Skip to content
ProductArena

How Fellow’s scores are calculated

The full audit trail, recomputed from the verdict data at build time through the same code that produced the leaderboard: verdict × quality × story weight per cell, cells sum to dimension scores, dimensions blend into the PA Score. Every number on the product page is reproducible from this page alone; for why the formula looks like this, see the methodology.

verdict factors: full ×1.0 · partial ×0.6 · disputed ×0.3 · none ×0.0 · n/a excluded from both sides · cell points = weight × quality × factor · cell max = weight × 10

PA Score30/100

Agent-ready 45.8 × 0.30 = 13.74

API quality 5.1 × 0.20 = 1.02

Openness 33.6 × 0.20 = 6.72

Built-in AI 41.8 × 0.15 = 6.27

Automation 16.5 × 0.15 = 2.48

(13.74 + 1.02 + 6.72 + 6.27 + 2.48) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 30.22 ÷ 1.00 = 30.2

Scores are stored to 1 decimal; the product page’s pills round to whole numbers for display. Each dimension below shows the stories, verdicts, and cited evidence behind its number.

Agent-ready45.8/100×0.30 of the PA blend

Outside-in: can YOUR agent reach and drive this product — API, MCP, CLI, headless runs, agent docs.

Point an agent at llms.txt or agent-oriented docsweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

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

Run the product headlessly / in CI for automationweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Plug MCP servers into this product so it can use their toolsweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Connect an agent via an official MCP serverweight 3

3 (weight) × 9 (quality) × 1.0 (full) = 27.0 of 30 max

  • [claimed-docs] https://developers.fellow.ai/reference/mcp-server.md“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] https://help.fellow.ai/en/articles/12622641-fellow-s-mcp-server“Fellow’s MCP Connector works with any AI tool that supports connectors, so you're never locked into one platform”
  • [claimed-docs] https://help.fellow.ai/en/articles/12622641-fellow-s-mcp-server“As a workspace admin, you decide which MCP tools your members’ AI assistants can use.”
  • [claimed-docs] https://fellow.ai/features/mcp-server“Your favorite AI chatbot like Claude, ChatGPT, or Cursor can now tap directly into your meeting recaps, notes, and action items”
  • [probe] https://developers.fellow.ai/reference/mcp-server“official MCP server documented at https://developers.fellow.ai/reference/mcp-server”
  • [probe] https://developers.fellow.ai/reference/mcp-server.md“PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to Fellow's hosted MCP server https://fellow.app/mcp returned HTTP 401 with `WWW-Authenticate: Bearer realm="Restricted"` — the documented MCP endpoint (get_action_items, get_meeting_transcript, search_meetings, etc.) is live and bearer-gated as documented.”

Use an official CLIweight 2

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Drive the product through a documented public APIweight 3

3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max

  • [claimed-docs] https://developers.fellow.ai“The Developer API opens that data to you: transcripts, structured notes, and more, all available through standard REST calls.”
  • [claimed-docs] https://developers.fellow.ai/reference/authentication-1.md“All API requests must include a valid API key in the Authorization header.”
  • [claimed-docs] https://developers.fellow.ai/reference/apps_developer_api_api_get_recordings.md“List recordings with optional filters and pagination.”
  • [claimed-docs] https://developers.fellow.ai/reference/apps_developer_api_api_get_action_items.md“List action items with optional filters and pagination.”
  • [claimed-docs] https://developers.fellow.ai/reference/apps_developer_api_api_append_note_agenda.md“Add Fellow Markdown to the end of a note's agenda, leaving the rest of the content in place.”
  • [claimed-docs] https://developers.fellow.ai/reference/webhooks.md“Webhooks allow you to receive real-time notifications when events occur in Fellow.”
  • [probe] https://developers.fellow.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://developers.fellow.ai/openapi.json, https://developers.fellow.ai/swagger.json, https://developers.fellow.ai/api/openapi.json, https://developers.fellow.ai/.well-known/openapi.json)”

Issue scoped/least-privilege API credentials for an agentweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

  • [claimed-docs] https://help.fellow.ai/en/articles/12622641-fellow-s-mcp-server“As a workspace admin, you decide which MCP tools your members’ AI assistants can use.”
  • [claimed-docs] https://developers.fellow.ai/reference/super-admin.md“Super Admin API keys can make requests on behalf of any user in the workspace using the `X-On-Behalf-Of` header.”
  • [claimed-docs] https://developers.fellow.ai/reference/super-admin.md“Fellow’s Super Admin API lets designated Enterprise‑plan administrators retrieve, export, and delete data across the entire workspace”
  • [claimed-docs] https://developers.fellow.ai/reference/authentication-1.md“Generate a new API key for your application, giving it a descriptive name.”
  • [claimed-docs] https://developers.fellow.ai/reference/authentication-1.md“All API requests must include a valid API key in the Authorization header.”

Build against official SDKsweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://developers.fellow.ai“The Developer API opens that data to you: transcripts, structured notes, and more, all available through standard REST calls.”
  • [claimed-docs] https://developers.fellow.ai/reference/authentication-1.md“All API requests must include a valid API key in the Authorization header.”
  • [claimed-docs] https://developers.fellow.ai/reference/authentication-1.md“Include your API key in the `X-API-KEY` header of every request”
  • [claimed-docs] https://developers.fellow.ai/reference/authentication-1.md“Generate a new API key for your application, giving it a descriptive name.”
  • [probe] https://developers.fellow.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://developers.fellow.ai/openapi.json, https://developers.fellow.ai/swagger.json, https://developers.fellow.ai/api/openapi.json, https://developers.fellow.ai/.well-known/openapi.json)”

Subscribe to events via webhooksweight 2

2 (weight) × 7 (quality) × 1.0 (full) = 14.0 of 20 max

  • [claimed-docs] https://developers.fellow.ai/reference/webhooks.md“Fellow sends an HTTP POST request to the URL you specify with details about the event.”
  • [claimed-docs] https://developers.fellow.ai/reference/webhooks.md“Webhooks allow you to receive real-time notifications when events occur in Fellow.”

Agent-ready = 87.0 ÷ 190 × 100 = 45.8

API quality5.1/100×0.20 of the PA blend

The programmable surface once an agent is there — machine-readable spec, interactive docs, sandbox, versioning discipline.

Explore an interactive API reference with runnable examplesweight 2

2 (weight) × 3 (quality) × 0.6 (partial) = 3.6 of 20 max

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

Download a machine-readable API spec (OpenAPI or equivalent)weight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://developers.fellow.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://developers.fellow.ai/openapi.json, https://developers.fellow.ai/swagger.json, https://developers.fellow.ai/api/openapi.json, https://developers.fellow.ai/.well-known/openapi.json)”

Test against a sandbox environment without touching production dataweight 1

1 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 10 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Rely on versioned APIs with a documented deprecation policyweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://developers.fellow.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://developers.fellow.ai/openapi.json, https://developers.fellow.ai/swagger.json, https://developers.fellow.ai/api/openapi.json, https://developers.fellow.ai/.well-known/openapi.json)”
  • [claimed-docs] https://developers.fellow.ai“The Developer API opens that data to you: transcripts, structured notes, and more, all available through standard REST calls.”
  • [claimed-docs] https://developers.fellow.ai/reference/authentication-1.md“All API requests must include a valid API key in the Authorization header.”

API quality = 3.6 ÷ 70 × 100 = 5.1

Openness33.6/100×0.20 of the PA blend

Can you leave, inspect, or self-host — data export, open source, portability.

Do everything through the API that I can do in the UIweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

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

Export all of my data in open formats and leaveweight 3

3 (weight) × 6 (quality) × 0.6 (partial) = 10.8 of 30 max

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

Read the product's source under an open licenseweight 2

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Self-host the core productweight 3

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Openness = 16.8 ÷ 50 × 100 = 33.6

Built-in AI41.8/100×0.15 of the PA blend

Inside-out: how agentic the product itself is for its users — built-in assistants, autonomous features.

Get AI-generated insights and suggestions from my data inside the productweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [claimed-docs] https://fellow.ai/features/ai-meeting-notes“You automatically receive a clear meeting summary, suggested AI action items, decisions, and topic-based minutes for every meeting.”
  • [claimed-docs] https://developers.fellow.ai/reference/mcp-server.md“Ask anything about your meetings - Get answers to questions like "What were my action items this week?"”
  • [claimed-docs] https://developers.fellow.ai/reference/mcp-server.md“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's standup?"”
  • [claimed-docs] https://fellow.ai/features/mcp-server“Your favorite AI chatbot like Claude, ChatGPT, or Cursor can now tap directly into your meeting recaps, notes, and action items”
  • [claimed-docs] https://developers.fellow.ai/reference/introduction.md“pass transcripts to an LLM for tailored recaps and action plans, the API gives you everything you need to make it happen”
  • [probe] https://developers.fellow.ai/reference/mcp-server.md“PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to Fellow's hosted MCP server https://fellow.app/mcp returned HTTP 401 with `WWW-Authenticate: Bearer realm="Restricted"` — the documented MCP endpoint (get_action_items, get_meeting_transcript, search_meetings, etc.) is live and bearer-gated as documented.”

Set up automations that run autonomously in the backgroundweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

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

Delegate tasks to a built-in AI assistant inside the productweight 3

3 (weight) × 4 (quality) × 0.6 (partial) = 7.2 of 30 max

  • [claimed-docs] https://fellow.ai/features/ai-meeting-notes“You automatically receive a clear meeting summary, suggested AI action items, decisions, and topic-based minutes for every meeting.”
  • [claimed-docs] https://developers.fellow.ai/reference/introduction.md“pass transcripts to an LLM for tailored recaps and action plans, the API gives you everything you need to make it happen”
  • [claimed-docs] https://developers.fellow.ai/reference/mcp-server.md“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] https://fellow.ai/features/mcp-server“Your favorite AI chatbot like Claude, ChatGPT, or Cursor can now tap directly into your meeting recaps, notes, and action items”
  • [claimed-docs] https://developers.fellow.ai/reference/mcp-server.md“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's standup?"”

Operate the product with natural-language commandsweight 2

2 (weight) × 7 (quality) × 0.6 (partial) = 8.4 of 20 max

  • [claimed-docs] https://developers.fellow.ai/reference/mcp-server.md“Ask anything about your meetings - Get answers to questions like "What were my action items this week?"”
  • [claimed-docs] https://help.fellow.ai/en/articles/12622641-fellow-s-mcp-server“Fellow’s MCP Connector works with any AI tool that supports connectors, so you're never locked into one platform”
  • [claimed-docs] https://developers.fellow.ai/reference/mcp-server.md“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] https://fellow.ai/features/mcp-server“Your favorite AI chatbot like Claude, ChatGPT, or Cursor can now tap directly into your meeting recaps, notes, and action items”
  • [claimed-docs] https://developers.fellow.ai/reference/mcp-server.md“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's standup?"”
  • [probe] https://developers.fellow.ai/reference/mcp-server“official MCP server documented at https://developers.fellow.ai/reference/mcp-server”
  • [probe] https://developers.fellow.ai/reference/mcp-server.md“PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to Fellow's hosted MCP server https://fellow.app/mcp returned HTTP 401 with `WWW-Authenticate: Bearer realm="Restricted"` — the documented MCP endpoint (get_action_items, get_meeting_transcript, search_meetings, etc.) is live and bearer-gated as documented.”

Built-in AI = 37.6 ÷ 90 × 100 = 41.8

Automation16.5/100×0.15 of the PA blend

Depth of automation primitives — rules, scheduling, bulk operations, webhooks.

Perform bulk operations across many items at onceweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

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

Define rules that trigger actions automatically on eventsweight 3

3 (weight) × 4 (quality) × 0.6 (partial) = 7.2 of 30 max

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

Schedule recurring jobs or workflowsweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Version, review, and roll back my automationsweight 1

1 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 10 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Automation = 13.2 ÷ 80 × 100 = 16.5