Fireflies.ai vs Fellow

Agent ops

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

   weight 2 · round to Fellow
   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

   Fellow~partialprobed5/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round to Fellow
   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

   Fellow✓fullprobed9/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round drawn
   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

   Fellow✓fullprobed8/10

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

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

   proof ↗⚑ flag

Agent access

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

   weight 2 · round to Fireflies.ai
   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

   Fellow✓fullprobed8/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round to Fireflies.ai
   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

   Fellow—none0/10

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

   ⚑ flag

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

   weight 3 · round drawn
   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

   Fellow—none0/10

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

   ⚑ flag

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

   weight 3 · round drawn
   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

   Fellow✓fullprobed9/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round to Fireflies.ai
   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

   Fellow✓fullprobed8/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round to Fellow
   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

   Fellow~partialclaimed5/10

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

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

   proof ↗⚑ flag

7. ai-native userBuild against official SDKs

   weight 2 · round drawn
   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

   Fellow—none0/10

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

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

   proof ↗⚑ flag

8. ai-native userSubscribe to events via webhooks

   weight 2 · round to Fellow
   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

   Fellow✓fullclaimed7/10

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

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

   proof ↗⚑ flag

Agentic features

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

   weight 2 · round to Fellow
   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

   Fellow✓fullprobed8/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round to Fellow
   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

   Fellow~partialclaimed5/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round drawn
   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

   Fellow~partialclaimed4/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round to 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

   Fellow~partialprobed7/10

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

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

   proof ↗⚑ flag

Api quality

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

   weight 2 · round to Fellow
   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

   Fellow~partialprobed3/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round drawn
   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

   Fellow—none0/10

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

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

   proof ↗⚑ flag

3. ai-native userTest against a sandbox environment without touching production data

   weight 1 · round drawn
   Fireflies.ai—none0/10

   No evidence of a sandbox/test environment, demo/test API keys, or staging mode that lets developers test integrations without touching real meeting/transcript data; all API and MCP evidence points to production endpoints gated by real bearer tokens or OAuth.

   ⚑ flag

   Fellow—none0/10

   No evidence of a sandbox/test environment, staging API keys, or synthetic test data separate from production; all API and MCP documentation refers only to live workspace data.

   ⚑ flag

4. 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

   Fellow—none0/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round to Fellow
   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

   Fellow~partialclaimed5/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round drawn
   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

   Fellow~partialclaimed4/10

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

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

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round drawn
   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

   Fellow—none0/10

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

   ⚑ flag

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

   weight 1 · round drawn
   Fireflies.ai—none0/10

   Fireflies has an admin 'Rules Engine' for meeting access/privacy automation, but there is no evidence of versioning, review workflows, or rollback capability for any automations or configurations — no changelog, diff, or undo mechanism is documented.

   ⚑ flag

   Fellow—none0/10

   Fellow's evidence covers webhooks, API access, and org-wide recording/retention policies, but nothing describes versioning, reviewing, or rolling back automations or workflow configurations. This is an applicable question given Fellow's policy/webhook configuration features, but no capability is documented.

   ⚑ 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

   Fellow~partialclaimed3/10

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

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

   proof ↗⚑ flag

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

   weight 1 · round to Fellow
   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

   Fellow~partialclaimed5/10

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

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

   proof ↗⚑ flag

Capture

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

   weight 2 · round to Fellow
   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

   Fellow✓fullclaimed8/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round to Fellow
   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

   Fellow✓fullclaimed8/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round drawn
   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

   Fellow—none0/10

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

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

   proof ↗⚑ flag

Integrations

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

   weight 3 · round drawn
   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

   Fellow—none0/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round drawn
   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

   Fellow—none0/10

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

   ⚑ flag

Memory

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

   weight 2 · round to Fellow
   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

   Fellow~partialprobed7/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round to Fellow
   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

   Fellow✓fullprobed7/10

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

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

   proof ↗⚑ flag

Summaries

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

   weight 3 · round to Fellow
   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

   Fellow✓fullclaimed8/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round drawn
   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

   Fellow—none0/10

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

   ⚑ flag

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

   weight 1 · round drawn
   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

   Fellow—none0/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round to Fellow
   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

   Fellow✓fullclaimed8/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round 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

   Fellow~partialprobed5/10

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

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

   proof ↗⚑ flag

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

   weight 3 · round to Fellow
   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

   Fellow~partialclaimed6/10

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

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

   proof ↗⚑ flag

Pricing

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

   weight 2 · round to Fireflies.ai
   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

   Fellow—none0/10

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

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

   proof ↗⚑ flag

Privacy

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

   weight 3 · round 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

   Fellow—none0/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round drawn
   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

   Fellow—none0/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round to Fellow
   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

   Fellow~partialclaimed6/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round 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

   Fellow—none0/10

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

   ⚑ flag

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

   weight 3 · round drawn
   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

   Fellow—none0/10

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

   ⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round to Fellow
   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

   Fellow✓fullclaimed8/10

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

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

   proof ↗⚑ flag

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

   weight 2 · round drawn
   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

   Fellow—none0/10

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

   ⚑ flag

Sharing

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

   weight 1 · round drawn
   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

   Fellow—none0/10

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

   ⚑ flag

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

   weight 2 · round to 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

   Fellow~partialclaimed5/10

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

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

   proof ↗⚑ flag

Transcription

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

   weight 2 · round 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

   Fellow—none0/10

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

   ⚑ flag

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

   weight 3 · round 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

   Fellow—none0/10

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

   ⚑ flag

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

   weight 3 · round drawn
   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

   Fellow—none0/10

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

   ⚑ flag