to record, pause, or resume capture when part of a conversation needs to stay off the record.”

   proof ↗⚑ flag

Integrations

1. sales leadMeeting notes and summaries sync automatically onto the right contact and deal records in my CRM (HubSpot, Salesforce, Attio)

   weight 3 · round to Fathom
   Fathom~partialclaimed5/10

   Fathom's pricing page explicitly advertises 'CRM field sync, updating records after meetings automatically' and Deal View summarizing insights, indicating native CRM record sync exists, but the evidence pack gives no detail on which CRMs (HubSpot, Salesforce, Attio explicitly named) are supported, how contact/deal matching works, or setup/configuration steps, and no independent/hands-on confirmation of reliability. missing for 10: named support for HubSpot/Salesforce/Attio specifically, technical documentation of the CRM sync mechanism, and independent verification that notes land on the correct contact/deal records.

   • [claimed-docs] “CRM field sync, updating records after meetings automatically”
   • [claimed-docs] “Deal View summarizing insights”

   proof ↗⚑ flag

   Fellow—none0/10

   The evidence describes Fellow's Developer API, webhooks, and MCP server for accessing transcripts/notes/action items, but there is no mention of any native integration or automatic sync with HubSpot, Salesforce, or Attio contact/deal records. A sales-focused meeting tool could plausibly ship such CRM sync, so the axis applies, but no evidence confirms it exists.

   • [claimed-docs] “The Developer API opens that data to you: transcripts, structured notes, and more, all available through standard REST calls.”
   • [claimed-docs] “Fellow sends an HTTP POST request to the URL you specify with details about the event.”
   • [claimed-docs] “Webhooks allow you to receive real-time notifications when events occur in Fellow.”
   • [claimed-docs] “pass transcripts to an LLM for tailored recaps and action plans, the API gives you everything you need to make it happen”

   proof ↗⚑ flag

2. product managerNotes flow into the tools where work happens — Slack channels, Notion pages, and thousands of apps via Zapier

   weight 2 · round drawn
   Fathom—none0/10

   The evidence pack shows generic developer infrastructure (REST API, webhooks, SDKs, MCP server for AI assistants) but contains no mention of native Slack, Notion, or Zapier integrations, nor a listed Zapier app — the specific 'thousands of apps' claim in the story has no supporting citation.

   ⚑ flag

   Fellow—none0/10

   The evidence pack only documents a generic Developer API, webhooks, and MCP server — there is no mention of native Slack, Notion, or Zapier integrations or an app marketplace listing that would let notes flow automatically into those specific tools.

   ⚑ flag

Memory

1. product managerAsk questions in natural language across my whole meeting history ("what did we decide about pricing?") and get answers with sources

   weight 2 · round to Fellow
   Fathom~partialprobed6/10

   Fathom advertises a 'Conversational meeting assistant' and 'search across calls' feature, and its official MCP server explicitly lets you bring 'your meeting data...inside ChatGPT, Claude, and more,' enabling natural-language queries over meeting history via a connected AI assistant. However, there's no first-party documentation describing how the built-in conversational assistant answers questions with cited sources, nor detail on cross-meeting recall depth or accuracy. Missing for 10: documented answer format/sourcing for the conversational assistant, evidence of true whole-history semantic search (vs. per-meeting), and independent/hands-on verification of source-accurate answers.

   • [claimed-docs] “Conversational meeting assistant”
   • [claimed-docs] “Clips, playlists + search across calls”
   • [claimed-docs] “Your meeting data, now inside ChatGPT, Claude, and more”
   • [claimed-docs] “Fathom now offers an official MCP (Model Context Protocol) server, allowing you to connect your Fathom meeting data to AI assistants like Ch…”
   • [claimed-docs] “Connect Fathom to any MCP-compatible tool using the server URL below, then authenticate to access your meeting data.”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the official hosted MCP server https://api.fathom.ai/mcp returned H…”

   proof ↗⚑ flag

   Fellow~partialprobed7/10

   Fellow's MCP server explicitly supports natural-language queries across meeting history (e.g. 'What did we decide in last month's standup?') and searchable full transcripts back the answers, with a runtime probe confirming the hosted MCP endpoint is live and functional. However, the evidence never explicitly describes source citations/links accompanying answers, only that transcripts and notes are the underlying data. Missing for 10: explicit documentation that MCP answers include citations/sources to specific meetings, and independent hands-on confirmation of answer quality/accuracy.

   • [claimed-docs] “Ask anything about your meetings - Get answers to questions like "What were my action items this week?"”
   • [claimed-docs] “Fellow's Model Context Protocol (MCP) Server allows you to ask your AI Assistant about your meetings, without needing to write any code.”
   • [claimed-docs] “Ask anything about your meetings - Get answers to questions like "What were my action items this week?" or "What did we decide in last month…”
   • [claimed-docs] “Every conversation becomes searchable through a full transcript, giving your team instant access to past context whenever they need it.”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to Fellow's hosted MCP server https://fellow.app/mcp returned HTTP 401…”
   • [probe] “official MCP server documented at https://developers.fellow.ai/reference/mcp-server”

   proof ↗⚑ flag

2. product managerSearch across every past meeting — transcripts, summaries, and notes — and jump to the exact moment something was said

   weight 3 · round to Fellow
   Fathom~partialclaimed5/10

   Fathom advertises 'Clips, playlists + search across calls' and keyword alerts/highlights, plus transcripts/summaries accessible via API, suggesting cross-meeting search exists, but the evidence never shows a concrete product UI for searching all transcripts/notes and jumping to a timestamped moment. missing for 10: a documented search UI/feature description showing full-text search across all past meetings with timestamp jump-to, independent/hands-on confirmation of search accuracy or scope, and detail on whether notes (not just transcripts/summaries) are indexed.

   • [claimed-docs] “Clips, playlists + search across calls”
   • [claimed-docs] “Collaboration using comments, folders, keyword alerts, + more”
   • [claimed-docs] “Automatically monitor key topics so you never miss critical moments”
   • [claimed-docs] “If you send `destination_url`, the endpoint will behave in an asynchronous manner. If you do not send `destination_url`, the endpoint will r…”
   • [claimed-docs] “Get summary ... Either the destination URL for where we'll POST the call summary, or the summary for the recording.”

   proof ↗⚑ flag

   Fellow✓fullprobed7/10

   Fellow explicitly advertises full-transcript search ('Every conversation becomes searchable through a full transcript') and its MCP server exposes tools like search_meetings and get_meeting_transcript for asking natural-language questions like 'what did we decide in last month's standup', confirmed live via a runtime probe. Missing for 10: explicit UI evidence of clicking a search result to jump to the exact timestamp/moment in a recording, and independent (non-vendor) confirmation of search accuracy across large history.

   • [claimed-docs] “Every conversation becomes searchable through a full transcript, giving your team instant access to past context whenever they need it.”
   • [claimed-docs] “Ask anything about your meetings - Get answers to questions like "What were my action items this week?"”
   • [claimed-docs] “Ask anything about your meetings - Get answers to questions like "What were my action items this week?" or "What did we decide in last month…”
   • [claimed-docs] “Your favorite AI chatbot like Claude, ChatGPT, or Cursor can now tap directly into your meeting recaps, notes, and action items”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to Fellow's hosted MCP server https://fellow.app/mcp returned HTTP 401…”
   • [probe] “official MCP server documented at https://developers.fellow.ai/reference/mcp-server”

   proof ↗⚑ flag

Summaries

1. product managerAction items with owners are automatically extracted from the conversation and collected somewhere I can track them

   weight 3 · round drawn
   Fathom✓fullprobed8/10

   Fathom automatically generates AI action items (fathom-docs-28) and provides webhooks/API that can include action items in structured data delivered to a destination URL (fathom-docs-22, fathom-docs-45), giving PMs a trackable, centralized feed of action items with meeting context. Core capability is well documented and includes runtime confirmation the API is live; missing for 10: explicit evidence of an in-app dashboard specifically tracking action items by owner over time (e.g., a dedicated action-items view) beyond the webhook/API delivery mechanism.

   • [claimed-docs] “AI generated action items”
   • [claimed-docs] “Webhooks will send your meeting data (optionally including the summary, transcript, and action items) to a URL of your choice.”
   • [claimed-docs] “Create a webhook to receive new meeting content. At least one of `include_transcript`, `include_crm_matches`, `include_summary`, or `include…”
   • [claimed-docs] “If you send `destination_url`, the endpoint will behave in an asynchronous manner. If you do not send `destination_url`, the endpoint will r…”
   • [claimed-docs] “Get summary ... Either the destination URL for where we'll POST the call summary, or the summary for the recording.”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless GET to the documented REST base https://api.fathom.ai/external/v1/meetings returned HTTP 401 ca…”

   proof ↗⚑ flag

   Fellow✓fullclaimed8/10

   Fellow automatically generates AI action items with assignees from meeting conversations (fellow-docs-23), and these are collected/trackable via the app and API's get_action_items endpoint with filters like assigned_to_me/assigned_to_others (fellow-docs-5, fellow-docs-19), plus surfaced via MCP queries like 'what were my action items' (fellow-docs-32). Missing for 10: no independent/hands-on evidence confirming extraction accuracy or owner-assignment reliability beyond vendor docs.

   • [claimed-docs] “You automatically receive a clear meeting summary, suggested AI action items, decisions, and topic-based minutes for every meeting.”
   • [claimed-docs] “List action items with optional filters and pagination.”
   • [claimed-docs] “assigned_to_me: Only action items assigned to the authenticated user\n- assigned_to_others: Only action items the user can edit, assigned to…”
   • [claimed-docs] “Ask anything about your meetings - Get answers to questions like "What were my action items this week?" or "What did we decide in last month…”
   • [claimed-docs] “pass transcripts to an LLM for tailored recaps and action plans, the API gives you everything you need to make it happen”

   proof ↗⚑ flag

2. sales leadShape the notes with custom templates or saved prompts per meeting type (discovery call, 1:1, standup) instead of one generic format

   weight 2 · round drawn
   Fathom—none0/10

   Evidence shows AI summaries, action items, and 'advanced/custom call summaries' as a pricing feature, but nothing describes per-meeting-type custom templates or saved prompts (e.g., discovery call vs 1:1 vs standup) that a sales lead could configure and reuse.

   • [claimed-docs] “AI summaries instantly available after your call”
   • [claimed-docs] “Advanced call summaries, including custom summaries”

   proof ↗⚑ flag

   Fellow—none0/10

   The evidence pack covers Fellow's API, MCP server, webhooks, recording controls, and retention policies, but contains no mention of customizable note templates or saved prompts tied to meeting type (discovery call, 1:1, standup). This is a fair axis for a meeting-notes product, but no evidence supports it.

   ⚑ flag

3. sales leadThe tool drafts my follow-up email from the meeting so I can review and send it in a couple of clicks

   weight 1 · round drawn
   Fathom—none0/10

   Fathom's evidence pack covers AI summaries, action items, CRM sync, and conversational meeting assistant features, but nowhere mentions drafting a follow-up email from a meeting for review-and-send. This is a plausible capability for a meeting-notes tool, but no evidence supports it.

   ⚑ flag

   Fellow—none0/10

   Fellow's evidence covers meeting summaries, action items, transcripts, and an API/MCP server for querying meeting data and even passing transcripts to an LLM for 'tailored recaps and action plans,' but there is no evidence of a native feature that drafts a follow-up email for one-click review and send — that would require custom API integration, not a documented built-in capability.

   • [claimed-docs] “You automatically receive a clear meeting summary, suggested AI action items, decisions, and topic-based minutes for every meeting.”
   • [claimed-docs] “pass transcripts to an LLM for tailored recaps and action plans, the API gives you everything you need to make it happen”
   • [claimed-docs] “Ask anything about your meetings - Get answers to questions like "What were my action items this week?"”
   • [claimed-docs] “Ask anything about your meetings - Get answers to questions like "What were my action items this week?" or "What did we decide in last month…”

   proof ↗⚑ flag

4. product managerI get a structured summary right after each meeting — key points, decisions, and next steps — good enough to share without editing

   weight 3 · round to Fellow
   Fathom✓fullclaimed7/10

   Fathom's core product delivers AI-generated call summaries and action items immediately after calls (fathom-docs-40, fathom-docs-28, fathom-docs-47), retrievable via the get-summary API endpoint (fathom-docs-27/37), matching the PM's need for a shareable post-meeting summary. Missing for 10: explicit documentation of 'decisions' as a distinct summary field and independent/hands-on evidence of summary quality being 'good enough to share without editing'.

   • [claimed-docs] “AI summaries instantly available after your call”
   • [claimed-docs] “AI generated action items”
   • [claimed-docs] “Advanced call summaries, including custom summaries”
   • [claimed-docs] “Get summary ... Either the destination URL for where we'll POST the call summary, or the summary for the recording.”
   • [claimed-docs] “Either the destination URL for where we'll POST the call summary, or the summary for the recording.”

   proof ↗⚑ flag

   Fellow✓fullclaimed8/10

   Fellow's core product docs state you automatically receive a clear meeting summary, suggested AI action items, decisions, and topic-based minutes for every meeting, directly matching the story of a structured post-meeting summary. Missing for 10: independent/hands-on user reviews confirming the summary quality is share-ready without edits, and no detail on editing workflow before sharing.

   • [claimed-docs] “You automatically receive a clear meeting summary, suggested AI action items, decisions, and topic-based minutes for every meeting.”
   • [claimed-docs] “Every conversation becomes searchable through a full transcript, giving your team instant access to past context whenever they need it.”
   • [claimed-docs] “Fellow gives teams the flexibility to record with a visible bot or without one — capturing audio directly from the desktop”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Fathom~partialprobed5/10

   Fathom's REST API/SDKs cover core meeting data (list meetings, transcripts, summaries, recordings, webhooks, users/permissions) confirmed live via runtime probes, so a solid subset of UI functionality is API-accessible. However, many UI/pricing-page features—CRM field sync, Deal View, coaching metrics/scorecards, playlists, comments/folders/keyword alerts, custom bot configuration, SSO/SCIM—have no corresponding documented API endpoints in the evidence, so full UI parity is not demonstrated. Missing for 10: API endpoints for CRM sync, Deal View, coaching/scorecards, playlists/collaboration features, and admin SSO/SCIM management.

   • [claimed-docs] “List the 10 most recent meetings recorded by you or shared to your team.”
   • [claimed-docs] “Added download recording endpoint.”
   • [claimed-docs] “Added users and permissions endpoint.”
   • [claimed-docs] “Webhooks will send your meeting data (optionally including the summary, transcript, and action items) to a URL of your choice.”
   • [claimed-docs] “Get started in minutes with our official SDKs. They handle authentication, pagination, error handling, and all the complex stuff so you can …”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless GET to the documented REST base https://api.fathom.ai/external/v1/meetings returned HTTP 401 ca…”
   • [probe] “PROBE runtime (recorded 2026-09-05): Fathom publishes a machine-readable OpenAPI 3.1.1 spec ('Fathom External API', versioned 1.0.0) at http…”
   • [claimed-docs] “CRM field sync, updating records after meetings automatically”
   • [claimed-docs] “Deal View summarizing insights”
   • [claimed-docs] “Coaching metrics & AI scorecards”
   • [claimed-docs] “SSO & SCIM provisioning”

   proof ↗⚑ flag

   Fellow~partialprobed5/10

   Fellow's Developer API exposes meaningful UI-parallel functionality (list recordings, list action items, append note agenda, webhooks, MCP conversational access) but the evidence only covers a subset of read/limited-write operations, not full parity with UI actions like recording controls, retention policy configuration, keyword tracking, or admin dashboard settings. missing for 10: API coverage for recording start/pause/resume, retention/compliance policy management via API, keyword tracking configuration, and broader write/update operations beyond appending agenda text.

   • [claimed-docs] “The Developer API opens that data to you: transcripts, structured notes, and more, all available through standard REST calls.”
   • [claimed-docs] “List recordings with optional filters and pagination.”
   • [claimed-docs] “List action items with optional filters and pagination.”
   • [claimed-docs] “Add Fellow Markdown to the end of a note's agenda, leaving the rest of the content in place.”
   • [claimed-docs] “Webhooks allow you to receive real-time notifications when events occur in Fellow.”
   • [claimed-docs] “pass transcripts to an LLM for tailored recaps and action plans, the API gives you everything you need to make it happen”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.fellow.ai/openapi.json, https://developers.fellow.ai/swagger.json, https://develo…”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   Fathom~partialprobed6/10

   Fathom's REST API and SDKs let a user programmatically list all meetings, fetch transcripts/summaries, and download recordings, giving JSON/media exports usable outside the platform (fathom-docs-2, fathom-docs-8, fathom-docs-26, fathom-docs-27, fathom-probe-rt-3). However there is no documented one-click 'export all my data' bulk tool or explicit data-portability/account-deletion guarantee, so a user must build their own export script via the API. Missing for 10: a first-party bulk export/archival feature, explicit data-portability policy, and independent confirmation that full historical data (not just per-meeting calls) can be retrieved and account fully closed out.

   • [claimed-docs] “List the 10 most recent meetings recorded by you or shared to your team.”
   • [claimed-docs] “Added download recording endpoint.”
   • [claimed-docs] “If you send `destination_url`, the endpoint will behave in an asynchronous manner. If you do not send `destination_url`, the endpoint will r…”
   • [claimed-docs] “Get summary ... Either the destination URL for where we'll POST the call summary, or the summary for the recording.”
   • [claimed-docs] “Get started in minutes with our official SDKs. They handle authentication, pagination, error handling, and all the complex stuff so you can …”
   • [probe] “PROBE runtime (recorded 2026-09-05): Fathom publishes a machine-readable OpenAPI 3.1.1 spec ('Fathom External API', versioned 1.0.0) at http…”

   proof ↗⚑ flag

   Fellow~partialclaimed6/10

   Fellow's Developer API exposes transcripts, notes, action items, and recordings via standard REST calls, and the Super Admin API can 'retrieve, export, and delete data across the entire workspace' for Enterprise admins, giving a path to full data export. However, there is no explicit documentation of a bulk 'export everything' feature, no stated output format guarantees (e.g., JSON/CSV schema for full account export), and no independent verification of completeness. Missing for 10: a documented one-click/bulk full-account export tool, explicit open-format (JSON/CSV) export spec, and independent confirmation that all data types are covered.

   • [claimed-docs] “The Developer API opens that data to you: transcripts, structured notes, and more, all available through standard REST calls.”
   • [claimed-docs] “List recordings with optional filters and pagination.”
   • [claimed-docs] “List action items with optional filters and pagination.”
   • [claimed-docs] “Fellow’s Super Admin API lets designated Enterprise‑plan administrators retrieve, export, and delete data across the entire workspace”
   • [claimed-docs] “pass transcripts to an LLM for tailored recaps and action plans, the API gives you everything you need to make it happen”

   proof ↗⚑ flag

Pricing

1. founderStart free and see exactly what each paid tier costs and adds — no "talk to sales" wall for basic use

   weight 2 · round to Fathom
   Fathom~partialclaimed4/10

   The pricing page evidence lists many tier-specific features (CRM sync, coaching metrics, SSO/SCIM, custom bot, etc.) implying a public pricing/feature comparison exists, but no evidence shows actual dollar amounts, a free tier definition, or confirmation that basic use avoids a 'talk to sales' gate for enterprise features like SSO/SCIM. Missing for 10: explicit price figures per tier, confirmation of a self-serve free plan, and absence of a sales-contact requirement for advanced tiers.

   • [claimed-docs] “CRM field sync, updating records after meetings automatically”
   • [claimed-docs] “Deal View summarizing insights”
   • [claimed-docs] “Coaching metrics & AI scorecards”
   • [claimed-docs] “Custom meeting bot”
   • [claimed-docs] “SSO & SCIM provisioning”

   proof ↗⚑ flag

   Fellow—none0/10

   The evidence pack only mentions two feature names ('Keyword tracking', 'Transcript redaction') from the pricing page but contains no details on free tier availability, tier pricing, or whether higher tiers require contacting sales. No evidence supports or contradicts a transparent self-serve pricing structure.

   • [claimed-docs] “Keyword tracking”
   • [claimed-docs] “Transcript redaction”

   proof ↗⚑ flag

Privacy

1. it adminThe product ships real consent features — participant notifications, in-meeting disclosure, or admin-enforced transparency — not just a policy PDF

   weight 3 · round drawn
   Fathom—none0/10

   The evidence pack covers API/SDK/webhook/MCP integration and pricing tiers (bot vs bot-free capture, SSO/SCIM) but contains no mention of participant consent notifications, in-meeting recording disclosure banners, or admin-enforced transparency controls — the core capabilities this story asks about. As a meeting-recording product, this axis clearly applies, but no evidence shows it being delivered.

   ⚑ flag

   Fellow—none0/10

   The evidence shows admin-side policy controls (retention settings, org-wide recording/access policies) and user-side recording controls, but nothing describing participant-facing consent mechanisms such as in-meeting recording disclosure banners, automated participant notifications when a bot joins, or admin-enforced transparency toward attendees. Notably, Fellow explicitly supports recording 'without a visible bot' by capturing desktop audio directly, which underscores the absence of a documented notification/disclosure mechanism rather than confirming one.

   • [claimed-docs] “Fellow gives teams the flexibility to record with a visible bot or without one — capturing audio directly from the desktop”
   • [claimed-docs] “Fellow gives teams the flexibility to record with a visible bot or without one — capturing audio directly from the desktop across Zoom, Goog…”
   • [claimed-docs] “Users choose when to record, pause, or resume capture when part of a conversation needs to stay off the record.”
   • [claimed-docs] “Set organization-wide policies for how meetings are recorded, accessed, and retained”
   • [claimed-docs] “Set configurable retention policies, including zero-day retention, so data is handled according to your organization’s requirements.”
   • [claimed-docs] “Standardize how meetings are captured, managed, and protected across every platform and format your teams use.”

   proof ↗⚑ flag

2. it adminThe vendor documents whether meeting data trains AI models and gives my org an enforceable opt-out, alongside SOC 2 / HIPAA posture

   weight 2 · round drawn
   Fathom—none0/10

   No evidence in the pack addresses AI training data usage policy, opt-out mechanisms, or SOC 2/HIPAA compliance posture; the docs cover API access, webhooks, SDKs, and MCP integration only. missing for 10: explicit documentation on whether meeting data is used to train AI models, an enforceable opt-out mechanism for orgs, and SOC 2/HIPAA compliance attestations.

   ⚑ flag

   Fellow—none0/10

   Evidence shows retention policies and org-wide recording/access controls, but there is no documentation addressing whether meeting data is used to train AI models, no explicit opt-out mechanism for AI training, and no mention of SOC 2 or HIPAA compliance posture anywhere in the pack.

   • [claimed-docs] “Set organization-wide policies for how meetings are recorded, accessed, and retained”
   • [claimed-docs] “Set configurable retention policies, including zero-day retention, so data is handled according to your organization’s requirements.”
   • [claimed-docs] “Standardize how meetings are captured, managed, and protected across every platform and format your teams use.”

   proof ↗⚑ flag

3. it adminSet retention policies — auto-delete transcripts and recordings on a schedule — and permanently erase data on demand

   weight 2 · round to Fellow
   Fathom—none0/10

   No evidence in the pack mentions retention policies, scheduled auto-deletion of transcripts/recordings, or an on-demand data erasure mechanism for admins; evidence only covers API access, webhooks, SDKs, MCP connectors, and pricing tiers.

   ⚑ flag

   Fellow~partialclaimed6/10

   Fellow documents configurable retention policies including zero-day retention, and the Super Admin API allows retrieving, exporting, and deleting data across the workspace, which supports on-demand erasure. However, there's no explicit documentation of a scheduled auto-delete mechanism for transcripts/recordings specifically or a UI/API for setting retention schedules with confirmation of enforcement. Missing for 10: detailed retention policy configuration UI/API docs, evidence of scheduled automated deletion execution, and independent confirmation that erasure requests are honored end-to-end.

   • [claimed-docs] “Set configurable retention policies, including zero-day retention, so data is handled according to your organization’s requirements.”
   • [claimed-docs] “Fellow’s Super Admin API lets designated Enterprise‑plan administrators retrieve, export, and delete data across the entire workspace”
   • [claimed-docs] “Set organization-wide policies for how meetings are recorded, accessed, and retained”
   • [claimed-docs] “Standardize how meetings are captured, managed, and protected across every platform and format your teams use.”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Fathom—none0/10

   No evidence in the pack mentions data residency, regional storage options, or geographic control over where Fathom stores data; all evidence concerns API/SDK/MCP/webhook functionality and pricing tiers. missing for 10: any mention of region selection, data residency options, or storage location controls.

   ⚑ flag

   Fellow—none0/10

   No evidence pack item mentions data residency, regional data storage options, or geographic data center selection; retention policies and admin controls are covered but region choice is not addressed.

   ⚑ flag

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

   weight 3 · round drawn
   Fathom—none0/10

   No evidence in the pack addresses AI-training data usage, opt-out settings, or data-privacy policies regarding model training; the evidence is entirely about API/SDK/MCP integration features.

   ⚑ flag

   Fellow—none0/10

   The evidence pack covers retention policies, redaction, recording controls, and API/MCP access, but contains no statement about whether Fellow uses customer data to train AI models or any opt-out mechanism for AI training.

   ⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round to Fellow
   Fathom—none0/10

   The evidence pack covers API access, webhooks, MCP integration, and SDKs, but contains no mention of data retention policies, deletion controls, or user ability to delete recordings/transcripts/data. No documentation of retention settings, data export/purge tools, or deletion endpoints is present.

   ⚑ flag

   Fellow✓fullclaimed8/10

   Fellow documents configurable retention policies including zero-day retention, org-wide policies on how data is recorded/accessed/retained, and Super Admin API to retrieve, export, and delete data across the entire workspace, directly addressing retention/deletion control. missing for 10: independent/hands-on verification of deletion actually purging data end-to-end and clearer per-user (non-admin) self-service deletion controls.

   • [claimed-docs] “Set configurable retention policies, including zero-day retention, so data is handled according to your organization’s requirements.”
   • [claimed-docs] “Set organization-wide policies for how meetings are recorded, accessed, and retained”
   • [claimed-docs] “Fellow’s Super Admin API lets designated Enterprise‑plan administrators retrieve, export, and delete data across the entire workspace”
   • [claimed-docs] “Standardize how meetings are captured, managed, and protected across every platform and format your teams use.”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Fathom—none0/10

   No evidence pack item mentions telemetry, usage tracking, analytics opt-out, or privacy settings of that kind; documentation covers API, webhooks, MCP, and pricing features only.

   ⚑ flag

   Fellow—none0/10

   No evidence pack item discusses telemetry opt-out or usage tracking controls for AI-native users; retention/recording policies are mentioned but not telemetry/usage-tracking opt-out specifically.

   ⚑ flag

Sharing

1. sales leadCut a soundbite or highlight clip from a call and share that moment instead of the whole recording

   weight 1 · round to Fathom
   Fathom~partialclaimed5/10

   Pricing page mentions 'Clips, playlists + search across calls' and 'Playlists of highlights from meetings', indicating Fathom supports creating and sharing highlight clips, but there's no documentation on how clipping/sharing actually works (UI flow, sharing mechanism, permissions). Missing for 10: detailed docs or hands-on evidence of the clip-creation workflow, sharing a clip link vs whole recording, and any independent corroboration.

   • [claimed-docs] “Clips, playlists + search across calls”
   • [claimed-docs] “Playlists of highlights from meetings”

   proof ↗⚑ flag

   Fellow—none0/10

   Evidence covers transcripts, recordings listing, action items, webhooks, and MCP access, but nothing describes clipping/highlighting a soundbite from a call or sharing a short excerpt instead of the full recording.

   ⚑ flag

2. it adminSharing is controlled — private-by-default notes, granular link/folder/workspace permissions, and admin visibility into what's shared

   weight 2 · round to Fellow
   Fathom~partialclaimed4/10

   Fathom docs mention admin-configurable view permissions for shared meetings and a dedicated users/permissions API endpoint, plus folders as an organizational feature, suggesting some admin control over sharing. However there's no evidence of private-by-default notes, granular link-level or workspace-level permission settings, or a dedicated admin dashboard for visibility into what's shared. missing for 10: private-by-default note settings, granular link-sharing permissions, workspace-level permission tiers, an admin audit/visibility dashboard for shared content.

   • [claimed-docs] “Admins can access all users' shared meetings by configuring View permissions”
   • [claimed-docs] “Added users and permissions endpoint.”
   • [claimed-docs] “Collaboration using comments, folders, keyword alerts, + more”
   • [claimed-docs] “SSO & SCIM provisioning”

   proof ↗⚑ flag

   Fellow~partialclaimed5/10

   Fellow offers org-wide retention/recording policies, workspace admin control over MCP tool access, and Super Admin API for workspace-wide visibility, which addresses some admin oversight needs. However, there is no explicit evidence of private-by-default note settings, granular link/folder-level sharing permissions, or a dedicated sharing-audit dashboard for admins. missing for 10: private-by-default note defaults, granular link/folder/workspace permission controls, admin visibility/audit log specifically for shared content.

   • [claimed-docs] “As a workspace admin, you decide which MCP tools your members’ AI assistants can use.”
   • [claimed-docs] “Set organization-wide policies for how meetings are recorded, accessed, and retained”
   • [claimed-docs] “Fellow’s Super Admin API lets designated Enterprise‑plan administrators retrieve, export, and delete data across the entire workspace”
   • [claimed-docs] “Build admin dashboards that display data from a specific user's perspective”
   • [claimed-docs] “Set configurable retention policies, including zero-day retention, so data is handled according to your organization’s requirements.”
   • [claimed-docs] “Standardize how meetings are captured, managed, and protected across every platform and format your teams use.”

   proof ↗⚑ flag

Transcription

1. founderRun meetings in languages other than English — transcription and summaries support many languages and handle language switching

   weight 2 · round drawn
   Fathom—none0/10

   The evidence pack contains no mention of multi-language transcription/summary support or language-switching handling anywhere in Fathom's docs, changelog, or pricing pages — all references focus on API access, webhooks, MCP integration, and English-oriented feature descriptions.

   ⚑ flag

   Fellow—none0/10

   No evidence in the pack mentions multi-language support, non-English transcription, or handling language switching within meetings; all citations focus on API access, MCP integration, and English-language feature descriptions.

   ⚑ flag

2. product managerThe transcript attributes words to the right named speakers (diarization plus real name matching), not just "Speaker 1/2"

   weight 3 · round drawn
   Fathom—none0/10

   No evidence in the pack addresses diarization or speaker-name matching in transcripts; the pack only covers API access, webhooks, MCP integration, and pricing tiers. This is a fair axis for a meeting-transcription product, but nothing here confirms accurate speaker attribution or real-name matching.

   ⚑ flag

   Fellow—none0/10

   The evidence pack covers API access, webhooks, MCP server, and recording/retention features, but nowhere mentions speaker diarization or matching transcript segments to real named speakers versus generic labels like 'Speaker 1/2'.

   ⚑ flag

3. product managerThe vendor documents how transcription actually works and its quality (models, accuracy claims, known limits) rather than just saying "AI-powered"

   weight 3 · round drawn
   Fathom—none0/10

   The evidence pack contains extensive docs on API access, webhooks, MCP integration, and pricing tiers, but nothing about transcription models, accuracy claims, language support, or known limitations of the transcription/AI engine itself — everything is marketed generically as 'AI summaries' or 'AI generated action items' without technical detail.

   ⚑ flag

   Fellow—none0/10

   The evidence pack covers API access, MCP server, webhooks, and recording/retention features, but contains no documentation of the transcription model used, accuracy benchmarks, or known limitations (e.g., accent/language handling, error rates). This axis clearly applies to a transcription product, but no such technical/accuracy disclosure is evidenced.

   ⚑ flag