Fireflies.ai vs Fathom

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
   Fireflies.ai~partialprobed4/10

   Fireflies exposes a documented GraphQL API (bearer-token auth) with transcript/action-item queries that a developer or agent could use to push action items into an external tracker, and MCP servers exist for docs/data access, but there is no evidence of native, first-party integrations, webhooks, or automations targeting Linear, Jira, or Asana specifically. missing for 10: documented webhooks, native Linear/Jira/Asana connectors, or automation templates that file action items into a project tracker.

   • [claimed-docs] “The transcripts query is designed to fetch a list of transcripts against input arguments.”
   • [claimed-docs] “The transcript query is designed to fetch details associated with a specific transcript ID.”
   • [claimed-docs] “The Fireflies API is built on top of GraphQL... This API allows you to retrieve exactly the data you need in a structured format.”
   • [claimed-docs] “We use a standard bearer token authentication mechanism.”
   • [probe] “PROBE runtime (recorded 2026-09-05): a keyless GraphQL query POSTed to the live endpoint https://api.fireflies.ai/graphql returned the docum…”
   • [claimed-docs] “Get detailed notes, action items, and customized summaries instantly after every meeting.”

   proof ↗⚑ flag

   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

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 to Fathom
   Fireflies.ai✓fullprobed8/10

   Fireflies documents and runtime evidence confirm a live, OAuth-gated hosted MCP server (api.fireflies.ai/mcp) that lets AI tools query meeting data with 'no API keys required,' matching the OAuth/no-glue-code requirement, and this is corroborated by a real runtime probe returning the expected OAuth challenge. Missing for 10: explicit documentation naming Claude (only ChatGPT's Deep Research is called out) and explicit confirmation that action-item queries specifically (not just transcripts/search) are exposed via the MCP tool surface rather than only the separate GraphQL API.

   • [claimed-docs] “Once connected, you can query your Fireflies data directly through ChatGPT's Deep Research feature.”
   • [claimed-docs] “Compare the objections mentioned in calls with Enterprise prospects versus SMB prospects this quarter”
   • [claimed-docs] “You can now connect Fireflies to ChatGPT using our OAuth integration—no API keys required.”
   • [probe] “official MCP server documented at https://guide.fireflies.ai/articles/8272956938-learn-about-the-fireflies-mcp-server-model-context-protocol”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the hosted MCP server https://api.fireflies.ai/mcp returned HTTP 40…”

   proof ↗⚑ flag

   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

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
   Fireflies.ai✓fullprobed8/10

   Fireflies documents a self-serve GraphQL API with bearer-token API keys (generated via Integrations UI), and dedicated queries for transcripts, transcript details, and audio upload, with runtime probes confirming the live endpoint enforces the documented auth scheme. Action items and summaries are surfaced as part of the transcript/meeting data model referenced in docs and marketing copy. missing for 10: no explicit documented query/field example returning action items or AI summary output specifically, and no independent third-party developer report confirming successful end-to-end script usage beyond docs and probes.

   • [claimed-docs] “Navigate to the Integrations section 3. Click on Fireflies API 4. Copy and store your API key securely”
   • [claimed-docs] “We use a standard bearer token authentication mechanism. This means that to make authorized requests to the API, you must include an `Author…”
   • [claimed-docs] “The transcripts query is designed to fetch a list of transcripts against input arguments.”
   • [claimed-docs] “The transcript query is designed to fetch details associated with a specific transcript ID.”
   • [claimed-docs] “The Fireflies API is built on top of GraphQL... This API allows you to retrieve exactly the data you need in a structured format.”
   • [claimed-docs] “Make your first request in under 5 minutes. This guide provides step-by-step instructions to make your first query with our GraphQL API”
   • [claimed-docs] “The uploadAudio mutation allows you to upload audio files to Fireflies.ai for transcription.”
   • [probe] “PROBE runtime (recorded 2026-09-05): a keyless GraphQL query POSTed to the live endpoint https://api.fireflies.ai/graphql returned the docum…”
   • [claimed-docs] “Get detailed notes, action items, and customized summaries instantly after every meeting.”

   proof ↗⚑ flag

   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

Agent access

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

   weight 2 · round drawn
   Fireflies.ai✓fullprobed9/10

   Fireflies hosts an llms.txt file confirmed live at https://docs.fireflies.ai/llms.txt (HTTP 200) and also runs an agent-oriented docs MCP server that completed a full keyless handshake, letting agents search documentation directly. This gives AI-native users two concrete, verified paths to point an agent at agent-oriented docs. Missing for 10: no independent third-party corroboration of llms.txt usage/adoption beyond the probe.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.fireflies.ai/llms.txt # Fireflies ## Docs - [Introduction](https://docs.fireflies.ai/getting-star…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the Fireflies docs MCP server at https://docs.fireflies.ai/mcp completed a FULL keyless JSON-RPC initia…”
   • [claimed-docs] “The Fireflies Documentation MCP Server enables AI tools to search and retrieve information directly from the Fireflies documentation.”

   proof ↗⚑ flag

   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

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

   weight 2 · round drawn
   Fireflies.ai~partialprobed6/10

   Fireflies exposes a documented GraphQL API with bearer-token auth (uploadAudio, transcripts queries) that is confirmed live via runtime probes, enabling headless scripted/automated use outside the UI. However there's no CLI, SDK, or explicit CI/pipeline documentation or examples showing scheduled/unattended automation workflows. missing for 10: official CLI or SDK for automation, documented CI/cron usage patterns, independent evidence of real-world headless deployment.

   • [claimed-docs] “We use a standard bearer token authentication mechanism. This means that to make authorized requests to the API, you must include an `Author…”
   • [claimed-docs] “The `uploadAudio` mutation allows you to upload audio files to Fireflies.ai for transcription.”
   • [claimed-docs] “The transcripts query is designed to fetch a list of transcripts against input arguments.”
   • [probe] “PROBE runtime (recorded 2026-09-05): a keyless GraphQL query POSTed to the live endpoint https://api.fireflies.ai/graphql returned the docum…”
   • [claimed-docs] “Make your first request in under 5 minutes. This guide provides step-by-step instructions to make your first query with our GraphQL API”

   proof ↗⚑ flag

   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

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

   weight 3 · round drawn
   Fireflies.ai—none0/10

   All evidence describes Fireflies as an MCP *server* (its docs MCP server and its data MCP server that ChatGPT/other agents connect to), not as a client that lets users plug external MCP servers into Fireflies so it can consume their tools. No documentation shows Fireflies' own AI assistant (Fred) accepting third-party MCP servers as tool sources.

   • [claimed-docs] “The Fireflies Documentation MCP Server enables AI tools to search and retrieve information directly from the Fireflies documentation.”
   • [claimed-docs] “Once connected, you can query your Fireflies data directly through ChatGPT's Deep Research feature.”
   • [probe] “official MCP server documented at https://guide.fireflies.ai/articles/8272956938-learn-about-the-fireflies-mcp-server-model-context-protocol”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the hosted MCP server https://api.fireflies.ai/mcp returned HTTP 40…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the Fireflies docs MCP server at https://docs.fireflies.ai/mcp completed a FULL keyless JSON-RPC initia…”

   proof ↗⚑ flag

   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

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

   weight 3 · round drawn
   Fireflies.ai✓fullprobed9/10

   Fireflies ships an official hosted MCP server (api.fireflies.ai/mcp, OAuth-gated) plus a separate docs MCP server, both confirmed live via runtime probes, allowing AI agents like ChatGPT Deep Research to query Fireflies data. missing for 10: independent third-party hands-on write-up beyond vendor docs/probes.

   • [claimed-docs] “The Fireflies Documentation MCP Server enables AI tools to search and retrieve information directly from the Fireflies documentation.”
   • [claimed-docs] “Once connected, you can query your Fireflies data directly through ChatGPT's Deep Research feature.”
   • [claimed-docs] “You can now connect Fireflies to ChatGPT using our OAuth integration—no API keys required.”
   • [probe] “official MCP server documented at https://guide.fireflies.ai/articles/8272956938-learn-about-the-fireflies-mcp-server-model-context-protocol”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the hosted MCP server https://api.fireflies.ai/mcp returned HTTP 40…”
   • [probe] “PROBE runtime (recorded 2026-09-05): the Fireflies docs MCP server at https://docs.fireflies.ai/mcp completed a FULL keyless JSON-RPC initia…”

   proof ↗⚑ flag

   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

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

   weight 3 · round drawn
   Fireflies.ai✓fullprobed9/10

   Fireflies documents a full public GraphQL API with bearer-token auth, queries/mutations (transcripts, uploadAudio), and a quickstart guide, and runtime probes confirm the live GraphQL endpoint enforces auth exactly as documented. This is corroborated by hands-on probes, not just vendor claims. Missing for 10: no OpenAPI/swagger spec discoverable and no independent third-party developer testimonial beyond internal docs.

   • [claimed-docs] “We use a standard bearer token authentication mechanism. This means that to make authorized requests to the API, you must include an `Author…”
   • [claimed-docs] “The `uploadAudio` mutation allows you to upload audio files to Fireflies.ai for transcription.”
   • [claimed-docs] “The transcripts query is designed to fetch a list of transcripts against input arguments.”
   • [claimed-docs] “The Fireflies API is built on top of GraphQL... This API allows you to retrieve exactly the data you need in a structured format.”
   • [claimed-docs] “Make your first request in under 5 minutes. This guide provides step-by-step instructions to make your first query with our GraphQL API”
   • [probe] “PROBE runtime (recorded 2026-09-05): a keyless GraphQL query POSTed to the live endpoint https://api.fireflies.ai/graphql returned the docum…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.fireflies.ai/openapi.json, https://docs.fireflies.ai/swagger.json, https://docs.firefli…”

   proof ↗⚑ flag

   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

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

   weight 2 · round drawn
   Fireflies.ai—none0/10

   Fireflies' API uses a single bearer-token API key per account with full account-level access (docs-2, docs-3, docs-23); there is no evidence of scoped, role-limited, or least-privilege credential issuance for agents (e.g., no per-agent scopes, read-only keys, or restricted-permission tokens). The OAuth flow mentioned is for connecting to ChatGPT, not for issuing narrower-scope credentials, and admin controls (Rules Engine, Super Admin) govern meeting access, not API credential scoping.

   • [claimed-docs] “Navigate to the Integrations section 3. Click on Fireflies API 4. Copy and store your API key securely”
   • [claimed-docs] “We use a standard bearer token authentication mechanism. This means that to make authorized requests to the API, you must include an `Author…”
   • [claimed-docs] “We use a standard bearer token authentication mechanism.”
   • [claimed-docs] “You can now connect Fireflies to ChatGPT using our OAuth integration—no API keys required.”
   • [claimed-docs] “Full meeting access to your entire workspace by upgrading to Super Admin status.”

   proof ↗⚑ flag

   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

7. ai-native userBuild against official SDKs

   weight 2 · round to Fathom
   Fireflies.ai—none0/10

   Evidence shows a GraphQL API with bearer-token auth and MCP servers, but no official language SDKs (e.g., Python/JS client libraries) are documented or referenced anywhere in the pack.

   • [claimed-docs] “The Fireflies API is built on top of GraphQL... This API allows you to retrieve exactly the data you need in a structured format.”
   • [claimed-docs] “We use a standard bearer token authentication mechanism. This means that to make authorized requests to the API, you must include an `Author…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.fireflies.ai/openapi.json, https://docs.fireflies.ai/swagger.json, https://docs.firefli…”

   proof ↗⚑ flag

   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

8. ai-native userSubscribe to events via webhooks

   weight 2 · round to Fathom
   Fireflies.ai—none0/10

   The evidence pack covers GraphQL API, MCP servers, and OAuth integration but contains no mention of webhooks or event-based subscriptions anywhere in the docs, pricing, or security pages provided.

   ⚑ flag

   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

Agentic features

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

   weight 2 · round to Fathom
   Fireflies.ai✓fullclaimed7/10

   Fireflies generates AI-driven meeting notes, action items, and customized summaries automatically (fireflies-docs-10), plus an AskFred AI assistant for querying meeting data and cross-meeting insights like comparing objections across prospect segments (fireflies-docs-18, fireflies-docs-24). These are in-product AI-generated insights/suggestions surfaced directly to users. missing for 10: independent/hands-on user reviews validating quality of AskFred's insights, and more detail on the breadth/accuracy of automated suggestions beyond marketing copy.

   • [claimed-docs] “Get detailed notes, action items, and customized summaries instantly after every meeting.”
   • [claimed-docs] “AskFred: AI assistant”
   • [claimed-docs] “Compare the objections mentioned in calls with Enterprise prospects versus SMB prospects this quarter”
   • [claimed-docs] “Conversation intelligence Team analytics (for admins)”

   proof ↗⚑ flag

   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

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

   weight 2 · round to Fathom
   Fireflies.ai~partialclaimed4/10

   Fireflies offers automation-adjacent features (auto-join calendar meetings, rules engine for admin workflows, API/MCP access) but there's no evidence of user-configurable autonomous agentic automations that run in the background beyond meeting recording/transcription triggers. missing for 10: documented workflow/automation builder for arbitrary recurring agentic tasks, evidence of scheduled/triggered actions beyond meeting auto-join, independent confirmation of autonomous multi-step automation execution.

   • [claimed-docs] “Invite fred@fireflies.ai to a live meeting or have it autojoin your calendar meetings to record, transcribe, and summarize.”
   • [claimed-docs] “Automation workflows for admins to have control over meeting access and privacy.”
   • [claimed-docs] “Rules Engine Automation workflows for admins to have control over meeting access and privacy.”
   • [claimed-docs] “Audit Logs ([API](https://docs.fireflies.ai/graphql-api/query/audit-events#audit-events))”

   proof ↗⚑ flag

   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

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

   weight 3 · round to Fireflies.ai
   Fireflies.ai~partialclaimed4/10

   Fireflies advertises 'AskFred: AI assistant' as a paid feature and an AI bot (fred@fireflies.ai) that can be invited to meetings to record, transcribe, and summarize, which is a built-in assistant a user can delegate meeting-related tasks to. However, evidence never details what tasks AskFred can perform beyond note-taking/summarization, provides no hands-on walkthrough, and gives no independent corroboration of its task-delegation capabilities. Missing for 10: detailed docs on AskFred's task scope/commands, hands-on or independent verification of delegating tasks to it, and clarity on limits beyond meeting summarization.

   • [claimed-docs] “Invite fred@fireflies.ai to a live meeting or have it autojoin your calendar meetings to record, transcribe, and summarize.”
   • [claimed-docs] “AskFred: AI assistant”
   • [claimed-docs] “Get detailed notes, action items, and customized summaries instantly after every meeting.”

   proof ↗⚑ flag

   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

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

   weight 2 · round to Fireflies.ai
   Fireflies.ai✓fullprobed7/10

   Fireflies ships an AskFred AI assistant and an official remote MCP server (OAuth-gated, live per runtime probe) that lets users query meeting data via natural language through ChatGPT/Deep Research, with documented example queries like 'Compare the objections mentioned in calls...'. missing for 10: no independent/hands-on review of NL command accuracy or breadth beyond the vendor's own examples, and no evidence of NL support outside the ChatGPT/MCP integration path.

   • [claimed-docs] “AskFred: AI assistant”
   • [claimed-docs] “Once connected, you can query your Fireflies data directly through ChatGPT's Deep Research feature.”
   • [claimed-docs] “Compare the objections mentioned in calls with Enterprise prospects versus SMB prospects this quarter”
   • [claimed-docs] “You can now connect Fireflies to ChatGPT using our OAuth integration—no API keys required.”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the hosted MCP server https://api.fireflies.ai/mcp returned HTTP 40…”
   • [probe] “official MCP server documented at https://guide.fireflies.ai/articles/8272956938-learn-about-the-fireflies-mcp-server-model-context-protocol”

   proof ↗⚑ flag

   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

Api quality

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

   weight 2 · round to Fathom
   Fireflies.ai—none0/10

   Fireflies documents its GraphQL API with markdown reference pages (queries/mutations) and a docs MCP server for AI search, but there is no evidence of an interactive API reference with runnable/try-it examples (e.g., GraphQL playground or Swagger UI); a probe explicitly found no OpenAPI/swagger spec at expected paths.

   • [claimed-docs] “The `uploadAudio` mutation allows you to upload audio files to Fireflies.ai for transcription.”
   • [claimed-docs] “The transcripts query is designed to fetch a list of transcripts against input arguments.”
   • [claimed-docs] “The Fireflies API is built on top of GraphQL... This API allows you to retrieve exactly the data you need in a structured format.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.fireflies.ai/openapi.json, https://docs.fireflies.ai/swagger.json, https://docs.firefli…”

   proof ↗⚑ flag

   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

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

   weight 2 · round to Fathom
   Fireflies.ai—none0/10

   Fireflies exposes a GraphQL API (not REST/OpenAPI), and an explicit probe for openapi.json/swagger.json at multiple standard paths returned 404s with no alternative machine-readable spec (e.g., GraphQL SDL/introspection download) surfaced in docs.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.fireflies.ai/openapi.json, https://docs.fireflies.ai/swagger.json, https://docs.firefli…”
   • [claimed-docs] “The Fireflies API is built on top of GraphQL... This API allows you to retrieve exactly the data you need in a structured format.”

   proof ↗⚑ flag

   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

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

   weight 2 · round drawn
   Fireflies.ai—none0/10

   The docs describe a single GraphQL API (queries/mutations) but there is no mention of API versioning, version numbers, changelogs, or a documented deprecation policy anywhere in the evidence pack; no evidence of any versioning scheme or deprecation communication exists.

   ⚑ flag

   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

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

   weight 2 · round drawn
   Fireflies.ai~partialprobed4/10

   The GraphQL API's transcripts query supports fetching filtered lists (e.g., by attendee emails), enabling bulk-read automation, and the MCP server exposes this to AI agents. However, there is no documented batch/bulk mutation (e.g., bulk delete, bulk tag, bulk update) across many items — only single-item mutations like uploadAudio are shown. missing for 10: explicit bulk write/update/delete endpoints, batch mutation support, pagination/rate-limit guidance for large-scale bulk operations, independent confirmation of bulk workflows in practice.

   • [claimed-docs] “The transcripts query is designed to fetch a list of transcripts against input arguments.”
   • [claimed-docs] “Filter meetings that contain any of these emails as attendees. Accepts an array of email addresses.”
   • [claimed-docs] “The `uploadAudio` mutation allows you to upload audio files to Fireflies.ai for transcription.”
   • [probe] “PROBE runtime (recorded 2026-09-05): a keyless GraphQL query POSTed to the live endpoint https://api.fireflies.ai/graphql returned the docum…”

   proof ↗⚑ flag

   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

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

   weight 3 · round to Fathom
   Fireflies.ai~partialclaimed4/10

   Fireflies explicitly advertises a 'Rules Engine' with 'Automation workflows for admins to have control over meeting access and privacy,' which is direct evidence of rule-based, event-triggered automation. However, this is scoped narrowly to admin governance (access/privacy controls) rather than a general-purpose, user-defined trigger-action automation system for AI-native workflows, and there's no documented API/webhook mechanism for arbitrary custom rules. Missing for 10: evidence of broader user-configurable triggers/actions beyond admin privacy controls, webhook/event API for custom automations, and independent confirmation of the Rules Engine's flexibility.

   • [claimed-docs] “Rules Engine Automation workflows for admins to have control over meeting access and privacy.”
   • [claimed-docs] “Automation workflows for admins to have control over meeting access and privacy.”
   • [claimed-docs] “Full meeting access to your entire workspace by upgrading to Super Admin status.”

   proof ↗⚑ flag

   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

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round drawn
   Fireflies.ai—none0/10

   The evidence shows GraphQL API access, MCP servers, and admin 'automation workflows' for meeting access/privacy controls, but nothing about scheduling recurring jobs or workflows (e.g., cron-like triggers, recurring API calls, workflow automation for tasks) that an AI-native user could set up and have run repeatedly.

   • [claimed-docs] “Automation workflows for admins to have control over meeting access and privacy.”
   • [claimed-docs] “Rules Engine Automation workflows for admins to have control over meeting access and privacy.”
   • [claimed-docs] “The Fireflies API is built on top of GraphQL... This API allows you to retrieve exactly the data you need in a structured format.”

   proof ↗⚑ flag

   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

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 Fireflies.ai
   Fireflies.ai~partialclaimed5/10

   Docs confirm calendar autojoin (Google Meet) and an admin-facing 'Rules Engine' for controlling meeting access/privacy, suggesting some rule-based control over capture, but there is no concrete evidence of a per-meeting-type configuration UI (e.g., rules keyed to meeting title/type) or explicit Outlook calendar connection flow. missing for 10: explicit Google/Outlook calendar-connect walkthrough, granular per-meeting-type capture rule examples, and any hands-on/independent confirmation of this workflow.

   • [claimed-docs] “Invite fred@fireflies.ai to a live meeting or have it autojoin your calendar meetings to record, transcribe, and summarize.”
   • [claimed-docs] “Automatically record your Google Meet calls and get real-time transcripts.”
   • [claimed-docs] “Automation workflows for admins to have control over meeting access and privacy.”
   • [claimed-docs] “Rules Engine Automation workflows for admins to have control over meeting access and privacy.”
   • [claimed-docs] “Full meeting access to your entire workspace by upgrading to Super Admin status.”

   proof ↗⚑ flag

   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

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 drawn
   Fireflies.ai—none0/10

   Fireflies documents transcript search/filtering by attendee email and analytics tools, which could technically support building such a feature, but there is no evidence of a native pre-meeting briefing or 'past meetings with same people + open threads' surfacing feature before a call.

   • [claimed-docs] “The transcripts query is designed to fetch a list of transcripts against input arguments.”
   • [claimed-docs] “Filter meetings that contain any of these emails as attendees. Accepts an array of email addresses.”
   • [claimed-docs] “AskFred: AI assistant”

   proof ↗⚑ flag

   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

Capture

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

   weight 2 · round to Fireflies.ai
   Fireflies.ai~partialcommunity6/10

   Docs confirm the fred@fireflies.ai bot can autojoin calendar meetings and specifically call out automatic Google Meet recording, plus admin-level 'Rules Engine' controls over meeting access/privacy for recording governance, but Zoom and Microsoft Teams are never explicitly named as supported recording targets in the pack, and a community comment questions the platform's overall complexity without concretely refuting capture reliability. missing for 10: explicit Zoom/Teams recording documentation, granular per-meeting recording-location controls, and independent hands-on confirmation of multi-platform capture reliability.

   • [claimed-docs] “Invite fred@fireflies.ai to a live meeting or have it autojoin your calendar meetings to record, transcribe, and summarize.”
   • [claimed-docs] “Automatically record your Google Meet calls and get real-time transcripts.”
   • [claimed-docs] “Automation workflows for admins to have control over meeting access and privacy.”
   • [claimed-docs] “Rules Engine Automation workflows for admins to have control over meeting access and privacy.”
   • [community] “Don't... I've tried and it's incredibly complex... there is another Startup called tldv.io that went even further with their tech than flies…”

   proof ↗⚑ flag

   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

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 Fathom
   Fireflies.ai—none0/10

   Fireflies' documented capture mechanism is bot-based — 'Invite fred@fireflies.ai to a live meeting or have it autojoin your calendar meetings to record' — meaning a visible bot participant joins calls; there is no evidence of a desktop-app/device-audio capture mode that avoids a visible bot. The only alternative is uploadAudio for pre-recorded files, which doesn't address live-meeting capture without a bot.

   • [claimed-docs] “Invite fred@fireflies.ai to a live meeting or have it autojoin your calendar meetings to record, transcribe, and summarize.”
   • [claimed-docs] “The `uploadAudio` mutation allows you to upload audio files to Fireflies.ai for transcription.”

   proof ↗⚑ flag

   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

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

   weight 2 · round drawn
   Fireflies.ai—none0/10

   The evidence pack covers meeting bot recording (autojoin, Google Meet), API uploadAudio, and MCP integrations, but contains no mention of a mobile app for recording in-person conversations or notes syncing to the same workspace from mobile capture.

   ⚑ flag

   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

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
   Fireflies.ai—none0/10

   The evidence pack contains detailed docs on the GraphQL API, MCP servers, and general meeting features, but nothing about native HubSpot, Salesforce, or Attio integrations or automatic syncing of notes/summaries to CRM contact/deal records. Without any documented CRM connector or sync workflow, this capability is unevidenced.

   ⚑ flag

   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

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

   weight 2 · round drawn
   Fireflies.ai—none0/10

   The evidence pack covers Fireflies' GraphQL API, MCP servers, and security/admin features, but contains no mention of native Slack, Notion, or Zapier integrations or any 'thousands of apps' automation ecosystem — the specific capability the story asks about is simply absent from the provided evidence.

   ⚑ flag

   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

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 drawn
   Fireflies.ai~partialprobed6/10

   Fireflies ships an 'AskFred' AI assistant and an MCP server that lets natural-language tools like ChatGPT Deep Research query meeting data with prompts like 'compare objections in Enterprise vs SMB calls this quarter,' which is direct evidence of cross-meeting natural-language Q&A. However, the evidence never shows answers being returned with explicit sourced excerpts/citations back to specific meetings, and there's no independent hands-on validation of answer quality. Missing for 10: documented citation/sourcing behavior in AskFred/MCP answers, and third-party verification of accuracy across large meeting histories.

   • [claimed-docs] “AskFred: AI assistant”
   • [claimed-docs] “Compare the objections mentioned in calls with Enterprise prospects versus SMB prospects this quarter”
   • [claimed-docs] “Once connected, you can query your Fireflies data directly through ChatGPT's Deep Research feature.”
   • [claimed-docs] “You can now connect Fireflies to ChatGPT using our OAuth integration—no API keys required.”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the hosted MCP server https://api.fireflies.ai/mcp returned HTTP 40…”

   proof ↗⚑ flag

   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

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

   weight 3 · round to Fireflies.ai
   Fireflies.ai~partialprobed6/10

   Fireflies provides cross-meeting search via AskFred AI assistant, the MCP server (which explicitly supports queries like comparing objections across many calls), and GraphQL queries (transcripts/transcript) that can filter by attendees and fetch specific transcript details, plus notes/summaries. However, the evidence never explicitly documents jumping to a precise timestamp/moment within a transcript from search results. Missing for 10: explicit documentation of timestamp-level deep-linking or in-transcript moment navigation from search results, and independent/hands-on confirmation of search accuracy across large meeting histories.

   • [claimed-docs] “The transcripts query is designed to fetch a list of transcripts against input arguments.”
   • [claimed-docs] “The transcript query is designed to fetch details associated with a specific transcript ID.”
   • [claimed-docs] “AskFred: AI assistant”
   • [claimed-docs] “Compare the objections mentioned in calls with Enterprise prospects versus SMB prospects this quarter”
   • [claimed-docs] “Filter meetings that contain any of these emails as attendees. Accepts an array of email addresses.”
   • [probe] “PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the hosted MCP server https://api.fireflies.ai/mcp returned HTTP 40…”

   proof ↗⚑ flag

   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

Summaries

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

   weight 3 · round to Fathom
   Fireflies.ai~partialclaimed6/10

   Fireflies docs claim it produces 'detailed notes, action items, and customized summaries instantly after every meeting' and offers a Rules Engine/team workflows for admins, which implies action items are captured and accessible via dashboard/API (transcripts query). However, there's no explicit evidence of owner assignment/attribution per action item, a dedicated tracking view/board, or task-management integration (e.g., sync to a task tool) beyond generic summary output. missing for 10: explicit owner-attribution logic, a dedicated action-item tracking dashboard, and third-party corroboration of accuracy/completeness.

   • [claimed-docs] “Get detailed notes, action items, and customized summaries instantly after every meeting.”
   • [claimed-docs] “Rules Engine Automation workflows for admins to have control over meeting access and privacy.”
   • [claimed-docs] “The transcripts query is designed to fetch a list of transcripts against input arguments.”

   proof ↗⚑ flag

   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

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
   Fireflies.ai—none0/10

   The evidence pack shows only generic 'customized summaries' language and API/MCP mechanics, but no documentation of configurable templates or saved prompts tied to meeting types (discovery call, 1:1, standup) that a sales lead could select or author.

   • [claimed-docs] “Get detailed notes, action items, and customized summaries instantly after every meeting.”

   proof ↗⚑ flag

   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

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
   Fireflies.ai—none0/10

   Fireflies documents meeting notes, action items, and customized summaries (fireflies-docs-10) plus an AskFred AI assistant (fireflies-docs-18), but no evidence pack item mentions drafting or auto-composing a follow-up email a sales rep can review and send in a couple of clicks. This is a fair capability to expect from a meeting-notes tool, so absence of evidence yields 'none' rather than 'na'.

   • [claimed-docs] “Get detailed notes, action items, and customized summaries instantly after every meeting.”
   • [claimed-docs] “AskFred: AI assistant”

   proof ↗⚑ flag

   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

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 drawn
   Fireflies.ai✓fullclaimed7/10

   Fireflies explicitly markets 'detailed notes, action items, and customized summaries instantly after every meeting' with AI-driven summarization (AskFred) and structured meeting notes, matching the PM story of a ready-to-share post-meeting summary. Missing for 10: no independent/hands-on review confirming summary quality is 'good enough to share without editing', and no detail on how decisions/next-steps are specifically structured in the output beyond marketing copy.

   • [claimed-docs] “Get detailed notes, action items, and customized summaries instantly after every meeting.”
   • [claimed-docs] “AskFred: AI assistant”
   • [claimed-docs] “Invite fred@fireflies.ai to a live meeting or have it autojoin your calendar meetings to record, transcribe, and summarize.”
   • [claimed-docs] “Real-time notes & live transcriptions”

   proof ↗⚑ flag

   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

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

   weight 2 · round to Fireflies.ai
   Fireflies.ai~partialprobed6/10

   Fireflies offers a documented GraphQL API covering core transcript/meeting data (queries, transcript details, uploadAudio mutation, audit events) plus MCP servers for docs and data access, showing solid API parity for core recording/transcription/search workflows. However, there's no evidence that UI-only features like the Rules Engine automation, admin Super Admin controls, AskFred AI assistant, or multi-language mode settings are exposed via the API, so full UI/API parity isn't demonstrated. Missing for 10: API endpoints for Rules Engine/admin automation, AskFred assistant interactions, and language-mode configuration.

   • [claimed-docs] “The `uploadAudio` mutation allows you to upload audio files to Fireflies.ai for transcription.”
   • [claimed-docs] “The transcripts query is designed to fetch a list of transcripts against input arguments.”
   • [claimed-docs] “The transcript query is designed to fetch details associated with a specific transcript ID.”
   • [claimed-docs] “Audit Logs ([API](https://docs.fireflies.ai/graphql-api/query/audit-events#audit-events))”
   • [claimed-docs] “Rules Engine Automation workflows for admins to have control over meeting access and privacy.”
   • [claimed-docs] “AskFred: AI assistant”
   • [probe] “PROBE runtime (recorded 2026-09-05): a keyless GraphQL query POSTed to the live endpoint https://api.fireflies.ai/graphql returned the docum…”

   proof ↗⚑ flag

   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

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

   weight 3 · round to Fathom
   Fireflies.ai~partialprobed5/10

   Fireflies exposes a GraphQL API (transcripts/transcript queries) that lets a user programmatically pull structured meeting data in JSON, and this is confirmed live and reachable in the runtime probe, giving a technical path to self-export. However, there is no documented bulk 'export all my data' feature, no mention of standard open export formats (CSV/JSON dump, GDPR-style account export), and no evidence of a data-portability or account-deletion export workflow for someone wanting to fully leave the platform. missing for 10: a documented full-account data export/portability feature, explicit open-format (CSV/JSON) bulk export tool, and evidence of an easy 'leave and take everything' workflow beyond ad-hoc API queries.

   • [claimed-docs] “The transcripts query is designed to fetch a list of transcripts against input arguments.”
   • [claimed-docs] “The transcript query is designed to fetch details associated with a specific transcript ID.”
   • [claimed-docs] “The Fireflies API is built on top of GraphQL... This API allows you to retrieve exactly the data you need in a structured format.”
   • [probe] “PROBE runtime (recorded 2026-09-05): a keyless GraphQL query POSTed to the live endpoint https://api.fireflies.ai/graphql returned the docum…”

   proof ↗⚑ flag

   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

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 drawn
   Fireflies.ai~partialclaimed4/10

   The pricing page evidently lists concrete feature differentiators per tier (e.g., AskFred, real-time notes, audit logs, multi-language mode, team analytics) suggesting a self-serve, itemized pricing page rather than a sales-only wall, but the pack never shows actual dollar figures, an explicit 'Free' plan, or a statement confirming no sales contact is required for basic use. missing for 10: explicit free-tier existence/limits, listed price points per tier, and confirmation that upgrading doesn't require contacting sales.

   • [claimed-docs] “Audit Logs ([API](https://docs.fireflies.ai/graphql-api/query/audit-events#audit-events))”
   • [claimed-docs] “AskFred: AI assistant”
   • [claimed-docs] “Real-time notes & live transcriptions”
   • [claimed-docs] “Private Storage on Enterprise to store your meeting data at your preferred location.”
   • [claimed-docs] “Conversation intelligence Team analytics (for admins)”
   • [claimed-docs] “Multi-language Mode”

   proof ↗⚑ flag

   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

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 to Fireflies.ai
   Fireflies.ai~partialclaimed3/10

   Fireflies documents admin-side privacy controls (a 'Rules Engine' for automation workflows governing meeting access/privacy, and Super Admin access controls) which give IT admins some enforced transparency levers, but there is no evidence of actual participant-facing consent mechanics — no documented in-meeting recording announcement, join notification, or consent banner beyond the bot ('Fred') simply appearing in the call as an implicit signal. missing for 10: explicit in-meeting disclosure/announcement feature, participant notification settings, and any documentation framing these as consent/compliance tools rather than generic access-control automation.

   • [claimed-docs] “Invite fred@fireflies.ai to a live meeting or have it autojoin your calendar meetings to record, transcribe, and summarize.”
   • [claimed-docs] “Automation workflows for admins to have control over meeting access and privacy.”
   • [claimed-docs] “Rules Engine Automation workflows for admins to have control over meeting access and privacy.”
   • [claimed-docs] “Full meeting access to your entire workspace by upgrading to Super Admin status.”

   proof ↗⚑ flag

   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

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
   Fireflies.ai—none0/10

   The evidence pack includes Fireflies security-page snippets (private storage, rules engine, audit logs) but contains no mention of whether meeting data is used to train AI models, no documented opt-out mechanism, and no SOC 2 or HIPAA certification claims. This axis is fair for a meeting-recording SaaS handling sensitive conversation data, but no supporting evidence exists in the pack.

   • [claimed-docs] “Audit Logs ([API](https://docs.fireflies.ai/graphql-api/query/audit-events#audit-events))”
   • [claimed-docs] “Automation workflows for admins to have control over meeting access and privacy.”
   • [claimed-docs] “Private Storage on Enterprise to store your meeting data at your preferred location.”
   • [claimed-docs] “Rules Engine Automation workflows for admins to have control over meeting access and privacy.”
   • [claimed-docs] “Secure, dedicated cloud storage exclusively for your organization’s data.”

   proof ↗⚑ flag

   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

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

   weight 2 · round drawn
   Fireflies.ai—none0/10

   Evidence shows admin-facing security/automation features (Rules Engine, Private Storage, Super Admin access) but no mention of configurable data retention schedules, auto-delete of transcripts/recordings, or an on-demand permanent erasure capability.

   • [claimed-docs] “Automation workflows for admins to have control over meeting access and privacy.”
   • [claimed-docs] “Private Storage on Enterprise to store your meeting data at your preferred location.”
   • [claimed-docs] “Rules Engine Automation workflows for admins to have control over meeting access and privacy.”
   • [claimed-docs] “Full meeting access to your entire workspace by upgrading to Super Admin status.”
   • [claimed-docs] “Secure, dedicated cloud storage exclusively for your organization’s data.”

   proof ↗⚑ flag

   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

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

   weight 2 · round to Fireflies.ai
   Fireflies.ai~partialclaimed6/10

   Fireflies documents Enterprise-tier 'Private Storage' to store meeting data at a preferred location and 'Secure, dedicated cloud storage exclusively for your organization's data,' directly addressing data residency choice, but this is gated to a specific plan with no detail on which regions are supported or how selection is configured. Missing for 10: list of available regions, self-serve UI/API for setting residency, independent/hands-on confirmation of the feature working as described.

   • [claimed-docs] “Private Storage on Enterprise to store your meeting data at your preferred location.”
   • [claimed-docs] “Secure, dedicated cloud storage exclusively for your organization’s data.”

   proof ↗⚑ flag

   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

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

   weight 3 · round drawn
   Fireflies.ai—none0/10

   No evidence pack item addresses AI-model-training opt-out or data-use-for-training policy; security/privacy pages mention private storage and access controls but never mention AI training exclusion.

   ⚑ flag

   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

3. ai-native userControl data retention and deletion

   weight 2 · round drawn
   Fireflies.ai—none0/10

   The evidence pack shows security/privacy features like private storage location, admin access rules, and audit logs, but nowhere documents a data retention policy, a deletion API/mutation, or user-controlled data purging (e.g., no deleteTranscript mutation or retention settings in the GraphQL API docs).

   ⚑ flag

   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

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

   weight 2 · round drawn
   Fireflies.ai—none0/10

   No evidence pack item mentions telemetry opt-out, usage tracking controls, or analytics disabling for Fireflies.ai itself; the closest items relate to admin privacy controls, storage location, and audit logs, not user-level telemetry opt-out.

   ⚑ flag

   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

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
   Fireflies.ai—none0/10

   The evidence pack contains no mention of a soundbite/clip-cutting or highlight-sharing feature for calls—only API/GraphQL docs, MCP server details, transcription, and general meeting summary features are documented.

   ⚑ flag

   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

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 Fireflies.ai
   Fireflies.ai~partialclaimed6/10

   Fireflies documents real admin-facing sharing controls: a Rules Engine for automating meeting access/privacy, Super Admin status for full workspace visibility, and an Audit Logs API for tracking activity, plus Enterprise private/dedicated storage. However there's no explicit documentation of private-by-default note settings or granular per-link/per-folder permission structures. missing for 10: explicit private-by-default note policy, granular link/folder-level permission docs, independent/hands-on verification of admin visibility features.

   • [claimed-docs] “Automation workflows for admins to have control over meeting access and privacy.”
   • [claimed-docs] “Rules Engine Automation workflows for admins to have control over meeting access and privacy.”
   • [claimed-docs] “Full meeting access to your entire workspace by upgrading to Super Admin status.”
   • [claimed-docs] “Audit Logs ([API](https://docs.fireflies.ai/graphql-api/query/audit-events#audit-events))”
   • [claimed-docs] “Secure, dedicated cloud storage exclusively for your organization’s data.”
   • [claimed-docs] “Private Storage on Enterprise to store your meeting data at your preferred location.”

   proof ↗⚑ flag

   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

Transcription

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

   weight 2 · round to Fireflies.ai
   Fireflies.ai~partialclaimed5/10

   Fireflies advertises automatic language switching between meetings and a paid 'Multi-language Mode' add-on, indicating some multilingual support, but there's no documentation of which languages are supported, accuracy across languages, or how mid-meeting switching/code-switching is handled, and no independent corroboration. missing for 10: list of supported languages, accuracy benchmarks per language, handling of code-switching within a single meeting, and third-party validation of multilingual transcription quality.

   • [claimed-docs] “Automatically switch languages from meeting to meeting with ease.”
   • [claimed-docs] “Multi-language Mode”

   proof ↗⚑ flag

   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

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

   weight 3 · round to Fireflies.ai
   Fireflies.ai~partialclaimed4/10

   Fireflies docs claim it 'identifies different speakers in meetings and audio files' (diarization), but there is no evidence detailing how it maps names to speaker labels (e.g., via calendar invitee matching or voice enrollment) or accuracy data. missing for 10: documentation on real-name matching mechanism, accuracy benchmarks, and independent/hands-on verification of correct name attribution.

   • [claimed-docs] “Fireflies identifies different speakers in meetings and audio files.”

   proof ↗⚑ flag

   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

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
   Fireflies.ai—none0/10

   The evidence pack shows marketing feature claims (speaker ID, multi-language, live transcription) and API docs, but nowhere documents the underlying transcription model, accuracy/WER benchmarks, or known limitations of the transcription engine itself — it is generic 'AI-powered' framing rather than the technical transparency the story asks for.

   • [claimed-docs] “Invite fred@fireflies.ai to a live meeting or have it autojoin your calendar meetings to record, transcribe, and summarize.”
   • [claimed-docs] “Automatically switch languages from meeting to meeting with ease.”
   • [claimed-docs] “Fireflies identifies different speakers in meetings and audio files.”
   • [claimed-docs] “Automatically record your Google Meet calls and get real-time transcripts.”
   • [claimed-docs] “Multi-language Mode”

   proof ↗⚑ flag

   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