[ { "productId": "fathom", "storyId": "action-items-extraction", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Fathom automatically generates AI action items (fathom-docs-28) and provides webhooks/API that can include action items in structured data delivered to a destination URL (fathom-docs-22, fathom-docs-45), giving PMs a trackable, centralized feed of action items with meeting context. Core capability is well documented and includes runtime confirmation the API is live; missing for 10: explicit evidence of an in-app dashboard specifically tracking action items by owner over time (e.g., a dedicated action-items view) beyond the webhook/API delivery mechanism.", "evidenceIds": [ "fathom-docs-28", "fathom-docs-22", "fathom-docs-45", "fathom-docs-26", "fathom-docs-27", "fathom-probe-rt-2" ] }, { "productId": "fathom", "storyId": "agent-files-action-items", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Fathom's REST API, webhooks, and SDKs expose AI-generated action items and meeting data (fathom-docs-22, fathom-docs-45, fathom-docs-28) that an agent could use to push items into a project tracker, and the MCP server lets AI assistants query meeting data directly. However there is no evidence of a native/pre-built Linear, Jira, or Asana integration — only CRM field sync is mentioned as a native automation. Missing for 10: documented native connectors to Linear/Jira/Asana, and any example/template showing action items being filed into a project tracker end-to-end.", "evidenceIds": [ "fathom-docs-22", "fathom-docs-45", "fathom-docs-28", "fathom-docs-12", "fathom-docs-10", "fathom-probe-rt-1", "fathom-probe-rt-2" ] }, { "productId": "fathom", "storyId": "agentic-agent-docs", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "Fathom serves a live llms.txt at developers.fathom.ai (HTTP 200, confirmed by probe) that indexes its agent-oriented docs, plus a machine-readable OpenAPI spec and MCP server docs, all directly consumable by an AI agent. missing for 10: no independent/third-party report of an agent successfully consuming llms.txt end-to-end.", "evidenceIds": [ "fathom-probe-1", "fathom-probe-rt-3", "fathom-docs-10", "fathom-docs-35" ] }, { "productId": "fathom", "storyId": "agentic-ai-insights", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Fathom generates AI summaries, action items, coaching scorecards, and Deal View insights directly from meeting data (docs-13,14,28,40), and surfaces this data conversationally via an official MCP server connected to ChatGPT/Claude (docs-10,19,35, probe-rt-1), confirmed live at runtime. Missing for 10: independent third-party review of insight quality/accuracy and more detail on how suggestions surface in-app beyond summaries/action items.", "evidenceIds": [ "fathom-docs-13", "fathom-docs-14", "fathom-docs-28", "fathom-docs-40", "fathom-docs-19", "fathom-docs-35", "fathom-docs-10", "fathom-probe-rt-1" ] }, { "productId": "fathom", "storyId": "agentic-autonomous-automation", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Fathom offers webhooks, an API/SDK, and an MCP server that let developers build automations reacting to meeting events, which supports background/autonomous workflows, but Fathom itself does not ship a native no-code 'automations' builder or scheduled/autonomous agent runner — users must write their own integration code or use third-party tools (e.g. Zapier) to achieve full autonomy. missing for 10: a first-party no-code automation/workflow builder, evidence of autonomous scheduled or trigger-based agent tasks running natively within Fathom, and independent confirmation of end-to-end automation use in production.", "evidenceIds": [ "fathom-docs-3", "fathom-docs-22", "fathom-docs-45", "fathom-docs-46", "fathom-docs-10", "fathom-probe-rt-1", "fathom-docs-24" ] }, { "productId": "fathom", "storyId": "agentic-builtin-assistant", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Fathom's pricing page lists a 'Conversational meeting assistant' feature alongside AI summaries and AI-generated action items, suggesting some built-in AI assistant capability, but there is no documentation of what tasks can be delegated to it, how it's invoked, or its scope of autonomy. Most other AI-native evidence (MCP server, API) describes external assistants pulling Fathom's data rather than a built-in assistant acting on the user's behalf inside the product. Missing for 10: detailed docs on the conversational assistant's task-delegation capabilities, examples of it performing actions, and independent/hands-on confirmation.", "evidenceIds": [ "fathom-docs-29", "fathom-docs-28", "fathom-docs-40" ] }, { "productId": "fathom", "storyId": "agentic-headless", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Fathom exposes a documented, live REST API with API-key auth, SDKs, webhooks, and an OpenAPI spec, all of which can be scripted headlessly in CI to pull meeting/transcript/summary data. However, there's no evidence of a CLI tool, official CI/CD templates, or GitHub Actions integration, and Fathom's core value (meeting capture/bot) is not something CI can trigger — automation is limited to data retrieval/webhooks, not the full product experience. missing for 10: dedicated CLI, CI/CD templates or GitHub Actions examples, evidence of automated meeting-capture triggering from CI, independent (non-vendor) confirmation of headless usage.", "evidenceIds": [ "fathom-docs-7", "fathom-docs-24", "fathom-docs-32", "fathom-docs-45", "fathom-probe-rt-2", "fathom-probe-rt-3" ] }, { "productId": "fathom", "storyId": "agentic-mcp-client", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "All MCP evidence describes Fathom as an MCP *server* that other AI assistants (Claude, ChatGPT) connect to, not Fathom acting as an MCP client that plugs in external MCP servers to use their tools. No evidence shows Fathom's own AI/assistant features consuming external MCP tool servers.", "evidenceIds": [ "fathom-docs-10", "fathom-docs-19", "fathom-docs-33", "fathom-docs-35", "fathom-probe-rt-1" ] }, { "productId": "fathom", "storyId": "agentic-mcp-server", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "Fathom ships an official hosted MCP server (api.fathom.ai/mcp) documented for connecting AI assistants like Claude and ChatGPT, with official connector status in Claude and CLI setup instructions, and a runtime probe confirms the endpoint is live and speaks MCP OAuth. Missing for 10: independent third-party (non-vendor) hands-on confirmation of the agent connection working end-to-end.", "evidenceIds": [ "fathom-docs-10", "fathom-docs-11", "fathom-docs-19", "fathom-docs-25", "fathom-docs-34", "fathom-docs-35", "fathom-probe-3", "fathom-probe-rt-1" ] }, { "productId": "fathom", "storyId": "agentic-nl-commands", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Fathom ships an official MCP server and official connectors for Claude/ChatGPT, letting users query and interact with meeting data via natural-language prompts in those assistants, and lists a 'Conversational meeting assistant' as a product feature — both are corroborated by live runtime probes of the MCP endpoint. Missing for 10: evidence of a native in-app natural-language command interface (e.g., voice/text commands to control Fathom itself rather than just query data through third-party assistants), and independent user reports of successful conversational task execution beyond data retrieval.", "evidenceIds": [ "fathom-docs-10", "fathom-docs-19", "fathom-docs-29", "fathom-docs-33", "fathom-docs-35", "fathom-probe-rt-1" ] }, { "productId": "fathom", "storyId": "agentic-official-cli", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Fathom is a meeting-recording/API SaaS product, not an agentic coding tool; the evidence shows REST API, SDKs, webhooks, and an MCP server, but no mention of an official CLI tool for AI-native workflows. This axis is more relevant to developer/agent tools, but since Fathom does offer a developer platform, absence of a CLI would normally be 'none' rather than 'na' — however no CLI-specific evidence exists at all, making this a fair 'none' call.", "evidenceIds": [] }, { "productId": "fathom", "storyId": "agentic-public-api", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "Fathom publishes a full public REST API with API-key auth, official TypeScript/Python SDKs, webhooks, and a machine-readable OpenAPI 3.1.1 spec, and runtime probes confirm the documented endpoints are live and match the docs exactly. This gives AI-native users a fully documented, verifiable way to drive the product programmatically beyond just MCP/chat connectors. Missing for 10: independent third-party developer reviews/case studies of building against the API.", "evidenceIds": [ "fathom-docs-7", "fathom-docs-24", "fathom-docs-32", "fathom-probe-rt-2", "fathom-probe-rt-3", "fathom-probe-2" ] }, { "productId": "fathom", "storyId": "agentic-scoped-keys", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Fathom's docs describe generating a single account-wide API key in User Settings (fathom-docs-1, fathom-docs-7) and a separate OAuth flow for public apps (fathom-docs-5, fathom-docs-21), but nowhere do the docs describe scopes, roles, or least-privilege permission grants that an AI agent could be issued. The 'users and permissions' endpoint (fathom-docs-9) and admin view-permission controls (fathom-docs-38) govern user-level meeting visibility, not credential scoping for agents. No evidence of restricting an API key/OAuth token to specific resources or actions for agentic use.", "evidenceIds": [ "fathom-docs-1", "fathom-docs-7", "fathom-docs-5", "fathom-docs-21", "fathom-docs-9", "fathom-docs-38" ] }, { "productId": "fathom", "storyId": "agentic-sdks", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "Fathom documents official TypeScript and Python SDKs that handle auth, pagination, error handling, plus webhook verification helpers, backed by a live REST API and OpenAPI spec confirmed via runtime probes. Missing for 10: independent (non-vendor) developer testimonials or hands-on third-party validation of the SDKs.", "evidenceIds": [ "fathom-docs-4", "fathom-docs-24", "fathom-docs-32", "fathom-docs-23", "fathom-probe-rt-2", "fathom-probe-rt-3" ] }, { "productId": "fathom", "storyId": "agentic-webhooks", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "Fathom offers documented webhook subscription for meeting events (create-a-webhook API, configurable payload fields like transcript/summary/action items/CRM matches), with signature-based verification via headers and an SDK helper (verify_webhook), all corroborated by docs and consistent with the live API surface. missing for 10: no independent third-party hands-on report of webhook delivery reliability beyond first-party docs.", "evidenceIds": [ "fathom-docs-3", "fathom-docs-22", "fathom-docs-45", "fathom-docs-46", "fathom-docs-6", "fathom-docs-23", "fathom-docs-31", "fathom-probe-rt-2" ] }, { "productId": "fathom", "storyId": "api-interactive-docs", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Fathom publishes a full API reference with per-endpoint docs (get-transcript, get-summary, create-a-webhook) and a machine-readable OpenAPI 3.1.1 spec confirmed live at runtime, plus SDKs that simplify calling those endpoints — this gives structured, machine-consumable reference material an AI-native user could explore. However, there's no evidence of an interactive 'try-it-now' console or embedded runnable code examples in the docs themselves (the openapi.json/swagger.json UI paths probed 404, suggesting no rendered interactive explorer). Missing for 10: an in-browser interactive API playground/try-it-now widget, evidence of executable/runnable code snippets directly in docs, and independent confirmation of this interactive experience.", "evidenceIds": [ "fathom-docs-26", "fathom-docs-27", "fathom-docs-24", "fathom-probe-2", "fathom-probe-rt-3" ] }, { "productId": "fathom", "storyId": "api-machine-spec", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Fathom publishes a machine-readable OpenAPI 3.1.1 spec at developers.fathom.ai/api-reference/openapi.yaml, confirmed by a runtime fetch, and this URL is advertised in the site's own llms.txt. Missing for 10: discoverability at conventional paths (openapi.json/swagger.json all 404) and independent third-party corroboration beyond the vendor's own runtime probe.", "evidenceIds": [ "fathom-probe-rt-3", "fathom-probe-1", "fathom-docs-7" ] }, { "productId": "fathom", "storyId": "api-sandbox", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Fathom is a meeting-recording/transcription SaaS product, not a developer platform with test/sandbox environments as a distinguishing product concern in the way this story implies; there's no evidence of any staging/test environment concept, and the product's data (real meeting recordings) is inherently 'production' by nature — sandboxing against fake data is not a fit axis for this kind of product.", "evidenceIds": [] }, { "productId": "fathom", "storyId": "api-versioning-policy", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Fathom publishes an OpenAPI spec (versioned 1.0.0) and a changelog tracking added endpoints, but there is no evidence of a documented API versioning scheme or a deprecation policy for breaking changes.", "evidenceIds": [ "fathom-docs-8", "fathom-docs-9", "fathom-probe-rt-3" ] }, { "productId": "fathom", "storyId": "automation-bulk-operations", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Fathom's API supports listing meetings, retrieving transcripts/summaries, and webhooks, which could be scripted to iterate across many meetings, but there is no documented bulk/batch endpoint, no pagination-across-thousands example, and no explicit bulk-operations feature (e.g., bulk export, bulk delete, bulk tagging) called out anywhere. missing for 10: dedicated bulk/batch API endpoints, documented pagination for large-scale iteration, bulk write/update operations, and any hands-on evidence of performing bulk actions across many items.", "evidenceIds": [ "fathom-docs-2", "fathom-docs-20", "fathom-docs-24", "fathom-probe-rt-2", "fathom-probe-rt-3" ] }, { "productId": "fathom", "storyId": "automation-rules-engine", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Fathom supports event-driven automation via webhooks (triggered on new meeting content, with signature verification) and topic monitoring alerts, which act as reactive triggers, but there is no evidence of a user-facing rules engine where AI-native users can define arbitrary conditional logic ('if X then do Y') beyond webhook subscriptions to fixed meeting events. missing for 10: a configurable rules/conditions engine, support for custom trigger logic beyond meeting-completion events, and evidence of chained multi-step automated actions.", "evidenceIds": [ "fathom-docs-3", "fathom-docs-22", "fathom-docs-45", "fathom-docs-46", "fathom-docs-18", "fathom-docs-12" ] }, { "productId": "fathom", "storyId": "automation-scheduled-jobs", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Fathom is a meeting-notes/transcription product with an API, webhooks, and MCP connector, but nothing in the evidence describes scheduling recurring jobs or automated workflow runs (e.g., cron-like triggers, recurring exports, or repeated automation tasks). Webhooks are event-driven (post-meeting), not scheduled/recurring job execution.", "evidenceIds": [ "fathom-docs-22", "fathom-docs-45", "fathom-docs-3" ] }, { "productId": "fathom", "storyId": "automation-versioned-workflows", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Fathom is a meeting-recording/AI-notes product with API, webhook, and MCP integrations, not a workflow/automation builder with version-controlled steps to review or roll back. Versioning/rollback of automations is a category error for this product type; there's no evidence of an automation-authoring surface at all.", "evidenceIds": [] }, { "productId": "fathom", "storyId": "bot-capture-major-platforms", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Evidence confirms Fathom offers flexible recording capture options (bot-based or bot-free/beta) and a 'custom meeting bot' tier, addressing the 'recording where I want it' part of the story, but the evidence pack never explicitly names Zoom, Google Meet, or Microsoft Teams as supported platforms. Missing for 10: explicit platform-by-platform support confirmation for Zoom/Meet/Teams, reliability/uptime evidence, and independent hands-on corroboration of capture across all three platforms.", "evidenceIds": [ "fathom-docs-17", "fathom-docs-39", "fathom-docs-41" ] }, { "productId": "fathom", "storyId": "botless-audio-capture", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Fathom's pricing page explicitly advertises a 'bot-free (in beta)' capture option alongside bot capture, and homepage marketing states \"Capture notes your way – bot or no bot – so you can stay focused on the meeting,\" indicating device-based audio capture without a visible bot joining the call. However, this is labeled beta with no technical documentation on how bot-free capture works, no confirmation it captures external participants' audio without their knowledge, and no independent/hands-on corroboration of the feature working as described. Missing for 10: technical docs on bot-free capture mechanism, confirmation of transcription quality/reliability in bot-free mode, independent user reports validating the beta feature works as claimed.", "evidenceIds": [ "fathom-docs-17", "fathom-docs-39" ] }, { "productId": "fathom", "storyId": "calendar-autojoin-rules", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "The evidence pack contains no mention of connecting a Google/Outlook calendar or configuring per-meeting-type auto-capture rules; it only covers API/webhook/SDK/MCP integration and pricing tiers (bot vs bot-free capture, custom bot) with no calendar-workflow specifics.", "evidenceIds": [] }, { "productId": "fathom", "storyId": "chat-with-meeting-history", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Fathom advertises a 'Conversational meeting assistant' and 'search across calls' feature, and its official MCP server explicitly lets you bring 'your meeting data...inside ChatGPT, Claude, and more,' enabling natural-language queries over meeting history via a connected AI assistant. However, there's no first-party documentation describing how the built-in conversational assistant answers questions with cited sources, nor detail on cross-meeting recall depth or accuracy. Missing for 10: documented answer format/sourcing for the conversational assistant, evidence of true whole-history semantic search (vs. per-meeting), and independent/hands-on verification of source-accurate answers.", "evidenceIds": [ "fathom-docs-29", "fathom-docs-30", "fathom-docs-19", "fathom-docs-10", "fathom-docs-35", "fathom-probe-rt-1" ] }, { "productId": "fathom", "storyId": "clips-highlights-share", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Pricing page mentions 'Clips, playlists + search across calls' and 'Playlists of highlights from meetings', indicating Fathom supports creating and sharing highlight clips, but there's no documentation on how clipping/sharing actually works (UI flow, sharing mechanism, permissions). Missing for 10: detailed docs or hands-on evidence of the clip-creation workflow, sharing a clip link vs whole recording, and any independent corroboration.", "evidenceIds": [ "fathom-docs-30", "fathom-docs-15" ] }, { "productId": "fathom", "storyId": "consent-notification-features", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack covers API/SDK/webhook/MCP integration and pricing tiers (bot vs bot-free capture, SSO/SCIM) but contains no mention of participant consent notifications, in-meeting recording disclosure banners, or admin-enforced transparency controls — the core capabilities this story asks about. As a meeting-recording product, this axis clearly applies, but no evidence shows it being delivered.", "evidenceIds": [] }, { "productId": "fathom", "storyId": "crm-auto-sync", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Fathom's pricing page explicitly advertises 'CRM field sync, updating records after meetings automatically' and Deal View summarizing insights, indicating native CRM record sync exists, but the evidence pack gives no detail on which CRMs (HubSpot, Salesforce, Attio explicitly named) are supported, how contact/deal matching works, or setup/configuration steps, and no independent/hands-on confirmation of reliability. missing for 10: named support for HubSpot/Salesforce/Attio specifically, technical documentation of the CRM sync mechanism, and independent verification that notes land on the correct contact/deal records.", "evidenceIds": [ "fathom-docs-12", "fathom-docs-13" ] }, { "productId": "fathom", "storyId": "custom-templates-prompts", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows AI summaries, action items, and 'advanced/custom call summaries' as a pricing feature, but nothing describes per-meeting-type custom templates or saved prompts (e.g., discovery call vs 1:1 vs standup) that a sales lead could configure and reuse.", "evidenceIds": [ "fathom-docs-40", "fathom-docs-47" ] }, { "productId": "fathom", "storyId": "followup-email-draft", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Fathom's evidence pack covers AI summaries, action items, CRM sync, and conversational meeting assistant features, but nowhere mentions drafting a follow-up email from a meeting for review-and-send. This is a plausible capability for a meeting-notes tool, but no evidence supports it.", "evidenceIds": [] }, { "productId": "fathom", "storyId": "meeting-mcp-server", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "Fathom ships an official hosted MCP server (api.fathom.ai/mcp) documented and installable as an official connector in Claude/ChatGPT via OAuth, with a runtime probe confirming it's live and enforces the MCP OAuth flow (401 + WWW-Authenticate pointing to oauth-protected-resource metadata), matching the story's search/transcript/action-items and no-glue-code OAuth requirements. Missing for 10: independent third-party (non-vendor) hands-on confirmation of query capabilities like search/action-items specifically through the MCP tool surface.", "evidenceIds": [ "fathom-docs-10", "fathom-docs-11", "fathom-docs-19", "fathom-docs-25", "fathom-docs-34", "fathom-docs-35", "fathom-probe-3", "fathom-probe-rt-1" ] }, { "productId": "fathom", "storyId": "mobile-in-person-capture", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence pack describes Fathom as a virtual-meeting recorder (bot or bot-free capture of online calls) with API/webhook/MCP integrations, but nothing mentions a mobile app or capturing in-person, non-virtual conversations.", "evidenceIds": [ "fathom-docs-17", "fathom-docs-39", "fathom-docs-18" ] }, { "productId": "fathom", "storyId": "multilingual-meetings", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "The evidence pack contains no mention of multi-language transcription/summary support or language-switching handling anywhere in Fathom's docs, changelog, or pricing pages — all references focus on API access, webhooks, MCP integration, and English-oriented feature descriptions.", "evidenceIds": [] }, { "productId": "fathom", "storyId": "no-training-on-my-data", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence in the pack addresses AI training data usage policy, opt-out mechanisms, or SOC 2/HIPAA compliance posture; the docs cover API access, webhooks, SDKs, and MCP integration only. missing for 10: explicit documentation on whether meeting data is used to train AI models, an enforceable opt-out mechanism for orgs, and SOC 2/HIPAA compliance attestations.", "evidenceIds": [] }, { "productId": "fathom", "storyId": "openness-api-parity", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Fathom's REST API/SDKs cover core meeting data (list meetings, transcripts, summaries, recordings, webhooks, users/permissions) confirmed live via runtime probes, so a solid subset of UI functionality is API-accessible. However, many UI/pricing-page features—CRM field sync, Deal View, coaching metrics/scorecards, playlists, comments/folders/keyword alerts, custom bot configuration, SSO/SCIM—have no corresponding documented API endpoints in the evidence, so full UI parity is not demonstrated. Missing for 10: API endpoints for CRM sync, Deal View, coaching/scorecards, playlists/collaboration features, and admin SSO/SCIM management.", "evidenceIds": [ "fathom-docs-2", "fathom-docs-8", "fathom-docs-9", "fathom-docs-22", "fathom-docs-24", "fathom-probe-rt-2", "fathom-probe-rt-3", "fathom-docs-12", "fathom-docs-13", "fathom-docs-14", "fathom-docs-42" ] }, { "productId": "fathom", "storyId": "openness-full-export", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Fathom's REST API and SDKs let a user programmatically list all meetings, fetch transcripts/summaries, and download recordings, giving JSON/media exports usable outside the platform (fathom-docs-2, fathom-docs-8, fathom-docs-26, fathom-docs-27, fathom-probe-rt-3). However there is no documented one-click 'export all my data' bulk tool or explicit data-portability/account-deletion guarantee, so a user must build their own export script via the API. Missing for 10: a first-party bulk export/archival feature, explicit data-portability policy, and independent confirmation that full historical data (not just per-meeting calls) can be retrieved and account fully closed out.", "evidenceIds": [ "fathom-docs-2", "fathom-docs-8", "fathom-docs-26", "fathom-docs-27", "fathom-docs-24", "fathom-probe-rt-3" ] }, { "productId": "fathom", "storyId": "openness-open-license", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Fathom is a closed-source SaaS product; the evidence pack shows only API/SDK/MCP documentation and pricing, with no mention of any open-source license or publicly readable source repository for the core product.", "evidenceIds": [] }, { "productId": "fathom", "storyId": "openness-self-host", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Fathom is a hosted SaaS meeting-recording/transcription product with cloud-only API, webhooks, and MCP server; there is no evidence of a self-hostable core product, and this category error means self-hosting is not a plausible axis for this type of service.", "evidenceIds": [] }, { "productId": "fathom", "storyId": "pre-meeting-context", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence covers recording, transcription, summaries, search across calls, CRM sync, and MCP/API access, but nothing documents a proactive pre-meeting brief that surfaces past meetings with the same attendees or open threads ahead of a call — that specific calendar-workflow prep feature is absent from the pack.", "evidenceIds": [] }, { "productId": "fathom", "storyId": "privacy-data-residency", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence in the pack mentions data residency, regional storage options, or geographic control over where Fathom stores data; all evidence concerns API/SDK/MCP/webhook functionality and pricing tiers. missing for 10: any mention of region selection, data residency options, or storage location controls.", "evidenceIds": [] }, { "productId": "fathom", "storyId": "privacy-no-training", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack addresses AI-training data usage, opt-out settings, or data-privacy policies regarding model training; the evidence is entirely about API/SDK/MCP integration features.", "evidenceIds": [] }, { "productId": "fathom", "storyId": "privacy-retention-controls", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "The evidence pack covers API access, webhooks, MCP integration, and SDKs, but contains no mention of data retention policies, deletion controls, or user ability to delete recordings/transcripts/data. No documentation of retention settings, data export/purge tools, or deletion endpoints is present.", "evidenceIds": [] }, { "productId": "fathom", "storyId": "privacy-telemetry-optout", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence pack item mentions telemetry, usage tracking, analytics opt-out, or privacy settings of that kind; documentation covers API, webhooks, MCP, and pricing features only.", "evidenceIds": [] }, { "productId": "fathom", "storyId": "retention-deletion-controls", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence in the pack mentions retention policies, scheduled auto-deletion of transcripts/recordings, or an on-demand data erasure mechanism for admins; evidence only covers API access, webhooks, SDKs, MCP connectors, and pricing tiers.", "evidenceIds": [] }, { "productId": "fathom", "storyId": "search-across-meetings", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Fathom advertises 'Clips, playlists + search across calls' and keyword alerts/highlights, plus transcripts/summaries accessible via API, suggesting cross-meeting search exists, but the evidence never shows a concrete product UI for searching all transcripts/notes and jumping to a timestamped moment. missing for 10: a documented search UI/feature description showing full-text search across all past meetings with timestamp jump-to, independent/hands-on confirmation of search accuracy or scope, and detail on whether notes (not just transcripts/summaries) are indexed.", "evidenceIds": [ "fathom-docs-30", "fathom-docs-16", "fathom-docs-18", "fathom-docs-26", "fathom-docs-27" ] }, { "productId": "fathom", "storyId": "sharing-permissions-controls", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Fathom docs mention admin-configurable view permissions for shared meetings and a dedicated users/permissions API endpoint, plus folders as an organizational feature, suggesting some admin control over sharing. However there's no evidence of private-by-default notes, granular link-level or workspace-level permission settings, or a dedicated admin dashboard for visibility into what's shared.\n\nmissing for 10: private-by-default note settings, granular link-sharing permissions, workspace-level permission tiers, an admin audit/visibility dashboard for shared content.", "evidenceIds": [ "fathom-docs-38", "fathom-docs-9", "fathom-docs-16", "fathom-docs-42" ] }, { "productId": "fathom", "storyId": "slack-notion-zapier-push", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack shows generic developer infrastructure (REST API, webhooks, SDKs, MCP server for AI assistants) but contains no mention of native Slack, Notion, or Zapier integrations, nor a listed Zapier app — the specific 'thousands of apps' claim in the story has no supporting citation.", "evidenceIds": [] }, { "productId": "fathom", "storyId": "speaker-identification", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack addresses diarization or speaker-name matching in transcripts; the pack only covers API access, webhooks, MCP integration, and pricing tiers. This is a fair axis for a meeting-transcription product, but nothing here confirms accurate speaker attribution or real-name matching.", "evidenceIds": [] }, { "productId": "fathom", "storyId": "structured-ai-summaries", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Fathom's core product delivers AI-generated call summaries and action items immediately after calls (fathom-docs-40, fathom-docs-28, fathom-docs-47), retrievable via the get-summary API endpoint (fathom-docs-27/37), matching the PM's need for a shareable post-meeting summary. Missing for 10: explicit documentation of 'decisions' as a distinct summary field and independent/hands-on evidence of summary quality being 'good enough to share without editing'.", "evidenceIds": [ "fathom-docs-40", "fathom-docs-28", "fathom-docs-47", "fathom-docs-27", "fathom-docs-37" ] }, { "productId": "fathom", "storyId": "transcription-quality-claims", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "The evidence pack contains extensive docs on API access, webhooks, MCP integration, and pricing tiers, but nothing about transcription models, accuracy claims, language support, or known limitations of the transcription/AI engine itself — everything is marketed generically as 'AI summaries' or 'AI generated action items' without technical detail.", "evidenceIds": [] }, { "productId": "fathom", "storyId": "transcripts-via-api", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "Fathom exposes a documented REST API with self-serve API-key generation, dedicated endpoints for transcripts and summaries, and webhook payloads that can include transcript/summary/action items, plus official SDKs and a live runtime-verified API surface with OpenAPI spec. Missing for 10: a clearly documented standalone REST 'get action items' endpoint (action items appear only bundled via webhook payloads) and independent (non-vendor) developer corroboration.", "evidenceIds": [ "fathom-docs-1", "fathom-docs-7", "fathom-docs-26", "fathom-docs-27", "fathom-docs-45", "fathom-docs-24", "fathom-probe-rt-2", "fathom-probe-rt-3" ] }, { "productId": "fathom", "storyId": "transparent-pricing-free-tier", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "The pricing page evidence lists many tier-specific features (CRM sync, coaching metrics, SSO/SCIM, custom bot, etc.) implying a public pricing/feature comparison exists, but no evidence shows actual dollar amounts, a free tier definition, or confirmation that basic use avoids a 'talk to sales' gate for enterprise features like SSO/SCIM. Missing for 10: explicit price figures per tier, confirmation of a self-serve free plan, and absence of a sales-contact requirement for advanced tiers.", "evidenceIds": [ "fathom-docs-12", "fathom-docs-13", "fathom-docs-14", "fathom-docs-41", "fathom-docs-42" ] }, { "productId": "fellow", "storyId": "action-items-extraction", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "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.", "evidenceIds": [ "fellow-docs-23", "fellow-docs-5", "fellow-docs-19", "fellow-docs-32", "fellow-docs-31" ] }, { "productId": "fellow", "storyId": "agent-files-action-items", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "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.", "evidenceIds": [ "fellow-docs-5", "fellow-docs-17", "fellow-docs-18", "fellow-docs-31", "fellow-probe-rt-1" ] }, { "productId": "fellow", "storyId": "agentic-agent-docs", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "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.", "evidenceIds": [ "fellow-probe-1", "fellow-docs-31", "fellow-probe-3" ] }, { "productId": "fellow", "storyId": "agentic-ai-insights", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "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.", "evidenceIds": [ "fellow-docs-23", "fellow-docs-8", "fellow-docs-32", "fellow-docs-26", "fellow-docs-31", "fellow-probe-rt-1" ] }, { "productId": "fellow", "storyId": "agentic-autonomous-automation", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fellow-docs-23", "fellow-docs-3", "fellow-docs-17", "fellow-docs-31", "fellow-docs-1" ] }, { "productId": "fellow", "storyId": "agentic-builtin-assistant", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "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.", "evidenceIds": [ "fellow-docs-23", "fellow-docs-31", "fellow-docs-18", "fellow-docs-26", "fellow-docs-32" ] }, { "productId": "fellow", "storyId": "agentic-headless", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "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.)", "evidenceIds": [] }, { "productId": "fellow", "storyId": "agentic-mcp-client", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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.", "evidenceIds": [] }, { "productId": "fellow", "storyId": "agentic-mcp-server", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "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.", "evidenceIds": [ "fellow-docs-18", "fellow-docs-9", "fellow-docs-10", "fellow-docs-26", "fellow-probe-3", "fellow-probe-rt-1" ] }, { "productId": "fellow", "storyId": "agentic-nl-commands", "verdict": "partial", "quality": 7, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fellow-docs-8", "fellow-docs-9", "fellow-docs-18", "fellow-docs-26", "fellow-docs-32", "fellow-probe-3", "fellow-probe-rt-1" ] }, { "productId": "fellow", "storyId": "agentic-official-cli", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Fellow is a meeting-notes/API platform, not an AI agent, so an 'official CLI' is a plausible ecosystem tool but no evidence exists; however, evidence pack only covers REST API/MCP server, no CLI is mentioned anywhere, and the product's primary offerings (API, webhooks, MCP) don't constitute a CLI. Given the axis could apply to a platform like this, absence of evidence should be 'none' rather than 'na' — reconsidering, this should be 'none'.", "evidenceIds": [] }, { "productId": "fellow", "storyId": "agentic-public-api", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "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.", "evidenceIds": [ "fellow-docs-1", "fellow-docs-2", "fellow-docs-4", "fellow-docs-5", "fellow-docs-6", "fellow-docs-17", "fellow-probe-2" ] }, { "productId": "fellow", "storyId": "agentic-scoped-keys", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fellow-docs-10", "fellow-docs-7", "fellow-docs-14", "fellow-docs-16", "fellow-docs-2" ] }, { "productId": "fellow", "storyId": "agentic-sdks", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fellow-docs-1", "fellow-docs-2", "fellow-docs-15", "fellow-docs-16", "fellow-probe-2" ] }, { "productId": "fellow", "storyId": "agentic-webhooks", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fellow-docs-3", "fellow-docs-17" ] }, { "productId": "fellow", "storyId": "api-interactive-docs", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "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.", "evidenceIds": [ "fellow-docs-4", "fellow-docs-5", "fellow-docs-6", "fellow-docs-1", "fellow-probe-2" ] }, { "productId": "fellow", "storyId": "api-machine-spec", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "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.", "evidenceIds": [ "fellow-probe-2" ] }, { "productId": "fellow", "storyId": "api-sandbox", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "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.", "evidenceIds": [] }, { "productId": "fellow", "storyId": "api-versioning-policy", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fellow-probe-2", "fellow-docs-1", "fellow-docs-2" ] }, { "productId": "fellow", "storyId": "automation-bulk-operations", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fellow-docs-4", "fellow-docs-5", "fellow-docs-14", "fellow-docs-25" ] }, { "productId": "fellow", "storyId": "automation-rules-engine", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fellow-docs-3", "fellow-docs-17", "fellow-docs-31" ] }, { "productId": "fellow", "storyId": "automation-scheduled-jobs", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "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.", "evidenceIds": [] }, { "productId": "fellow", "storyId": "automation-versioned-workflows", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "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.", "evidenceIds": [] }, { "productId": "fellow", "storyId": "bot-capture-major-platforms", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fellow-docs-11", "fellow-docs-20", "fellow-docs-27", "fellow-docs-29" ] }, { "productId": "fellow", "storyId": "botless-audio-capture", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fellow-docs-11", "fellow-docs-20", "fellow-docs-21", "fellow-docs-27" ] }, { "productId": "fellow", "storyId": "calendar-autojoin-rules", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "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.", "evidenceIds": [ "fellow-docs-12", "fellow-docs-27", "fellow-docs-29", "fellow-docs-28" ] }, { "productId": "fellow", "storyId": "chat-with-meeting-history", "verdict": "partial", "quality": 7, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fellow-docs-8", "fellow-docs-18", "fellow-docs-32", "fellow-docs-21", "fellow-probe-rt-1", "fellow-probe-3" ] }, { "productId": "fellow", "storyId": "clips-highlights-share", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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.", "evidenceIds": [] }, { "productId": "fellow", "storyId": "consent-notification-features", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fellow-docs-11", "fellow-docs-20", "fellow-docs-27", "fellow-docs-12", "fellow-docs-28", "fellow-docs-29" ] }, { "productId": "fellow", "storyId": "crm-auto-sync", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fellow-docs-1", "fellow-docs-3", "fellow-docs-17", "fellow-docs-31" ] }, { "productId": "fellow", "storyId": "custom-templates-prompts", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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.", "evidenceIds": [] }, { "productId": "fellow", "storyId": "followup-email-draft", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fellow-docs-23", "fellow-docs-31", "fellow-docs-8", "fellow-docs-32" ] }, { "productId": "fellow", "storyId": "meeting-mcp-server", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "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.", "evidenceIds": [ "fellow-docs-8", "fellow-docs-9", "fellow-docs-10", "fellow-docs-18", "fellow-docs-26", "fellow-docs-32", "fellow-probe-3", "fellow-probe-rt-1" ] }, { "productId": "fellow", "storyId": "mobile-in-person-capture", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fellow-docs-20", "fellow-docs-21", "fellow-docs-27" ] }, { "productId": "fellow", "storyId": "multilingual-meetings", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "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.", "evidenceIds": [] }, { "productId": "fellow", "storyId": "no-training-on-my-data", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fellow-docs-12", "fellow-docs-28", "fellow-docs-29" ] }, { "productId": "fellow", "storyId": "openness-api-parity", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fellow-docs-1", "fellow-docs-4", "fellow-docs-5", "fellow-docs-6", "fellow-docs-17", "fellow-docs-31", "fellow-probe-2" ] }, { "productId": "fellow", "storyId": "openness-full-export", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fellow-docs-1", "fellow-docs-4", "fellow-docs-5", "fellow-docs-14", "fellow-docs-31" ] }, { "productId": "fellow", "storyId": "openness-open-license", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Fellow is a closed-source SaaS meeting-notes product; no evidence of any open-source licensing of its codebase. Source-code openness is not an applicable axis for this type of proprietary commercial product.", "evidenceIds": [] }, { "productId": "fellow", "storyId": "openness-self-host", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Fellow is a SaaS meeting-notes product with no evidence of a self-hostable core offering; self-hosting is not a fair axis for this cloud-native product category, so it does not apply.", "evidenceIds": [] }, { "productId": "fellow", "storyId": "pre-meeting-context", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fellow-docs-21", "fellow-docs-32", "fellow-docs-8", "fellow-docs-26", "fellow-docs-31" ] }, { "productId": "fellow", "storyId": "privacy-data-residency", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "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.", "evidenceIds": [] }, { "productId": "fellow", "storyId": "privacy-no-training", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "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.", "evidenceIds": [] }, { "productId": "fellow", "storyId": "privacy-retention-controls", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fellow-docs-28", "fellow-docs-12", "fellow-docs-14", "fellow-docs-29" ] }, { "productId": "fellow", "storyId": "privacy-telemetry-optout", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "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.", "evidenceIds": [] }, { "productId": "fellow", "storyId": "retention-deletion-controls", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fellow-docs-28", "fellow-docs-14", "fellow-docs-12", "fellow-docs-29" ] }, { "productId": "fellow", "storyId": "search-across-meetings", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fellow-docs-21", "fellow-docs-8", "fellow-docs-32", "fellow-docs-26", "fellow-probe-rt-1", "fellow-probe-3" ] }, { "productId": "fellow", "storyId": "sharing-permissions-controls", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "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.", "evidenceIds": [ "fellow-docs-10", "fellow-docs-12", "fellow-docs-14", "fellow-docs-25", "fellow-docs-28", "fellow-docs-29" ] }, { "productId": "fellow", "storyId": "slack-notion-zapier-push", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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.", "evidenceIds": [] }, { "productId": "fellow", "storyId": "speaker-identification", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "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'.", "evidenceIds": [] }, { "productId": "fellow", "storyId": "structured-ai-summaries", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fellow-docs-23", "fellow-docs-21", "fellow-docs-11" ] }, { "productId": "fellow", "storyId": "transcription-quality-claims", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "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.", "evidenceIds": [] }, { "productId": "fellow", "storyId": "transcripts-via-api", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "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.", "evidenceIds": [ "fellow-docs-1", "fellow-docs-2", "fellow-docs-4", "fellow-docs-5", "fellow-docs-15", "fellow-docs-16", "fellow-docs-17", "fellow-docs-31", "fellow-probe-1", "fellow-probe-2", "fellow-probe-rt-1" ] }, { "productId": "fellow", "storyId": "transparent-pricing-free-tier", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "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.", "evidenceIds": [ "fellow-docs-13", "fellow-docs-22" ] }, { "productId": "fireflies", "storyId": "action-items-extraction", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fireflies-docs-10", "fireflies-docs-21", "fireflies-docs-5" ] }, { "productId": "fireflies", "storyId": "agent-files-action-items", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fireflies-docs-5", "fireflies-docs-6", "fireflies-docs-16", "fireflies-docs-23", "fireflies-probe-rt-3", "fireflies-docs-10" ] }, { "productId": "fireflies", "storyId": "agentic-agent-docs", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "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.", "evidenceIds": [ "fireflies-probe-1", "fireflies-probe-rt-2", "fireflies-docs-7" ] }, { "productId": "fireflies", "storyId": "agentic-ai-insights", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fireflies-docs-10", "fireflies-docs-18", "fireflies-docs-24", "fireflies-docs-26" ] }, { "productId": "fireflies", "storyId": "agentic-autonomous-automation", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "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.", "evidenceIds": [ "fireflies-docs-9", "fireflies-docs-15", "fireflies-docs-21", "fireflies-docs-14" ] }, { "productId": "fireflies", "storyId": "agentic-builtin-assistant", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "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.", "evidenceIds": [ "fireflies-docs-9", "fireflies-docs-18", "fireflies-docs-10" ] }, { "productId": "fireflies", "storyId": "agentic-headless", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fireflies-docs-3", "fireflies-docs-4", "fireflies-docs-5", "fireflies-probe-rt-3", "fireflies-docs-17" ] }, { "productId": "fireflies", "storyId": "agentic-mcp-client", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fireflies-docs-7", "fireflies-docs-8", "fireflies-probe-3", "fireflies-probe-rt-1", "fireflies-probe-rt-2" ] }, { "productId": "fireflies", "storyId": "agentic-mcp-server", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "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.", "evidenceIds": [ "fireflies-docs-7", "fireflies-docs-8", "fireflies-docs-30", "fireflies-probe-3", "fireflies-probe-rt-1", "fireflies-probe-rt-2" ] }, { "productId": "fireflies", "storyId": "agentic-nl-commands", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fireflies-docs-18", "fireflies-docs-8", "fireflies-docs-24", "fireflies-docs-30", "fireflies-probe-rt-1", "fireflies-probe-3" ] }, { "productId": "fireflies", "storyId": "agentic-official-cli", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Fireflies is a meeting-transcription SaaS with a GraphQL API and MCP servers; an 'official CLI' is not a category-fit axis for this product type — no CLI is mentioned anywhere, and the product's AI-native access is delivered via API/MCP, not a command-line tool.", "evidenceIds": [] }, { "productId": "fireflies", "storyId": "agentic-public-api", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "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.", "evidenceIds": [ "fireflies-docs-3", "fireflies-docs-4", "fireflies-docs-5", "fireflies-docs-16", "fireflies-docs-17", "fireflies-probe-rt-3", "fireflies-probe-2" ] }, { "productId": "fireflies", "storyId": "agentic-scoped-keys", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fireflies-docs-2", "fireflies-docs-3", "fireflies-docs-23", "fireflies-docs-30", "fireflies-docs-25" ] }, { "productId": "fireflies", "storyId": "agentic-sdks", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fireflies-docs-16", "fireflies-docs-3", "fireflies-probe-2" ] }, { "productId": "fireflies", "storyId": "agentic-webhooks", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "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.", "evidenceIds": [] }, { "productId": "fireflies", "storyId": "api-interactive-docs", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fireflies-docs-4", "fireflies-docs-5", "fireflies-docs-16", "fireflies-probe-2" ] }, { "productId": "fireflies", "storyId": "api-machine-spec", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "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.", "evidenceIds": [ "fireflies-probe-2", "fireflies-docs-16" ] }, { "productId": "fireflies", "storyId": "api-sandbox", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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.", "evidenceIds": [] }, { "productId": "fireflies", "storyId": "api-versioning-policy", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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.", "evidenceIds": [] }, { "productId": "fireflies", "storyId": "automation-bulk-operations", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "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.", "evidenceIds": [ "fireflies-docs-5", "fireflies-docs-29", "fireflies-docs-4", "fireflies-probe-rt-3" ] }, { "productId": "fireflies", "storyId": "automation-rules-engine", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "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.", "evidenceIds": [ "fireflies-docs-21", "fireflies-docs-15", "fireflies-docs-25" ] }, { "productId": "fireflies", "storyId": "automation-scheduled-jobs", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fireflies-docs-15", "fireflies-docs-21", "fireflies-docs-16" ] }, { "productId": "fireflies", "storyId": "automation-versioned-workflows", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "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.", "evidenceIds": [] }, { "productId": "fireflies", "storyId": "bot-capture-major-platforms", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fireflies-docs-9", "fireflies-docs-13", "fireflies-docs-15", "fireflies-docs-21", "fireflies-comm-1" ] }, { "productId": "fireflies", "storyId": "botless-audio-capture", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "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.", "evidenceIds": [ "fireflies-docs-9", "fireflies-docs-4" ] }, { "productId": "fireflies", "storyId": "calendar-autojoin-rules", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "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.", "evidenceIds": [ "fireflies-docs-9", "fireflies-docs-13", "fireflies-docs-15", "fireflies-docs-21", "fireflies-docs-25" ] }, { "productId": "fireflies", "storyId": "chat-with-meeting-history", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fireflies-docs-18", "fireflies-docs-24", "fireflies-docs-8", "fireflies-docs-30", "fireflies-probe-rt-1" ] }, { "productId": "fireflies", "storyId": "clips-highlights-share", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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.", "evidenceIds": [] }, { "productId": "fireflies", "storyId": "consent-notification-features", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "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.", "evidenceIds": [ "fireflies-docs-9", "fireflies-docs-15", "fireflies-docs-21", "fireflies-docs-25" ] }, { "productId": "fireflies", "storyId": "crm-auto-sync", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "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.", "evidenceIds": [] }, { "productId": "fireflies", "storyId": "custom-templates-prompts", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fireflies-docs-10" ] }, { "productId": "fireflies", "storyId": "followup-email-draft", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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'.", "evidenceIds": [ "fireflies-docs-10", "fireflies-docs-18" ] }, { "productId": "fireflies", "storyId": "meeting-mcp-server", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "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.", "evidenceIds": [ "fireflies-docs-8", "fireflies-docs-24", "fireflies-docs-30", "fireflies-probe-3", "fireflies-probe-rt-1" ] }, { "productId": "fireflies", "storyId": "mobile-in-person-capture", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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.", "evidenceIds": [] }, { "productId": "fireflies", "storyId": "multilingual-meetings", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "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.", "evidenceIds": [ "fireflies-docs-11", "fireflies-docs-28" ] }, { "productId": "fireflies", "storyId": "no-training-on-my-data", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fireflies-docs-14", "fireflies-docs-15", "fireflies-docs-20", "fireflies-docs-21", "fireflies-docs-27" ] }, { "productId": "fireflies", "storyId": "openness-api-parity", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fireflies-docs-4", "fireflies-docs-5", "fireflies-docs-6", "fireflies-docs-14", "fireflies-docs-21", "fireflies-docs-18", "fireflies-probe-rt-3" ] }, { "productId": "fireflies", "storyId": "openness-full-export", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fireflies-docs-5", "fireflies-docs-6", "fireflies-docs-16", "fireflies-probe-rt-3" ] }, { "productId": "fireflies", "storyId": "openness-open-license", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Fireflies.ai is a closed SaaS meeting-transcription product; there is no source code to inspect, and 'open license source availability' is a category error for this product type, not a missing feature.", "evidenceIds": [] }, { "productId": "fireflies", "storyId": "openness-self-host", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Fireflies is a cloud SaaS meeting-transcription product with no self-hosted deployment offering; self-hosting the 'core product' is a category error for this type of hosted service, not an unmet capability.", "evidenceIds": [] }, { "productId": "fireflies", "storyId": "pre-meeting-context", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fireflies-docs-5", "fireflies-docs-29", "fireflies-docs-18" ] }, { "productId": "fireflies", "storyId": "privacy-data-residency", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fireflies-docs-20", "fireflies-docs-27" ] }, { "productId": "fireflies", "storyId": "privacy-no-training", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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.", "evidenceIds": [] }, { "productId": "fireflies", "storyId": "privacy-retention-controls", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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).", "evidenceIds": [] }, { "productId": "fireflies", "storyId": "privacy-telemetry-optout", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "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.", "evidenceIds": [] }, { "productId": "fireflies", "storyId": "retention-deletion-controls", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fireflies-docs-15", "fireflies-docs-20", "fireflies-docs-21", "fireflies-docs-25", "fireflies-docs-27" ] }, { "productId": "fireflies", "storyId": "search-across-meetings", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fireflies-docs-5", "fireflies-docs-6", "fireflies-docs-18", "fireflies-docs-24", "fireflies-docs-29", "fireflies-probe-rt-1" ] }, { "productId": "fireflies", "storyId": "sharing-permissions-controls", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fireflies-docs-15", "fireflies-docs-21", "fireflies-docs-25", "fireflies-docs-14", "fireflies-docs-27", "fireflies-docs-20" ] }, { "productId": "fireflies", "storyId": "slack-notion-zapier-push", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "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.", "evidenceIds": [] }, { "productId": "fireflies", "storyId": "speaker-identification", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "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.", "evidenceIds": [ "fireflies-docs-12" ] }, { "productId": "fireflies", "storyId": "structured-ai-summaries", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "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.", "evidenceIds": [ "fireflies-docs-10", "fireflies-docs-18", "fireflies-docs-9", "fireflies-docs-19" ] }, { "productId": "fireflies", "storyId": "transcription-quality-claims", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "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.", "evidenceIds": [ "fireflies-docs-9", "fireflies-docs-11", "fireflies-docs-12", "fireflies-docs-13", "fireflies-docs-28" ] }, { "productId": "fireflies", "storyId": "transcripts-via-api", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "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.", "evidenceIds": [ "fireflies-docs-2", "fireflies-docs-3", "fireflies-docs-5", "fireflies-docs-6", "fireflies-docs-16", "fireflies-docs-17", "fireflies-docs-22", "fireflies-probe-rt-3", "fireflies-docs-10" ] }, { "productId": "fireflies", "storyId": "transparent-pricing-free-tier", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "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.", "evidenceIds": [ "fireflies-docs-14", "fireflies-docs-18", "fireflies-docs-19", "fireflies-docs-20", "fireflies-docs-26", "fireflies-docs-28" ] }, { "productId": "granola", "storyId": "action-items-extraction", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Granola's docs describe general AI summaries, chat Q&A, and workflow actions (draft follow-up emails, Slack messages, calendar events) but never mention structured action-item extraction with assigned owners or a dedicated tracking view/list. Community evidence reinforces this gap: a PM explicitly built a separate third-party app to turn Granola meeting notes into a kanban to-do list because action items 'tend to slip through' natively.", "evidenceIds": [ "granola-docs-5", "granola-docs-20", "granola-docs-29", "granola-comm-7" ] }, { "productId": "granola", "storyId": "agent-files-action-items", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Granola offers a documented API/MCP server for programmatic access to meeting notes and a Zapier integration claiming 8,000+ app connections to 'automate what happens after a meeting,' which could route action items to Linear/Jira/Asana, and a native HubSpot sync exists as a precedent for native two-way automation. However, there is no documented native integration or pre-built automation specifically for Linear/Jira/Asana, and MCP/Chat tools shown (search notes, draft email/Slack, calendar events) are read/communication-focused rather than ticket-filing into project trackers. Missing for 10: a documented native Linear/Jira/Asana integration or explicit Zapier recipe/template for action-item ticket creation, and evidence of webhook-triggered ticket creation in these specific trackers.", "evidenceIds": [ "granola-docs-9", "granola-docs-16", "granola-docs-33", "granola-docs-17", "granola-probe-rt-1", "granola-docs-10", "granola-docs-29" ] }, { "productId": "granola", "storyId": "agentic-agent-docs", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "A live llms.txt is confirmed via direct HTTP probe (200 OK) at docs.granola.ai/llms.txt, and Granola also documents agent-oriented resources (API for custom agents, an official OAuth-protected MCP server verified live via runtime probe), giving agents multiple discoverable, machine-readable entry points into Granola's docs and data. Missing for 10: no independent/community confirmation of an agent actually consuming llms.txt successfully in practice.", "evidenceIds": [ "granola-probe-1", "granola-probe-3", "granola-probe-rt-1", "granola-docs-16", "granola-docs-34" ] }, { "productId": "granola", "storyId": "agentic-ai-insights", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Granola Chat lets users ask questions and get instant AI-generated insights, spot patterns across calls, and generate follow-up outputs directly inside the product, with Recipes providing reusable insight-generating prompt templates. This is native, first-party AI-native functionality well documented across multiple docs pages. Missing for 10: independent/hands-on validation of insight quality and accuracy beyond vendor docs.", "evidenceIds": [ "granola-docs-4", "granola-docs-5", "granola-docs-6", "granola-docs-19", "granola-docs-20", "granola-docs-29", "granola-docs-37" ] }, { "productId": "granola", "storyId": "agentic-autonomous-automation", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Granola supports automations that fire after meetings via Zapier (8,000+ app connections) and HubSpot auto-sync, and offers an API/MCP server for building custom 'agents' that analyze calls—these run without manual intervention once configured. However, there's no evidence of a native scheduler or persistent background agent loop inside Granola itself; the 'autonomy' comes from third-party automation platforms (Zapier/HubSpot) or requires the user to build their own agent via API/MCP rather than Granola running one natively. Missing for 10: native in-app automation/scheduling engine, evidence of continuously running background agents (not just event-triggered post-meeting syncs), and independent confirmation these automations run reliably unattended.", "evidenceIds": [ "granola-docs-9", "granola-docs-10", "granola-docs-39", "granola-docs-34", "granola-docs-16", "granola-probe-3", "granola-probe-rt-1" ] }, { "productId": "granola", "storyId": "agentic-builtin-assistant", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Granola ships a built-in 'Granola Chat' assistant that users can delegate post-meeting tasks to, e.g. drafting and sending follow-up emails/Slack messages and creating calendar events directly from meeting notes, plus reusable 'Recipes' prompt templates for repeated tasks. This is documented across multiple first-party doc pages describing concrete agentic actions triggered from chat.\nMissing for 10: independent/hands-on verification that these delegated actions (sending email, creating calendar events) actually execute reliably, and more detail on assistant autonomy/error-handling beyond vendor docs.", "evidenceIds": [ "granola-docs-4", "granola-docs-5", "granola-docs-19", "granola-docs-20", "granola-docs-29", "granola-docs-37", "granola-docs-6" ] }, { "productId": "granola", "storyId": "agentic-headless", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Granola exposes a REST API and an MCP server for programmatic access to meeting notes/transcripts, which could be scripted into automated pipelines, but the core product is a desktop app that captures live meeting audio and there is no documented CLI, headless mode, or CI-specific workflow. Missing for 10: explicit headless/CI execution mode, CLI tooling, and any example of running Granola non-interactively in an automation pipeline.", "evidenceIds": [ "granola-docs-1", "granola-docs-16", "granola-docs-33", "granola-probe-3", "granola-probe-rt-1" ] }, { "productId": "granola", "storyId": "agentic-mcp-client", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "All evidence describes Granola exposing its own MCP server (and API) so other AI tools can pull Granola's meeting data — the reverse of the story, which asks whether Granola itself can consume external MCP servers as a client to gain new tools. No evidence shows Granola's Chat or any other feature accepting/plugging in third-party MCP servers.", "evidenceIds": [ "granola-docs-3", "granola-docs-17", "granola-docs-35", "granola-probe-3", "granola-probe-rt-1" ] }, { "productId": "granola", "storyId": "agentic-mcp-server", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Granola documents an official MCP server ('Granola MCP') for connecting AI tools/agents to meeting notes (search, list_meetings, get_meeting_transcript, query_granola_meetings), and a runtime probe confirms the hosted endpoint https://mcp.granola.ai/mcp is live and correctly speaks MCP's OAuth-protected resource flow. Missing for 10: independent/community hands-on confirmation of a successful agent connection beyond the vendor docs and probe.", "evidenceIds": [ "granola-docs-3", "granola-docs-17", "granola-docs-35", "granola-probe-3", "granola-probe-rt-1" ] }, { "productId": "granola", "storyId": "agentic-nl-commands", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Granola Chat lets users interact via natural-language queries to recall meeting details, spot patterns, and trigger actions like drafting/sending a follow-up email, drafting a Slack message, or creating a calendar event—clear NL-command operation within the product. missing for 10: independent/hands-on corroboration of chat-driven command execution, and detail on reliability/limits of the NL command surface beyond first-party docs.", "evidenceIds": [ "granola-docs-4", "granola-docs-5", "granola-docs-19", "granola-docs-20", "granola-docs-29", "granola-docs-37" ] }, { "productId": "granola", "storyId": "agentic-official-cli", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Evidence covers an API, MCP server, and integrations (Zapier, HubSpot), but there is no mention of an official CLI tool for AI-native workflows anywhere in the docs, community, or probes.", "evidenceIds": [] }, { "productId": "granola", "storyId": "agentic-public-api", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Granola documents a RESTful public API for programmatic access to meeting notes, transcripts, and summaries, including workspace-level API keys for admins, and a live official MCP server (confirmed via runtime probe) that supports OAuth-based agent access to meeting data. This is solid documented evidence of API-driven, agentic use of the product beyond the base app UI. Missing for 10: a formal OpenAPI/reference spec (probe found 404s for openapi.json/swagger.json) and independent third-party developer reports validating real-world API integration.", "evidenceIds": [ "granola-docs-33", "granola-docs-28", "granola-docs-34", "granola-probe-3", "granola-probe-rt-1", "granola-probe-2" ] }, { "productId": "granola", "storyId": "agentic-scoped-keys", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Granola documents API keys (personal and workspace-level) and an OAuth-based MCP server, but there is no evidence of scoped or least-privilege credential issuance — e.g., no read-only vs write scopes, no per-agent permission granularity, and workspace keys are described as broad and non-expiring rather than restrictable.", "evidenceIds": [ "granola-docs-28", "granola-probe-rt-1", "granola-probe-3" ] }, { "productId": "granola", "storyId": "agentic-sdks", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Granola exposes a documented RESTful API and an official hosted MCP server (confirmed live via runtime probe with OAuth), which lets AI-native users build custom agents/integrations, but there is no evidence of official language SDKs, client libraries, or a discoverable OpenAPI/swagger spec (probe found only 404s). Missing for 10: published SDKs in common languages, an OpenAPI spec, and independent developer corroboration of building against the API.", "evidenceIds": [ "granola-docs-16", "granola-docs-33", "granola-docs-34", "granola-docs-3", "granola-probe-3", "granola-probe-rt-1", "granola-probe-2" ] }, { "productId": "granola", "storyId": "agentic-webhooks", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence covers a REST API, MCP server, Zapier/HubSpot integrations, and chat workflows, but nothing in the pack describes any webhook subscription mechanism for event notifications. Zapier could theoretically enable trigger-based automation, but no documentation confirms Granola exposes outbound webhooks for developers to subscribe to events directly. missing for 10: documented webhook endpoints, event types, subscription/registration mechanism, payload schema.", "evidenceIds": [ "granola-docs-16", "granola-docs-9", "granola-probe-2" ] }, { "productId": "granola", "storyId": "api-interactive-docs", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "There's a mention of a RESTful API and MCP server, but no evidence of an interactive API reference with runnable examples; probes explicitly show no OpenAPI/swagger spec is exposed (all candidate paths 404), and no docs mention interactive playgrounds or code samples runnable in-browser.", "evidenceIds": [ "granola-probe-2", "granola-docs-33", "granola-docs-16" ] }, { "productId": "granola", "storyId": "api-machine-spec", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Granola documents a REST API and MCP integration but explicit probes show no OpenAPI/Swagger spec is published at any standard location (all candidate paths returned 404), and no machine-readable API spec is referenced anywhere in the docs.", "evidenceIds": [ "granola-probe-2", "granola-docs-33" ] }, { "productId": "granola", "storyId": "api-sandbox", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Granola is a meeting-notes/AI-notetaker product, not a developer platform with a sandbox/test-mode environment concept; there is no notion of 'production data' vs sandbox data to test against. This story is a category error for this product type.", "evidenceIds": [] }, { "productId": "granola", "storyId": "api-versioning-policy", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence shows a Granola REST API and MCP server exist, but there is no documentation of API versioning scheme or a deprecation policy; an openapi.json probe returned 404s, suggesting no formal API spec/versioning surface is published. missing for 10: versioning scheme documentation, deprecation policy/notice process, changelog or migration guides.", "evidenceIds": [ "granola-docs-33", "granola-probe-2", "granola-docs-28" ] }, { "productId": "granola", "storyId": "automation-bulk-operations", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Granola offers bulk *export* of all notes to CSV and API/MCP access that can read across the whole workspace (search, list_meetings), which supports bulk analysis, but there's no documented capability for bulk mutating operations (e.g., batch delete, batch re-tag, batch share) across many items at once. missing for 10: explicit bulk write/update operations, batch API endpoints for multi-item actions, evidence of an agent actually performing such an operation.", "evidenceIds": [ "granola-docs-22", "granola-docs-30", "granola-docs-33", "granola-probe-3", "granola-probe-rt-1" ] }, { "productId": "granola", "storyId": "automation-rules-engine", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "Granola supports event-triggered automation only via third-party integrations: Zapier (8,000+ apps, 'automate what happens after a meeting') and HubSpot folder-based auto-sync ('automatically save any notes added to Granola folders to relevant contacts/deals'). These act as rule-like triggers but are not a native in-product rules/automation engine, and Chat 'workflows' are manually invoked rather than event-triggered. Missing for 10: a native rules/automation builder within Granola itself, documentation of custom trigger-condition-action definitions, and evidence of broader event types beyond folder-add/meeting-end.", "evidenceIds": [ "granola-docs-9", "granola-docs-39", "granola-docs-18", "granola-docs-20" ] }, { "productId": "granola", "storyId": "automation-scheduled-jobs", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows Granola offers APIs, MCP, Zapier/HubSpot integrations, and one-off Chat workflows (draft emails, Slack messages, calendar events), but nothing describes scheduling recurring jobs or automated workflows to run on a cadence within Granola itself — recurring automation would rely entirely on third-party tools like Zapier, not a native Granola feature.", "evidenceIds": [ "granola-docs-9", "granola-docs-20", "granola-docs-29", "granola-docs-16", "granola-docs-34" ] }, { "productId": "granola", "storyId": "automation-versioned-workflows", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Granola is a meeting-notes/transcription tool with recipes/templates and chat workflows, but it has no concept of 'automations' with version history, review, or rollback — this is a category error, not a missing feature of this product type.", "evidenceIds": [] }, { "productId": "granola", "storyId": "bot-capture-major-platforms", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Granola explicitly claims to work with Zoom, Google Meet, Teams and other apps, and records via computer audio rather than a bot joining the call, directly addressing the 'recording where I want it' preference. Community evidence corroborates real-world reliability (battery/performance) and PM usage, though no independent side-by-side accuracy test across all three platforms is present. Missing for 10: independent verification of capture reliability across each specific platform (Zoom/Meet/Teams) and no mention of optional bot-based recording for cases where computer-audio capture isn't desired.", "evidenceIds": [ "granola-docs-24", "granola-docs-31", "granola-comm-5", "granola-comm-7" ] }, { "productId": "granola", "storyId": "botless-audio-capture", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "Granola's core value prop is capturing device/computer audio directly without a bot joining the call, explicitly stated as 'Uses your computer audio, so doesn't invite a bot' and works across Zoom/Meet/Teams/etc, with transparency messaging posted in chat rather than a visible bot presence. Community evidence corroborates it runs quietly in the background on the user's device. Missing for 10: independent hands-on confirmation from a founder-specific use case and no explicit contradicting report of a visible bot ever appearing.", "evidenceIds": [ "granola-docs-31", "granola-docs-24", "granola-docs-25", "granola-comm-1" ] }, { "productId": "granola", "storyId": "calendar-autojoin-rules", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows Granola connects to a calendar to display upcoming meetings and offers templates per call type for note formatting, but there is no mention of per-meeting-type rules controlling which meetings get automatically captured/recorded — no filtering, auto-join rules, or selective-capture settings are documented.", "evidenceIds": [ "granola-docs-32", "granola-docs-7", "granola-docs-21" ] }, { "productId": "granola", "storyId": "chat-with-meeting-history", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Granola Chat explicitly lets users ask natural-language questions across meeting notes/transcripts and get insights, with a magnifying-glass feature to trace an answer back to its source location in the transcript/notes, and the MCP/API integrations further support searching past meetings and surfacing sourced context. missing for 10: independent/hands-on validation of answer accuracy and citation quality, and explicit confirmation that native Chat (not just MCP) searches the *entire* historical corpus rather than per-meeting.", "evidenceIds": [ "granola-docs-19", "granola-docs-4", "granola-docs-27", "granola-docs-35", "granola-probe-rt-1" ] }, { "productId": "granola", "storyId": "clips-highlights-share", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Granola's sharing features (copy note link, CSV export, folder sync to CRM) all share the full note/transcript, not a trimmed audio/video soundbite or highlight clip; no evidence anywhere in the docs pack of a clip-cutting or highlight-extraction feature. Missing for 10: any mention of clip/soundbite creation, timestamp-based excerpting, or audio/video snippet sharing.", "evidenceIds": [ "granola-docs-13", "granola-docs-23", "granola-docs-8", "granola-docs-38" ] }, { "productId": "granola", "storyId": "consent-notification-features", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Granola documents concrete in-meeting disclosure (a chat message announcing transcription start) and consent-adjacent controls like opting out of model training and auto-deleting transcripts, going beyond a mere policy PDF. However, there is no evidence of admin-enforced transparency settings (e.g., workspace-wide consent policy enforcement, participant opt-out controls, or audit of consent compliance) that would let an IT admin mandate or verify these behaviors across the org. Missing for 10: admin-level enforcement/configuration of consent notifications, participant-side consent management, and any audit trail for consent compliance.", "evidenceIds": [ "granola-docs-25", "granola-docs-26", "granola-docs-12", "granola-docs-40", "granola-docs-13" ] }, { "productId": "granola", "storyId": "crm-auto-sync", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Granola has a documented native HubSpot integration that auto-syncs meeting notes to the correct contacts, companies, and deals via folders (granola-docs-10, granola-docs-39), which directly matches the story for HubSpot. However, there is no dedicated Salesforce or Attio integration documented — those CRMs would only be reachable indirectly via the generic Zapier connector (granola-docs-9), not a first-party record-matching sync. Missing for 10: explicit native Salesforce and Attio CRM sync with contact/deal matching, and independent/hands-on confirmation that the HubSpot sync reliably attaches to the 'right' record.", "evidenceIds": [ "granola-docs-10", "granola-docs-18", "granola-docs-39", "granola-docs-9" ] }, { "productId": "granola", "storyId": "custom-templates-prompts", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Granola explicitly supports custom/default templates per call type (1:1s, interviews, sales pitches) and 'Recipes' as reusable prompt templates to avoid retyping the same questions, directly matching the story's need for per-meeting-type customization. Missing for 10: independent/hands-on user corroboration of template customization quality and confirmation that saved 'recipes' can be tied to specific meeting types automatically.", "evidenceIds": [ "granola-docs-7", "granola-docs-21", "granola-docs-36", "granola-docs-6" ] }, { "productId": "granola", "storyId": "followup-email-draft", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Granola Chat explicitly supports drafting and sending a follow-up email directly from meeting notes as a documented workflow, with sales-relevant templates (e.g., sales pitch note templates) and CRM sync options for follow-through. Missing for 10: no independent/hands-on review confirming the 'couple of clicks' review-and-send UX in practice, and no detail on how much editing/review is typically needed before sending.", "evidenceIds": [ "granola-docs-5", "granola-docs-20", "granola-docs-29", "granola-docs-37", "granola-docs-21" ] }, { "productId": "granola", "storyId": "meeting-mcp-server", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "Granola documents an official hosted MCP server (mcp.granola.ai) supporting search, transcripts, and meeting queries, and a runtime probe confirms the endpoint is live and enforces OAuth via the standard MCP protected-resource flow (401 + WWW-Authenticate pointing to oauth-protected-resource metadata), matching the story's OAuth/no-glue-code requirement. Missing for 10: independent third-party (non-vendor) hands-on confirmation of a successful end-to-end OAuth connection and action-item retrieval.", "evidenceIds": [ "granola-docs-3", "granola-docs-17", "granola-docs-35", "granola-probe-3", "granola-probe-rt-1" ] }, { "productId": "granola", "storyId": "mobile-in-person-capture", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Granola's docs confirm a mobile app for recording AI-enhanced notes during in-person meetings and iOS calls, and separate docs confirm workspace-wide search/chat over meeting notes, but no evidence explicitly ties mobile-captured notes into the same searchable workspace pipeline. missing for 10: explicit confirmation that mobile-recorded notes/transcripts sync into the same workspace and are searchable via Chat/API alongside desktop notes, and any hands-on user report validating this integration.", "evidenceIds": [ "granola-docs-15", "granola-docs-19", "granola-docs-27", "granola-docs-32" ] }, { "productId": "granola", "storyId": "multilingual-meetings", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Docs explicitly state Granola supports multiple languages for both transcription and generated summaries (granola-docs-11), directly confirming the core claim. However, there is no detail on which languages are supported, no mention of handling mid-meeting language switching, and no independent/hands-on corroboration of multilingual accuracy. missing for 10: list of supported languages, evidence of accurate language-switching handling, independent verification of non-English transcription quality.", "evidenceIds": [ "granola-docs-11" ] }, { "productId": "granola", "storyId": "no-training-on-my-data", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "Granola's docs confirm an opt-out setting for model training (granola-docs-26) and note transparency/consent features like auto-deletion of transcripts and start-of-recording notifications (granola-docs-12, granola-docs-25), but there is no evidence in the pack of SOC 2 or HIPAA compliance documentation, a formal enterprise DPA, or admin-enforced (org-wide) opt-out controls as opposed to per-user settings. Missing for 10: SOC 2/HIPAA certification pages, org-level enforceable opt-out (vs individual toggle), and any compliance/trust-center documentation.", "evidenceIds": [ "granola-docs-26", "granola-docs-12", "granola-docs-25" ] }, { "productId": "granola", "storyId": "openness-api-parity", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "The Granola API and MCP server give programmatic read access to meeting notes, transcripts, and summaries, and support building custom agents (granola-docs-1/16/34/35, granola-probe-rt-1 confirms live OAuth MCP endpoint), but there's no documented API endpoint for the many interactive UI capabilities like Chat workflows (draft/send email, Slack, calendar events), Recipes/templates, folder-based CRM sync, or transcript auto-deletion settings — these remain UI-only or handled via separate third-party integrations (Zapier/HubSpot). No OpenAPI spec was found (granola-probe-2 shows 404s), suggesting a narrow, undocumented surface rather than full UI parity. Missing for 10: API endpoints for chat-driven actions, template/recipe management via API, and any documented parity for sharing/export settings.", "evidenceIds": [ "granola-docs-1", "granola-docs-16", "granola-docs-34", "granola-docs-35", "granola-probe-rt-1", "granola-probe-2", "granola-docs-29", "granola-docs-6" ] }, { "productId": "granola", "storyId": "openness-full-export", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Granola documents a CSV export of meeting notes (titles, summaries, transcripts) via Settings, plus API/MCP access to notes data, giving a real open-format export path, but this covers only notes/transcripts, not a full account/data export (templates, folders, integration settings, chat history) that would let a user fully leave with everything. Community commentary also frames export as a manual workaround ('copy-paste note summaries out to Obsidian') rather than a first-class 'export everything' feature. Missing for 10: comprehensive full-account export beyond notes/transcripts, and any independent confirmation that exported CSV/API data is truly complete and portable.", "evidenceIds": [ "granola-docs-8", "granola-docs-22", "granola-docs-30", "granola-docs-38", "granola-docs-16", "granola-comm-4" ] }, { "productId": "granola", "storyId": "openness-open-license", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Granola is closed-source proprietary software; no evidence pack item mentions open-sourcing the app or any open license for its source code — all evidence covers APIs, integrations, and app features, not source availability.", "evidenceIds": [] }, { "productId": "granola", "storyId": "openness-self-host", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Granola is a closed SaaS/desktop app (with local .md-only community workaround noted, not official self-hosting); no evidence of an open-source core, self-hosted server option, or on-prem deployment mode is provided anywhere in the docs or community notes.", "evidenceIds": [] }, { "productId": "granola", "storyId": "pre-meeting-context", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "Granola stores meeting notes/transcripts and lets users search or chat with past notes (via Chat or MCP's 'search through your meeting notes, find specific topics discussed in past meetings'), and it connects to your calendar to show upcoming meetings, which together could support manual meeting prep. However, there is no evidence of an automatic pre-call brief or a feature that proactively surfaces past meetings with the same attendees before a call starts — the burden is on the user to search/chat manually. Missing for 10: automatic surfacing of past meetings by attendee tied to calendar events, a dedicated pre-meeting briefing/open-threads summary feature, and any first-hand account of this proactive workflow.", "evidenceIds": [ "granola-docs-32", "granola-docs-19", "granola-docs-35", "granola-docs-4" ] }, { "productId": "granola", "storyId": "privacy-data-residency", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence anywhere in the docs or community mentions data residency, regional storage options, or geographic control over where meeting notes/transcripts are stored; only auto-deletion and opt-out-of-training controls are documented, which is a different privacy axis.", "evidenceIds": [ "granola-docs-12", "granola-docs-26", "granola-docs-40" ] }, { "productId": "granola", "storyId": "privacy-no-training", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Granola docs explicitly state users can opt out of model training via Settings, directly delivering the story's core requirement. Missing for 10: independent/hands-on confirmation that opt-out actually stops training, and details on scope (e.g., whether opted-out data is retroactively excluded).", "evidenceIds": [ "granola-docs-26" ] }, { "productId": "granola", "storyId": "privacy-retention-controls", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Docs confirm concrete retention controls: automatic transcript deletion after a set period (transcripts only, notes unaffected) and an opt-out of model training in Settings, giving users some control over data handling. However, there's no evidence of full note/data deletion, account-level data purge, or granular retention policies beyond transcripts. Missing for 10: full note/data deletion controls, account-wide data export-then-delete workflow, and documented retention periods/config options beyond transcripts.", "evidenceIds": [ "granola-docs-12", "granola-docs-40", "granola-docs-26" ] }, { "productId": "granola", "storyId": "privacy-telemetry-optout", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Granola offers an explicit opt-out of model training in Settings, which is a direct telemetry/data-usage control, but there is no evidence of a broader opt-out for general product usage/analytics telemetry beyond this single toggle. missing for 10: documentation of a general analytics/telemetry opt-out (not just model-training), independent confirmation the opt-out is honored, and any UI/settings detail beyond the one-line mention.", "evidenceIds": [ "granola-docs-26" ] }, { "productId": "granola", "storyId": "retention-deletion-controls", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Docs confirm Granola supports automatic deletion of transcripts after a set period (a scheduled retention policy), but this is framed as a general privacy setting, not clearly an IT-admin-controlled workspace policy, and notes/recordings are explicitly excluded ('your notes are not affected'). There is no evidence of an on-demand 'permanently erase all data' admin action or coverage of audio recordings specifically. Missing for 10: admin-level retention policy management console, recordings deletion (not just transcripts), and an on-demand permanent erase/purge capability.", "evidenceIds": [ "granola-docs-12", "granola-docs-40" ] }, { "productId": "granola", "storyId": "search-across-meetings", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Granola Chat lets users ask questions and get insights across notes/transcripts (docs-19, docs-4), the MCP server explicitly supports searching through meeting notes and finding topics across past meetings plus retrieving full transcripts (docs-35, granola-probe-rt-1), and the in-app magnifying-glass feature jumps to the exact transcript/note location a note came from (docs-27). Missing for 10: independent/hands-on evidence confirming true cross-meeting semantic search quality (vs. single-note context) and no explicit documentation of a dedicated 'search all meetings' UI beyond Chat/MCP.", "evidenceIds": [ "granola-docs-19", "granola-docs-35", "granola-docs-27", "granola-probe-rt-1", "granola-docs-4" ] }, { "productId": "granola", "storyId": "sharing-permissions-controls", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Docs confirm private-by-default notes (not shared unless you share a link or add to a team folder) and simple link/folder sharing controls, plus workspace-level API keys for admins, but there is no evidence of granular per-link or per-folder permission settings, workspace-wide sharing policy controls, or an admin dashboard/audit view into what has been shared. Missing for 10: granular link/folder/workspace permission settings, admin visibility/audit log of shared notes, org-wide sharing policy controls.", "evidenceIds": [ "granola-docs-13", "granola-docs-23", "granola-docs-39", "granola-docs-28" ] }, { "productId": "granola", "storyId": "slack-notion-zapier-push", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Granola explicitly documents Zapier integration to 8,000+ apps, native HubSpot CRM sync, and Chat workflows that draft/send Slack messages and follow-up emails, directly matching the story's 'flows into Slack, Notion, and thousands of apps' vision. Notion isn't named directly, but it would be covered under the 8,000+ app Zapier ecosystem; missing for 10: an explicit first-party Notion integration/doc and independent user confirmation that Slack/Notion syncing works reliably in practice.", "evidenceIds": [ "granola-docs-9", "granola-docs-10", "granola-docs-18", "granola-docs-20", "granola-docs-29", "granola-docs-39" ] }, { "productId": "granola", "storyId": "speaker-identification", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Granola's docs confirm a 'Speaker tags' feature that labels transcript segments with participant names rather than generic 'Speaker 1/2' or 'Me/Them' labels, indicating some diarization+name-matching capability. However, there's no detail on how names are resolved (calendar matching, manual tagging, or true voice diarization) and no independent/community evidence validating accuracy of this attribution in multi-speaker calls. Missing for 10: technical explanation of the diarization method, accuracy benchmarks, and hands-on/independent verification of correct name attribution across speakers.", "evidenceIds": [ "granola-docs-14" ] }, { "productId": "granola", "storyId": "structured-ai-summaries", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Granola's core AI-enhanced notes produce structured summaries with templates for different meeting types (1:1s, interviews, sales pitches), speaker attribution, and searchable source-linked notes, which are shareable via link or CSV export without further editing. missing for 10: independent hands-on evaluation of summary quality/accuracy (e.g., a reviewer confirming it required no edits), and no direct evidence addressing 'decisions' and 'next steps' as distinct structured fields versus a general summary format.", "evidenceIds": [ "granola-docs-7", "granola-docs-21", "granola-docs-36", "granola-docs-14", "granola-docs-27", "granola-docs-23", "granola-docs-8" ] }, { "productId": "granola", "storyId": "transcription-quality-claims", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack documents feature-level transcription capabilities (multi-language support, speaker tags, auto-deletion, export) but contains no documentation of the underlying transcription model, accuracy benchmarks, or explicit known limitations (e.g., accent/noise handling, word-error-rate). Community comments raise trust/skepticism but do not confirm or deny transcription documentation quality.", "evidenceIds": [ "granola-docs-11", "granola-docs-14", "granola-docs-24" ] }, { "productId": "granola", "storyId": "transcripts-via-api", "verdict": "partial", "quality": 7, "confidence": "medium", "rationale": "Granola docs confirm a documented REST API for programmatic access to meeting notes, transcripts, and AI summaries (granola-docs-1,16,33,34), and reference both individual and workspace-level API keys, implying self-serve key generation (granola-docs-28). However, action items are not explicitly called out as a retrievable field, and a probe found no live OpenAPI/swagger spec, suggesting the API reference may be thin or beta (granola-probe-2). missing for 10: explicit documentation of action-item extraction, a public OpenAPI/schema reference, and independent developer corroboration of successful API key self-service and querying.", "evidenceIds": [ "granola-docs-1", "granola-docs-16", "granola-docs-33", "granola-docs-34", "granola-docs-28", "granola-probe-2" ] }, { "productId": "granola", "storyId": "transparent-pricing-free-tier", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence pack content addresses Granola's pricing tiers, free plan limits, or paid plan costs/features; only community comments vaguely mention 'free for a limited number of notes' without detail on tier costs or sales-contact requirements. missing for 10: pricing page details, tier breakdown, cost transparency documentation, confirmation of no 'talk to sales' wall.", "evidenceIds": [ "granola-comm-4" ] }, { "productId": "otter", "storyId": "action-items-extraction", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Otter automatically extracts action items with assigned owners from meetings (otter-docs-3, otter-docs-21, otter-docs-30) and collects them in a trackable, searchable workspace, with the ability to sync/push them to task tools like JIRA, Asana, ClickUp, and CRMs for centralized tracking (otter-docs-10, otter-docs-31, otter-docs-4). This is corroborated by an enterprise blog post and integrations page confirming live functionality, plus a working MCP server for querying meeting action items. Missing for 10: independent hands-on verification specifically of action-item/owner extraction accuracy (community evidence focuses on privacy/security concerns rather than confirming or disputing action-item quality).", "evidenceIds": [ "otter-docs-3", "otter-docs-21", "otter-docs-30", "otter-docs-10", "otter-docs-31", "otter-docs-4", "otter-docs-37", "otter-probe-rt-1" ] }, { "productId": "otter", "storyId": "agent-files-action-items", "verdict": "partial", "quality": 7, "confidence": "medium", "rationale": "Otter explicitly documents sending action items into JIRA and Asana (and other tools) plus a public API/webhooks tier and a live, OAuth-gated MCP server enabling AI agents to pull meeting/action-item data into workflows. However, Linear is never named, no OpenAPI/API spec is discoverable (404s on all probed paths), and API/MCP/native project-tracker automations appear gated to Enterprise plans with no independent hands-on confirmation that action items sync correctly end-to-end. Missing for 10: explicit Linear support, publicly discoverable API schema, and independent verification of the automation actually filing items correctly.", "evidenceIds": [ "otter-docs-10", "otter-docs-26", "otter-docs-31", "otter-docs-40", "otter-docs-46", "otter-probe-rt-1", "otter-probe-1" ] }, { "productId": "otter", "storyId": "agentic-agent-docs", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of an llms.txt file or agent-oriented documentation format for Otter.ai; the evidence pack covers MCP server integration and product features but nothing about machine-readable docs for agents to consume directly.", "evidenceIds": [] }, { "productId": "otter", "storyId": "agentic-ai-insights", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Otter's AI Chat and meeting summaries generate insights, decisions, action items, sentiment, and follow-ups directly from meeting data (otter-docs-1,3,21,37,34,13), and this is corroborated by a live, OAuth-gated MCP endpoint confirmed via runtime probe (otter-probe-rt-1). missing for 10: independent hands-on validation of insight quality/accuracy (community evidence focuses on privacy/recording concerns, not insight usefulness), and MCP/insight features are Enterprise-gated rather than universally available.", "evidenceIds": [ "otter-docs-1", "otter-docs-3", "otter-docs-21", "otter-docs-37", "otter-docs-34", "otter-docs-13", "otter-docs-46", "otter-probe-rt-1", "otter-probe-2" ] }, { "productId": "otter", "storyId": "agentic-autonomous-automation", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Otter supports background automation scoped to meetings: scheduled auto-join notetakers, automatic transcription/summarization, auto-extraction of action items, and automatic syncing of notes/action items to CRMs, Jira, Asana, Zendesk, Airtable, S3, etc. (otter-docs-17,9,10,28,29,31,4,3,26,40). This is real autonomous background behavior but it is templated around meeting workflows rather than a general-purpose automation/agent builder where a user defines arbitrary triggers/conditions. Missing for 10: evidence of a flexible, user-configurable automation/workflow engine (beyond Zapier/webhooks) and independent confirmation that these automations reliably run unattended without manual re-triggering.", "evidenceIds": [ "otter-docs-17", "otter-docs-9", "otter-docs-10", "otter-docs-28", "otter-docs-29", "otter-docs-31", "otter-docs-4", "otter-docs-3", "otter-docs-26", "otter-docs-40" ] }, { "productId": "otter", "storyId": "agentic-builtin-assistant", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Otter ships a built-in 'Otter AI Chat' assistant that can search meetings, answer questions, draft follow-ups/reports, and auto-extract action items/summaries, which is genuine in-product task delegation (otter-docs-1,3,21,41). However this delegation is scoped narrowly to meeting-related tasks (not general-purpose), and there's no independent/hands-on evidence validating the AI Chat's actual task-completion quality — community evidence only covers transcription accuracy and privacy issues, not the assistant's agentic performance. Missing for 10: independent hands-on validation of Otter AI Chat's task delegation, broader (non-meeting) task scope, and confirmation the chat assistant reliably executes multi-step actions vs. just answering queries.", "evidenceIds": [ "otter-docs-1", "otter-docs-3", "otter-docs-21", "otter-docs-41", "otter-docs-30" ] }, { "productId": "otter", "storyId": "agentic-headless", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "Otter offers a Public API, Webhooks, and an MCP server that could be scripted/integrated into automated pipelines (otter-docs-26, otter-docs-40, otter-probe-rt-1), but these are gated to Enterprise workspaces and there's no documentation of a CLI, SDK, or explicit CI/headless workflow support — the API/MCP surface is aimed at chat-tool integration rather than programmatic batch automation. Missing for 10: documented CLI or SDK for scripted/CI use, explicit CI/automation guides, evidence of non-Enterprise API access, and confirmation the API supports full headless operation (uploading, processing, retrieving) without interactive UI.", "evidenceIds": [ "otter-docs-26", "otter-docs-40", "otter-docs-48", "otter-probe-rt-1", "otter-probe-1" ] }, { "productId": "otter", "storyId": "agentic-mcp-client", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "All evidence describes Otter shipping its own MCP *server* so external AI tools (Claude, ChatGPT) can pull Otter's meeting data — this is the reverse of the story, which asks whether a user can plug external MCP servers into Otter so Otter itself can consume their tools. No evidence shows Otter acting as an MCP client consuming third-party MCP servers.", "evidenceIds": [ "otter-docs-6", "otter-docs-16", "otter-docs-46", "otter-probe-2", "otter-probe-rt-1" ] }, { "productId": "otter", "storyId": "agentic-mcp-server", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Otter documents and ships an official hosted MCP server (mcp.otter.ai) that connects Claude, ChatGPT, and other AI agents to meeting data, with OAuth-based granular permissions, confirmed live via a runtime probe returning a valid OAuth-protected-resource challenge rather than a dead endpoint. Missing for 10: independent third-party (non-vendor) hands-on confirmation of successful agent connection/tool use beyond the auth handshake, and the capability is restricted to Enterprise workspaces rather than universally available.", "evidenceIds": [ "otter-docs-6", "otter-docs-16", "otter-docs-46", "otter-docs-47", "otter-docs-35", "otter-probe-2", "otter-probe-rt-1" ] }, { "productId": "otter", "storyId": "agentic-nl-commands", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Otter AI Chat lets users query meetings, CRMs, and connected apps using natural language to get answers, drafts, and reports (otter-docs-1, otter-docs-11), and this NL interface also works through MCP-connected assistants like Claude/ChatGPT (otter-docs-16, otter-docs-46), confirmed live by a runtime probe. However, evidence is limited to search/chat-style querying rather than broader NL-driven control of the product (e.g., scheduling, settings, workflow actions), and there is no independent hands-on report validating chat accuracy or command breadth. Missing for 10: independent verification of NL Chat's reliability/accuracy, evidence of NL controlling actions beyond querying/summarizing (e.g., configuring integrations, managing recordings via command), and broader command scope beyond meeting Q&A.", "evidenceIds": [ "otter-docs-1", "otter-docs-11", "otter-docs-16", "otter-docs-46", "otter-probe-rt-1" ] }, { "productId": "otter", "storyId": "agentic-official-cli", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Otter.ai is a meeting-transcription SaaS product, not a developer tool or platform where a CLI is a natural fit; the evidence pack covers API/MCP/integrations but no CLI is mentioned or implied, and CLI usage is not a fair expectation for this product category.", "evidenceIds": [] }, { "productId": "otter", "storyId": "agentic-public-api", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Otter references a 'Public API' and 'API & Webhooks' as an Enterprise/paid-tier feature (otter-docs-26, otter-docs-40, otter-docs-48), implying programmatic access exists, but no actual API reference, schema, or endpoint documentation is shown, and a live probe found no discoverable OpenAPI/swagger spec (otter-probe-1). The MCP server is real and OAuth-gated (otter-probe-rt-1) but that's a different (agent-tool) interface, not a general-purpose documented public API for driving the product programmatically. missing for 10: published API reference/docs with endpoints and schemas, independent confirmation of working API calls, clarity on which tiers can access it.", "evidenceIds": [ "otter-docs-26", "otter-docs-40", "otter-docs-48", "otter-probe-1", "otter-probe-rt-1" ] }, { "productId": "otter", "storyId": "agentic-scoped-keys", "verdict": "partial", "quality": 7, "confidence": "medium", "rationale": "Otter's MCP server is OAuth-authenticated with granular permissions and explicit meeting-level authorization ('AI assistant can only access meetings you explicitly authorize'), and a runtime probe confirms the endpoint is live and OAuth-gated rather than just a marketing claim. However, this capability is restricted to Enterprise workspaces, and there's no independent evidence of fine-grained scope customization (e.g., read-only vs write, specific resource scoping) beyond vendor description. Missing for 10: independent/hands-on verification of granular scope options, evidence of least-privilege scoping beyond meeting-level authorization, and availability outside Enterprise tier.", "evidenceIds": [ "otter-docs-35", "otter-docs-47", "otter-docs-46", "otter-probe-rt-1", "otter-docs-26" ] }, { "productId": "otter", "storyId": "agentic-sdks", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "Otter documents a Public API, webhooks, and a live, OAuth-gated MCP server (confirmed by runtime probe) that let developers integrate meeting data into custom workflows, which supports 'building against Otter programmatically,' but no evidence names an official SDK (Python/JS/etc.) or provides SDK-style client libraries — only raw API/webhook/MCP endpoints are documented. missing for 10: explicit official SDK documentation/libraries, code samples, language coverage, independent developer corroboration of SDK usage.", "evidenceIds": [ "otter-docs-26", "otter-docs-40", "otter-docs-46", "otter-docs-47", "otter-probe-2", "otter-probe-rt-1", "otter-probe-1" ] }, { "productId": "otter", "storyId": "agentic-webhooks", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Otter's pricing page explicitly lists 'Otter API & Webhooks' as a feature on paid plans, confirming webhook subscription capability exists, but there is no documentation describing webhook event types, payload schemas, subscription setup, or independent confirmation of usage. missing for 10: webhook event catalog/documentation, setup/configuration guide, and hands-on or independent verification of webhook delivery.", "evidenceIds": [ "otter-docs-26" ] }, { "productId": "otter", "storyId": "api-interactive-docs", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Otter has a Public API/webhooks and MCP server, so an interactive API reference is a fair ask, but the evidence pack shows no interactive docs or runnable examples — a direct probe for OpenAPI/Swagger specs returned 404s and no docs page with a live API explorer is cited.", "evidenceIds": [ "otter-probe-1", "otter-docs-26", "otter-docs-40" ] }, { "productId": "otter", "storyId": "api-machine-spec", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Otter advertises a 'Public API' and webhooks (otter-docs-26, otter-docs-40, otter-docs-48), but a direct probe for machine-readable spec files (openapi.json, swagger.json, etc.) returned 404 on all candidate paths, and no documentation link to an OpenAPI/Swagger spec appears anywhere in the evidence pack.", "evidenceIds": [ "otter-probe-1", "otter-docs-26", "otter-docs-40" ] }, { "productId": "otter", "storyId": "api-sandbox", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Otter.ai is a meeting-transcription/AI-notetaker SaaS product, not a developer platform or API where users would test integrations against a sandbox vs production environment; no such concept (test/sandbox mode, staging data) applies to its use case.", "evidenceIds": [] }, { "productId": "otter", "storyId": "api-versioning-policy", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "There is evidence of an Otter public API and an MCP server, but no documentation of API versioning scheme or a formal deprecation policy anywhere in the pack; the openapi probe returned 404s. Missing for 10: versioning scheme documentation, changelog/deprecation policy, migration guides, evidence of stable version lifecycle.", "evidenceIds": [ "otter-docs-26", "otter-docs-40", "otter-probe-1" ] }, { "productId": "otter", "storyId": "automation-bulk-operations", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Otter offers API/webhooks, unlimited file import, and cross-meeting search/analysis (e.g., 'analyze patterns and themes across multiple meetings', 'search meeting transcripts across all time periods') that could support automation across many meetings at once, but there is no explicit documentation of a bulk-edit/bulk-delete/bulk-tag operation or batch endpoint for acting on many items simultaneously. Missing for 10: documented bulk edit/delete/tag UI or API endpoints, evidence of batch processing limits/behavior, and independent confirmation that cross-meeting operations scale reliably.", "evidenceIds": [ "otter-docs-26", "otter-docs-34", "otter-docs-18", "otter-docs-44", "otter-docs-40" ] }, { "productId": "otter", "storyId": "automation-rules-engine", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Otter offers built-in automatic actions (auto-capture of action items, auto-sync to CRM/Zendesk/JIRA/Asana) and lists 'Otter API & Webhooks' and Zapier integration in its pricing page, which would let users build custom event-triggered automations. However, these are fixed, vendor-defined automatic behaviors rather than a documented native interface where users define their own conditional rules; the webhook/Zapier capability is only mentioned as a bullet with no documentation of rule configuration. Missing for 10: a documented rule/automation builder or webhook event catalog showing user-defined trigger-condition-action logic, and independent evidence it works as described.", "evidenceIds": [ "otter-docs-26", "otter-docs-25", "otter-docs-9", "otter-docs-10", "otter-docs-30" ] }, { "productId": "otter", "storyId": "automation-scheduled-jobs", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "Otter documents scheduling only in the narrow sense of automatically joining recurring calendar meetings ('Schedule your AI Meeting Notetaker to automatically join all your Zoom, Teams, and Google Meet meetings'), plus webhooks/API/Zapier integrations that could be chained into workflows. There is no evidence of a general recurring-job/workflow scheduler (e.g., scheduled reports, cron-like automation, or repeatable AI-agent tasks beyond meeting attendance). Missing for 10: documented recurring workflow/job scheduling beyond meeting attendance, evidence of cron-like or repeatable automation configuration, independent confirmation of this capability in use.", "evidenceIds": [ "otter-docs-17", "otter-docs-26", "otter-docs-46" ] }, { "productId": "otter", "storyId": "automation-versioned-workflows", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Otter.ai is a meeting transcription/notes product, not an automation-builder platform with defined workflows/automations that could be versioned, reviewed, or rolled back; there is no concept of an 'automation' object with version history in its evidence. This axis is a category error for this product type.", "evidenceIds": [] }, { "productId": "otter", "storyId": "bot-capture-major-platforms", "verdict": "disputed", "quality": 5, "confidence": "medium", "rationale": "Otter documents solid capture breadth: scheduled bot-based joining across Zoom/Teams/Meet (otter-docs-17), plus bot-free desktop and Meet capture for users who don't want a bot present (otter-docs-2, otter-docs-15, otter-docs-38). But hands-on/community reports concretely contradict the 'recording where I want it' promise — users found the bot joining confidential calls unexpectedly, being unable to identify who invited it, and the bot rejoining despite attempts to remove it (otter-comm-8, otter-comm-6, otter-comm-7, otter-comm-5), undermining reliable, controlled capture. missing for 10: independent verification of accurate/controllable scheduling behavior, resolution of the 'can't stop the bot' complaints, and confirmation that bot-free recording is equally reliable across all three platforms.", "evidenceIds": [ "otter-docs-17", "otter-docs-2", "otter-docs-15", "otter-docs-38", "otter-comm-8", "otter-comm-6", "otter-comm-7", "otter-comm-5" ] }, { "productId": "otter", "storyId": "botless-audio-capture", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Otter explicitly documents desktop-based, bot-free recording/transcription (\"Record conversations directly from your Mac or Windows desktop, without bots joining the call\" and \"Capture impromptu Google Meet calls without a bot present\"), directly matching the story. However, all supporting evidence is vendor-authored; community discussion in the pack focuses entirely on the bot-based joining experience (visible bot, default sharing, privacy issues) rather than validating the bot-free desktop-capture mode, so there is no independent hands-on confirmation this mode works as claimed. Missing for 10: independent/third-party confirmation that bot-free desktop capture actually works and is undetectable to other participants, and detail on what info (if any) is disclosed to other call participants in this mode.", "evidenceIds": [ "otter-docs-2", "otter-docs-15", "otter-docs-38" ] }, { "productId": "otter", "storyId": "calendar-autojoin-rules", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows Otter can auto-join Zoom/Teams/Google Meet meetings via scheduling (otter-docs-17), but nothing in the pack describes connecting a Google or Outlook calendar or setting per-meeting-type rules for which meetings get captured. This specific calendar-integration and rule-based control capability is unevidenced.", "evidenceIds": [ "otter-docs-17" ] }, { "productId": "otter", "storyId": "chat-with-meeting-history", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Otter AI Chat and its enterprise MCP server explicitly support natural-language querying across meeting history ('what did we decide about pricing?'-style questions), searching transcripts across all time periods, analyzing patterns across meetings, and citing/linking back to source meetings via the AI Chat interface. This is corroborated by a live runtime probe confirming the MCP endpoint is real and OAuth-gated, not vaporware. Missing for 10: independent hands-on verification of answer accuracy/quality and explicit confirmation that answers include inline source citations (docs describe search/analysis but don't detail citation format in depth).", "evidenceIds": [ "otter-docs-1", "otter-docs-11", "otter-docs-18", "otter-docs-34", "otter-docs-46", "otter-probe-rt-1" ] }, { "productId": "otter", "storyId": "clips-highlights-share", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack shows Otter can share full transcripts, notes, and summaries, and sync them to other tools, but there is no mention of cutting a specific soundbite/highlight clip from a recording to share instead of the whole call. Missing for 10: any documented clip/highlight creation or snippet-sharing feature, timestamped audio/video excerpt export, or hands-on evidence of this specific capability.", "evidenceIds": [ "otter-docs-32", "otter-docs-12" ] }, { "productId": "otter", "storyId": "consent-notification-features", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence pack item describes any real consent mechanism (participant notification banners, in-meeting disclosure indicators, or admin-enforced consent settings); the docs focus entirely on recording, transcription, and integrations. Community reports go further, describing the bot silently joining sensitive/confidential meetings, transcripts shared with all participants by default without prior notice, and company support dismissing responsibility when participants weren't informed — confirming the absence of a genuine consent feature rather than just a documentation gap.", "evidenceIds": [ "otter-comm-2", "otter-comm-3", "otter-comm-7", "otter-comm-8", "otter-comm-5" ] }, { "productId": "otter", "storyId": "crm-auto-sync", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Vendor docs claim CRM integrations that extract deal details, notes, and next steps and sync them to Salesforce and HubSpot (otter-docs-4, otter-docs-8, otter-docs-25, otter-docs-36), which covers two of the three named CRMs, but Attio is never mentioned anywhere in the evidence pack. All support is first-party marketing copy with no independent/hands-on confirmation that notes actually land on the correct contact/deal record versus a generic sync, and the pricing page flags the integration with an asterisk suggesting limitations. Missing for 10: Attio support, independent verification of accurate record-level (contact/deal) matching, and confirmation the sync works outside enterprise/marketing claims.", "evidenceIds": [ "otter-docs-4", "otter-docs-8", "otter-docs-25", "otter-docs-36", "otter-docs-40" ] }, { "productId": "otter", "storyId": "custom-templates-prompts", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Otter claims 'fully customizable, AI-powered meeting summaries' that adapt to meeting purpose and functional role (sales, recruiters, PMs), implying some template-like customization, but there's no documentation of a concrete UI for creating/saving custom templates or prompts per meeting type (discovery call vs 1:1 vs standup) that a sales lead could configure themselves. Missing for 10: explicit template/prompt library or editor, evidence of user-defined per-meeting-type presets, and any hands-on confirmation that summaries can be shaped beyond the automatic role-based defaults.", "evidenceIds": [ "otter-docs-37", "otter-docs-21" ] }, { "productId": "otter", "storyId": "followup-email-draft", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Otter directly claims automatic follow-up email drafting from meetings (otter-docs-41: 'Instantly auto-generate follow-up emails and next steps for client calls'), plus related CRM sync of key deal details and next steps (otter-docs-4) and role-tailored summaries for sales (otter-docs-37), matching the sales-lead persona. Missing for 10: independent hands-on confirmation of the follow-up email drafting feature specifically (evidence is vendor-sourced only) and clarity on whether it's Enterprise-tier gated like other advanced features.", "evidenceIds": [ "otter-docs-41", "otter-docs-4", "otter-docs-37", "otter-docs-3", "otter-docs-42" ] }, { "productId": "otter", "storyId": "meeting-mcp-server", "verdict": "partial", "quality": 7, "confidence": "high", "rationale": "Otter has an official, live MCP server (mcp.otter.ai) confirmed by a runtime probe returning proper OAuth-gated 401/WWW-Authenticate flow, and docs describe searching meetings, transcripts, action items, and granular permission scoping via Claude/ChatGPT — matching the story closely (otter-docs-16, otter-docs-46, otter-docs-47, otter-docs-35, otter-probe-rt-1, otter-probe-2). However, the same probe notes this MCP/API access is gated to Enterprise workspaces only, meaning many AI-native individual users cannot actually use it without an enterprise contract. Missing for 10: broader/self-serve tier availability, independent third-party (non-vendor) confirmation of the OAuth/query experience beyond the runtime probe, and public documentation of full query capabilities (e.g., exact tool/resource list).", "evidenceIds": [ "otter-docs-16", "otter-docs-46", "otter-docs-47", "otter-docs-35", "otter-probe-rt-1", "otter-probe-2" ] }, { "productId": "otter", "storyId": "mobile-in-person-capture", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Otter's docs confirm bot-free recording from desktop and searchable, shared workspaces (otter-docs-2, otter-docs-5, otter-docs-18, otter-docs-38), and general live transcription/speaker recognition (otter-docs-22), but none of the evidence explicitly describes a mobile app for recording in-person conversations — only desktop capture is documented. Missing for 10: explicit mobile-app in-person recording capability, confirmation that mobile-captured notes sync into the same workspace as other recordings, and independent hands-on evidence of mobile recording quality.", "evidenceIds": [ "otter-docs-2", "otter-docs-5", "otter-docs-18", "otter-docs-22", "otter-docs-38" ] }, { "productId": "otter", "storyId": "multilingual-meetings", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Otter's marketing states 'live transcription in multiple languages' but the evidence pack has no detail on which languages are supported, whether meeting summaries (not just transcripts) are generated in non-English languages, or how mid-meeting language switching is handled. Community evidence only discusses English-accent transcription quality, giving no corroboration of multilingual performance. Missing for 10: documented language list/coverage, evidence that AI summaries (not just live transcript) work in non-English languages, evidence of handling code-switching/mixed-language meetings, and independent hands-on confirmation of non-English accuracy.", "evidenceIds": [ "otter-docs-22", "otter-comm-9" ] }, { "productId": "otter", "storyId": "no-training-on-my-data", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "Otter documents an enterprise-tier opt-out from AI model training ('Keep your organization's data out of AI model training. Contact your account manager to get started' — otter-docs-43), and community evidence confirms that by default Otter's privacy policy allows using 'anonymized' recordings for training (otter-comm-6), consistent with an opt-in-by-default posture that requires manual admin action to disable. However, the opt-out is not a self-service, enforceable admin toggle — it requires contacting an account manager — and no evidence pack item documents SOC 2 or HIPAA compliance status. Missing for 10: explicit SOC 2/HIPAA certification documentation, a self-service admin-console opt-out control, and independent audit confirmation that opted-out orgs' data is actually excluded from training.", "evidenceIds": [ "otter-docs-43", "otter-comm-6", "otter-docs-20", "otter-docs-19" ] }, { "productId": "otter", "storyId": "openness-api-parity", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "Otter documents a Public API/Webhooks (Pro+ tier) and a hosted MCP server for querying meeting transcripts, summaries and action items (otter-docs-26/40/46, otter-probe-rt-1 confirms the MCP endpoint is live and OAuth-gated), but these are limited to read/query-style meeting-data access and are gated to paid/Enterprise workspaces rather than exposing full UI parity (recording controls, collaborative editing, CRM/ticket integrations, admin/security settings) as callable API operations, and no public OpenAPI/reference spec was found (otter-probe-1 all 404). Missing for 10: evidence of API coverage for non-meeting-data UI actions (recording management, collaborative editing, integration configuration), a public API reference/spec, and availability outside Enterprise tier.", "evidenceIds": [ "otter-docs-26", "otter-docs-40", "otter-docs-46", "otter-docs-6", "otter-probe-2", "otter-probe-rt-1", "otter-probe-1" ] }, { "productId": "otter", "storyId": "openness-full-export", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Otter offers some data egress via S3 export of transcripts/summaries/metadata and its public API/webhooks, which could support portability, but there is no documented comprehensive 'export all your data' or account-deletion/data-portability feature, nor any explicit open-format guarantee (e.g., standard transcript formats, full account export tool). missing for 10: dedicated full-account data export tool, explicit open/standard file formats, documented account deletion/data-takeout process, independent confirmation of successful full export.", "evidenceIds": [ "otter-docs-29", "otter-docs-26", "otter-docs-40" ] }, { "productId": "otter", "storyId": "openness-open-license", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Otter.ai is a closed, commercial SaaS meeting-transcription product with no open-source licensing model; source-code openness is not a category this product participates in.", "evidenceIds": [] }, { "productId": "otter", "storyId": "openness-self-host", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Otter.ai is a cloud SaaS meeting-transcription product with no self-hosted/open-source deployment option evidenced or plausible for this category; self-hosting is not a fair axis for a proprietary SaaS transcription service.", "evidenceIds": [] }, { "productId": "otter", "storyId": "pre-meeting-context", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "Otter clearly supports search across past meetings, grouping by team/project/topic, and AI Chat that can surface insights and follow-ups (otter-docs-1, otter-docs-5, otter-docs-11, otter-docs-12, otter-docs-18), which could be used to find prior context with the same people. However, there is no evidence of a proactive, calendar-triggered 'pre-meeting brief' that automatically surfaces past meetings with the same attendees before a call starts — all capabilities described are pull-based search/chat rather than an automated prep experience tied to the upcoming meeting. Missing for 10: automatic calendar-based attendee matching, a dedicated 'pre-call brief' UI/feature, and any independent evidence confirming this specific prep workflow works as described.", "evidenceIds": [ "otter-docs-1", "otter-docs-5", "otter-docs-11", "otter-docs-12", "otter-docs-18", "otter-docs-34" ] }, { "productId": "otter", "storyId": "privacy-data-residency", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence anywhere in the pack mentions data residency, regional storage options, or geographic controls over where data is stored; the closest privacy-related item (otter-docs-43) only addresses excluding data from model training, not storage location. Community evidence discusses data sharing and retention concerns but not regional choice, so this applicable privacy axis has no supporting evidence.", "evidenceIds": [] }, { "productId": "otter", "storyId": "privacy-no-training", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Otter explicitly advertises an enterprise-only opt-out ('Keep your organization's data out of AI model training. Contact your account manager to get started' — otter-docs-43), but this is gated behind Enterprise plans and manual account-manager setup rather than a self-serve control available to all users. Community reports (otter-comm-6) note that by default Otter's privacy policy allows use of 'anonymized' recordings as training data, meaning most users cannot avoid this without enterprise contracting. Missing for 10: self-serve toggle for all tiers, independent confirmation the enterprise opt-out is honored in practice, and clarity on what 'anonymized' training use means for non-enterprise accounts.", "evidenceIds": [ "otter-docs-43", "otter-comm-6" ] }, { "productId": "otter", "storyId": "privacy-retention-controls", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Otter's docs mention only a narrow enterprise-only opt-out from AI-model training (otter-docs-43) via contacting an account manager, but there is no documented self-service data retention policy, deletion controls, or export/delete workflow for individual users. Community evidence (otter-comm-2, otter-comm-4, otter-comm-6, otter-comm-7) further indicates data is retained in the cloud, used for training unless specially arranged, and that deletion/support requests go unanswered, undermining any claim of user control over retention/deletion.", "evidenceIds": [ "otter-docs-43", "otter-comm-2", "otter-comm-4", "otter-comm-6", "otter-comm-7" ] }, { "productId": "otter", "storyId": "privacy-telemetry-optout", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence of a telemetry/usage-tracking opt-out setting; the closest item (otter-docs-43) only covers excluding org data from AI model training for Enterprise accounts, not general telemetry/usage analytics opt-out, and community reports actually highlight data-sharing/retention concerns rather than opt-out controls.", "evidenceIds": [ "otter-docs-43", "otter-comm-6", "otter-comm-13" ] }, { "productId": "otter", "storyId": "retention-deletion-controls", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence describes configurable retention schedules, auto-deletion of transcripts/recordings, or an on-demand data erasure mechanism; enterprise docs mention audit trails and excluding data from AI training but nothing about retention/deletion controls, and community reports even highlight data being retained/shared unexpectedly. This axis clearly applies to an IT-admin/enterprise product but is unaddressed in the evidence.", "evidenceIds": [ "otter-docs-20", "otter-docs-43", "otter-comm-6" ] }, { "productId": "otter", "storyId": "search-across-meetings", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Otter directly supports cross-meeting search and jump-to-moment via natural-language search over transcripts, summaries, and notes ('Search your meeting transcripts across all time periods', 'Find key insights from past calls, documents, and more using natural-language', grouping by project/topic), plus AI Chat and MCP server for querying meeting knowledge, corroborated by a live runtime probe confirming the MCP endpoint is real and functioning. Missing for 10: independent hands-on verification of precise timestamp jump-to-moment UX and any third-party review confirming search accuracy/recall across large historical archives.", "evidenceIds": [ "otter-docs-18", "otter-docs-11", "otter-docs-5", "otter-docs-1", "otter-docs-46", "otter-probe-rt-1", "otter-probe-2" ] }, { "productId": "otter", "storyId": "sharing-permissions-controls", "verdict": "disputed", "quality": 4, "confidence": "medium", "rationale": "Otter documents enterprise access controls (SSO via Okta/Azure AD, audit trails/logging, OAuth-gated granular permissions for MCP) suggesting admin-controlled sharing exists at the enterprise tier, but multiple independent hands-on reports directly contradict the 'private-by-default' premise: users report Otter shares transcripts with every meeting participant by default without consent, and confidential/sensitive meetings were transcribed and distributed without attendees' knowledge, causing real harm (killed business deal, custody case exposure). Missing for 10: documented granular link/folder/workspace-level permission controls, clear evidence of a private-by-default note setting, and resolution of the community reports of default-sharing behavior.", "evidenceIds": [ "otter-docs-19", "otter-docs-20", "otter-docs-47", "otter-comm-2", "otter-comm-3", "otter-comm-5", "otter-comm-7", "otter-comm-8" ] }, { "productId": "otter", "storyId": "slack-notion-zapier-push", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Otter documents direct integrations with Slack-adjacent workflow tools (Notion is not explicitly named, but Zapier, Airtable, ClickUp, Zendesk, ServiceNow, JIRA, Asana, Glean, S3, CRM syncs), plus a public API/webhooks and a live, OAuth-gated MCP server confirmed by runtime probe, enabling notes/action items to flow into thousands of apps via Zapier and beyond. Missing for 10: explicit first-party mention of Slack and Notion integrations by name, and independent (non-vendor) confirmation of the Zapier/Airtable/ClickUp integrations actually working in practice.", "evidenceIds": [ "otter-docs-10", "otter-docs-25", "otter-docs-28", "otter-docs-31", "otter-docs-33", "otter-docs-9", "otter-docs-26", "otter-probe-2", "otter-probe-rt-1" ] }, { "productId": "otter", "storyId": "speaker-identification", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Otter's docs mention 'speaker recognition' during live transcription and 'taggable speakers' in pricing tiers, suggesting some diarization plus a manual tagging mechanism to assign real names, but there's no detailed documentation of automatic real-name matching accuracy or independent verification of correctness. Community threads only discuss transcription accuracy for accents, not speaker attribution reliability. Missing for 10: documentation of automatic vs. manual name assignment, accuracy benchmarks for speaker identification, and independent hands-on verification that speakers are correctly named rather than generic labels.", "evidenceIds": [ "otter-docs-22", "otter-docs-24", "otter-comm-9" ] }, { "productId": "otter", "storyId": "structured-ai-summaries", "verdict": "disputed", "quality": 5, "confidence": "medium", "rationale": "Otter's docs claim every meeting is turned into a structured summary with decisions, action items, and next steps (otter-docs-21, otter-docs-3, otter-docs-37, otter-docs-30), which matches the story. However a hands-on account describes Otter emailing an 'absurd, inaccurate outline' after a real meeting (otter-comm-1), directly contradicting the 'good enough to share without editing' bar, and another user notes it doesn't handle accented English well (otter-comm-9), suggesting summaries often need review. Missing for 10: independent benchmarking of summary accuracy/completeness, and confirmation that decisions/action items are reliably correct without user correction.", "evidenceIds": [ "otter-docs-21", "otter-docs-3", "otter-docs-37", "otter-docs-30", "otter-comm-1", "otter-comm-9" ] }, { "productId": "otter", "storyId": "transcription-quality-claims", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "The evidence pack shows only marketing-style feature claims (AI-powered summaries, live transcription, speaker recognition) with no vendor documentation of the transcription model(s) used, quantified accuracy benchmarks, or explicitly stated known limitations (e.g., accent/language performance, noise handling). Community evidence even flags real accuracy gaps (accents, non-English speech) that the vendor's own docs never acknowledge, reinforcing the absence of transparent quality documentation.", "evidenceIds": [ "otter-docs-22", "otter-comm-9", "otter-comm-12" ] }, { "productId": "otter", "storyId": "transcripts-via-api", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "Otter documents an 'Otter API & Webhooks' feature in pricing tiers and a Public API for custom integrations, plus a live MCP server for pulling transcripts/summaries/action items into AI tools, but the runtime probe shows the MCP endpoint is OAuth-gated and both API/MCP access are restricted to Enterprise workspaces (contact account manager), not self-serve; no public OpenAPI/swagger docs were found (all 404). Missing for 10: publicly discoverable API reference docs, evidence of self-serve API key generation for individual/non-enterprise users, and independent confirmation of successful script-based pulls.", "evidenceIds": [ "otter-docs-26", "otter-docs-40", "otter-docs-46", "otter-probe-1", "otter-probe-2", "otter-probe-rt-1" ] }, { "productId": "otter", "storyId": "transparent-pricing-free-tier", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "The evidence confirms a public /pricing page listing tier-specific features (e.g., otter-docs-23-27 detail limits like '3 lifetime file imports' and '3 concurrent meetings' presumably tied to a plan), and enterprise-tier features explicitly require contacting an account manager (otter-docs-43), implying lower tiers are self-serve. However, no evidence shows actual dollar prices, a clear free-vs-paid breakdown, or confirmation that all paid-tier costs are shown without a sales contact requirement. Missing for 10: explicit price points per tier, confirmation of a self-serve checkout flow, and independent corroboration that no sales-gate exists for basic paid tiers.", "evidenceIds": [ "otter-docs-23", "otter-docs-24", "otter-docs-25", "otter-docs-26", "otter-docs-27", "otter-docs-43" ] } ]