[ { "productId": "attio", "storyId": "agent-enriches-lead", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Attio has a documented REST API for creating/updating records (attio-docs-2, attio-docs-8/9/14) and an official MCP server (attio-probe-3, attio-docs-3, attio-docs-12) letting AI tools search, update and create records, and separately advertises 'automatic data enrichment' (attio-docs-26/45/47). However, there is no explicit documentation showing an end-to-end workflow of creating a lead, auto-filling company data, and assigning an owner in one API/MCP call chain — owner-assignment and enrichment-via-API/MCP specifics are unevidenced. Missing for 10: explicit API/MCP example of owner assignment, documented enrichment endpoint/field mapping, and a hands-on end-to-end example combining all three steps.", "evidenceIds": [ "attio-docs-2", "attio-docs-3", "attio-docs-12", "attio-docs-26", "attio-docs-45", "attio-docs-47", "attio-probe-3", "attio-docs-8", "attio-docs-9", "attio-docs-14" ] }, { "productId": "attio", "storyId": "agent-preps-account-brief", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Attio has an official MCP server (attio-docs-3, attio-probe-3) and a REST API supporting filtering/sorting, deal/company/history objects (attio-docs-1,2,6,29,30,16) that would let an agent pull open deals, history, and records; the AI platform page explicitly names 'create account briefs' as a capability (attio-docs-22) alongside call transcription/logging that could feed 'recent emails/interactions' context. Missing for 10: independent/hands-on confirmation that the MCP server actually returns email history or that account-brief generation works end-to-end in practice, and explicit documentation of email data access via the API.", "evidenceIds": [ "attio-docs-3", "attio-probe-3", "attio-docs-22", "attio-docs-16", "attio-docs-30", "attio-docs-2", "attio-docs-6" ] }, { "productId": "attio", "storyId": "agent-updates-deal-stages", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Attio has a documented MCP server that lets AI tools search, update and manage workspace data (attio-probe-3, attio-docs-3, attio-docs-12), plus REST API with read/write access and webhooks for real-time signals (attio-docs-2, attio-docs-5), and deals/next-steps fields exist as standard objects (attio-docs-13, attio-docs-30). AI features mention drafting follow-ups and updating records, and call AI picks up buying signals (attio-docs-22, attio-docs-24), suggesting the pieces exist, but there's no concrete documentation of an agent workflow specifically ingesting email/meeting signals to update deal stage/next-steps fields end-to-end. Missing for 10: explicit documented workflow/recipe connecting email or meeting transcript signals to automated deal-stage/next-steps updates via API or MCP, and independent/hands-on confirmation of this specific automation working.", "evidenceIds": [ "attio-probe-3", "attio-docs-3", "attio-docs-12", "attio-docs-2", "attio-docs-5", "attio-docs-13", "attio-docs-30", "attio-docs-22", "attio-docs-24" ] }, { "productId": "attio", "storyId": "agentic-agent-docs", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "Attio directly hosts a working llms.txt at docs.attio.com/llms.txt (verified via probe returning HTTP 200 with structured doc links), confirming agents can be pointed at agent-oriented documentation, and this is corroborated by an official MCP endpoint for AI tool integration. missing for 10: independent third-party confirmation beyond the direct probe.", "evidenceIds": [ "attio-probe-1", "attio-probe-3", "attio-docs-3" ] }, { "productId": "attio", "storyId": "agentic-ai-insights", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Attio's AI platform docs describe in-product AI features like buying-signal detection, call transcription and analysis, account briefs, AI-driven workflow agents (scoring, routing, web research), and 'search, update, create with AI' surfaced directly in the CRM, which match the story of AI-generated insights/suggestions from workspace data. Missing for 10: independent/hands-on verification of these AI insight features in real use (all evidence is vendor marketing copy) and detail on underlying model/accuracy.", "evidenceIds": [ "attio-docs-12", "attio-docs-22", "attio-docs-23", "attio-docs-24", "attio-docs-18", "attio-docs-19", "attio-docs-37", "attio-docs-25" ] }, { "productId": "attio", "storyId": "agentic-autonomous-automation", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Attio documents workflow automations with triggers (e.g., new deal created) and AI-driven 'agents' (Web Agent, Routing Agent, Scoring Agent) that run automatically in the background, plus webhooks for real-time event handling. However, there's no independent/hands-on evidence of true autonomous multi-step agentic execution or scheduling reliability beyond first-party marketing copy. Missing for 10: independent verification of autonomous background execution, details on failure handling/monitoring of these automations, and evidence beyond vendor marketing pages.", "evidenceIds": [ "attio-docs-17", "attio-docs-18", "attio-docs-19", "attio-docs-37", "attio-docs-36", "attio-docs-5", "attio-docs-25" ] }, { "productId": "attio", "storyId": "agentic-builtin-assistant", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Attio has built-in AI features that act as an assistant: search/update/create with AI, drafting follow-ups, updating records, scheduling next steps, building account briefs, and even building workflows by describing a goal, plus AI call transcription and signal detection. This shows delegable AI assistant tasks embedded in the product, but evidence lacks detail on a dedicated chat-style assistant UI, task delegation scope, or independent hands-on confirmation of reliability. missing for 10: independent/hands-on validation of assistant behavior, clarity on assistant UI/interaction model, and limits/scope of delegable tasks.", "evidenceIds": [ "attio-docs-12", "attio-docs-22", "attio-docs-23", "attio-docs-24", "attio-docs-25" ] }, { "productId": "attio", "storyId": "agentic-headless", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Attio exposes a REST API, OAuth, webhooks, and SQL query access that let developers script and automate workspace actions headlessly outside the UI, and probes confirm a real API/docs surface (llms.txt, MCP server) rather than pure marketing. However, there is no mention of a CLI, SDK for CI pipelines, or any CI-specific tooling/guide, so the 'run in CI' half of the story is unevidenced. Missing for 10: CLI or CI-pipeline integration guide, examples of scheduled/headless jobs, official SDK usable in build pipelines.", "evidenceIds": [ "attio-docs-2", "attio-docs-5", "attio-docs-7", "attio-docs-4", "attio-probe-1", "attio-probe-2" ] }, { "productId": "attio", "storyId": "agentic-mcp-client", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows Attio ships its own MCP server so external AI tools (Claude, ChatGPT) can connect to and control Attio (attio-docs-3, attio-probe-3), but this is the reverse of the story — there is no evidence Attio itself can plug in and consume external MCP servers' tools.", "evidenceIds": [ "attio-docs-3", "attio-probe-3" ] }, { "productId": "attio", "storyId": "agentic-mcp-server", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Attio documents an official MCP server (attio.com/mcp) explicitly enabling connection of Claude, ChatGPT, or other AI tools to search, update, and manage the workspace, and a probe confirms this page exists. Missing for 10: independent/hands-on third-party corroboration of the MCP server working in practice and more detail on setup/auth specifics.", "evidenceIds": [ "attio-docs-3", "attio-probe-3" ] }, { "productId": "attio", "storyId": "agentic-nl-commands", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Attio explicitly documents natural-language control via AI: connecting Claude/ChatGPT to search, update and manage the workspace, an official MCP server, and AI features to search/update/create records and build workflows just by describing goals. This directly matches the story of operating the product via natural-language commands, though evidence is vendor-documented without independent hands-on verification. missing for 10: independent/third-party confirmation of natural-language command reliability, and depth on limits/edge cases of NL command coverage.", "evidenceIds": [ "attio-docs-3", "attio-docs-12", "attio-docs-22", "attio-docs-25", "attio-probe-3" ] }, { "productId": "attio", "storyId": "agentic-official-cli", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Attio is a CRM SaaS platform whose ecosystem could plausibly ship an official CLI, but the evidence pack contains no mention of a CLI tool anywhere—only REST API, webhooks, SQL query access, and an MCP server for AI assistants. Absence of evidence for this applicable capability yields none.", "evidenceIds": [ "attio-docs-2", "attio-docs-4", "attio-probe-3" ] }, { "productId": "attio", "storyId": "agentic-public-api", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Attio documents a REST API for reading/writing workspace data, OAuth flows, filtering/sorting, rate limiting, and webhooks, giving AI-native users a fully documented public API to drive the product; llms.txt and docs.attio.com confirm developer-facing documentation. missing for 10: no discoverable OpenAPI/Swagger spec (probe found 404s) and no independent/third-party corroboration beyond vendor docs.", "evidenceIds": [ "attio-docs-2", "attio-docs-5", "attio-docs-6", "attio-docs-7", "attio-docs-32", "attio-probe-1", "attio-probe-2" ] }, { "productId": "attio", "storyId": "agentic-scoped-keys", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Attio documents a general OAuth flow for third-party apps (attio-docs-7) and an MCP server for AI tools (attio-probe-3), but there is no evidence of granular, least-privilege scopes or agent-specific API credential issuance — no mention of scope lists, permission levels, or restricting an API key/token to specific objects/actions for an AI agent.", "evidenceIds": [ "attio-docs-7", "attio-probe-3" ] }, { "productId": "attio", "storyId": "agentic-sdks", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "Attio documents a REST API, OAuth flow, webhooks, and a TypeScript-based 'Apps' framework for building on the platform, which functions as a developer toolkit, but there is no explicit mention of dedicated official client SDKs (e.g., named Node.js/Python/Go libraries), and the OpenAPI spec probe returned 404s, suggesting no auto-generated or downloadable SDK artifacts. Missing for 10: named official language SDK packages/libraries, published SDK versioning/changelog, and independent developer corroboration of SDK usage.", "evidenceIds": [ "attio-docs-1", "attio-docs-2", "attio-docs-7", "attio-probe-2" ] }, { "productId": "attio", "storyId": "agentic-webhooks", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Attio's REST API docs explicitly describe webhook subscriptions for real-time change events, including signed payloads for verification, which directly satisfies subscribing to events via webhooks. Missing for 10: independent/hands-on corroboration beyond vendor docs, and details on event-type granularity/filtering for webhook subscriptions.", "evidenceIds": [ "attio-docs-2", "attio-docs-5", "attio-docs-28" ] }, { "productId": "attio", "storyId": "api-interactive-docs", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The docs describe REST API concepts (filtering, webhooks, rate limits, OAuth) but there is no mention of an interactive API reference or runnable/try-it examples, and a probe found no discoverable OpenAPI spec at any standard path, suggesting no such interactive console exists.", "evidenceIds": [ "attio-docs-7", "attio-docs-32", "attio-docs-40", "attio-probe-2" ] }, { "productId": "attio", "storyId": "api-machine-spec", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Direct probes for OpenAPI/Swagger spec files at Attio's docs domain all returned 404, and no evidence pack item references a downloadable machine-readable API spec despite extensive REST API documentation.", "evidenceIds": [ "attio-probe-2" ] }, { "productId": "attio", "storyId": "api-sandbox", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of a sandbox/test workspace or staging environment separate from production; docs cover API, objects, workflows, and MCP but nothing about sandbox testing without touching live data.", "evidenceIds": [] }, { "productId": "attio", "storyId": "api-versioning-policy", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence of API versioning scheme or a documented deprecation policy; the docs cover REST API features (filtering, webhooks, rate limits, OAuth) but nothing about version numbers, changelogs, or deprecation timelines. OpenAPI spec probes also 404'd, further suggesting no clear versioned contract is published.", "evidenceIds": [ "attio-docs-7", "attio-docs-32", "attio-probe-2" ] }, { "productId": "attio", "storyId": "auto-enrichment", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Attio's pricing page explicitly lists 'Automatic data enrichment' and 'Real-time contact syncing' as features, and the platform data page mentions prospect context 'automatically drawn from 100' (sources, cut off), suggesting some enrichment capability. However there's no detail on what firmographic/contact data sources are used, how enrichment is triggered/configured, or coverage/accuracy — missing for 10: documentation of enrichment data providers, configuration/setup details, coverage scope, and independent/hands-on verification of enrichment quality.", "evidenceIds": [ "attio-docs-26", "attio-docs-45", "attio-docs-47", "attio-docs-48", "attio-docs-35" ] }, { "productId": "attio", "storyId": "automation-bulk-operations", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Attio's REST API supports filtering/sorting to narrow record sets and has SQL query access, and its API/MCP integration could enable scripted bulk updates, but there is no explicit documentation of a bulk-update/bulk-create/bulk-delete endpoint or batch operation limits for AI-driven mass edits. missing for 10: explicit bulk write/update API endpoints, documented batch size limits, and evidence of AI agents performing bulk operations across many records at once.", "evidenceIds": [ "attio-docs-4", "attio-docs-6", "attio-docs-27", "attio-docs-31", "attio-docs-40", "attio-probe-3" ] }, { "productId": "attio", "storyId": "automation-rules-engine", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Attio's Workflows platform explicitly supports event-based triggers (e.g. 'trigger when a new deal record is created') that fire automated actions/agents (routing, scoring, web research agents), and webhooks/REST API allow custom event-driven automation. Missing for 10: detailed documentation of the full trigger/condition/action rule-builder UI, and independent/hands-on verification of complex multi-step automation reliability.", "evidenceIds": [ "attio-docs-10", "attio-docs-17", "attio-docs-36", "attio-docs-37", "attio-docs-18", "attio-docs-19", "attio-docs-5", "attio-docs-25" ] }, { "productId": "attio", "storyId": "automation-scheduled-jobs", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Attio's workflows platform supports event-triggered automations (e.g., 'when a new deal is created') and AI agents that run continuously (routing, scoring, web research), implying ongoing/ongoing-scheduled automation, but there is no explicit documentation of cron-like recurring/time-based scheduling of jobs. Missing for 10: explicit recurring/scheduled job trigger (e.g., 'run every day/week'), documentation of interval-based automation, and independent confirmation of scheduling reliability.", "evidenceIds": [ "attio-docs-10", "attio-docs-17", "attio-docs-18", "attio-docs-19", "attio-docs-37", "attio-docs-25" ] }, { "productId": "attio", "storyId": "automation-versioned-workflows", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of version history, review workflows, or rollback for Attio's automations/workflows; docs describe building and triggering workflows but nothing about versioning or reverting them. missing for 10: version history for automations, change review/approval process, rollback mechanism, audit trail of automation edits.", "evidenceIds": [] }, { "productId": "attio", "storyId": "bidirectional-sync-api", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Attio's docs confirm a read/write REST API, documented rate limits (429 + Retry-After) and webhooks for real-time change detection, which together support much of the story. However, there is no explicit documentation in the evidence pack of upsert/assert-style endpoints or guidance on syncing at scale (batching, pagination limits, throughput), so the story is only partially covered. missing for 10: explicit upsert endpoint docs, scale/batch sync guidance, independent corroboration of reliability at scale.", "evidenceIds": [ "attio-docs-2", "attio-docs-5", "attio-docs-28", "attio-docs-32", "attio-docs-6", "attio-docs-31" ] }, { "productId": "attio", "storyId": "calendar-meeting-sync", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence describes a calendar sync feature that surfaces meetings on contact/deal timelines; mentions of 'real-time contact syncing' and call logging/transcription do not address calendar/meeting sync specifically.", "evidenceIds": [] }, { "productId": "attio", "storyId": "contact-company-records", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Attio's data model natively supports People and Companies as linked objects connected via a graph model, with custom fields, list/table views, and full interaction history surfaced per record (e.g., 'Link objects to make your data actionable' and 'Get instant visibility into the full history of every interaction'). This directly matches the ops story of managing linked contact/company records with activity timelines. missing for 10: independent/hands-on corroboration of the timeline UI itself (only first-party marketing/docs cited), and no explicit screenshot or detailed description of the timeline feed contents.", "evidenceIds": [ "attio-docs-9", "attio-docs-16", "attio-docs-14", "attio-docs-29", "attio-docs-46", "attio-docs-34" ] }, { "productId": "attio", "storyId": "crm-migration", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Attio references migration mostly via marketing-chat snippets promising deal history mapping and an onboarding migration checklist, but there is no documented import tool, CSV/CRM connector, owner-mapping mechanism, or independent verification that records/owners/history transfer intact. missing for 10: a documented migration tool or CRM-specific importer, evidence of owner/user mapping during migration, independent case studies or hands-on confirmation of successful full-history migration, and details on handling of activity/history data beyond a marketing anecdote.", "evidenceIds": [ "attio-docs-15", "attio-docs-38", "attio-docs-44", "attio-docs-16" ] }, { "productId": "attio", "storyId": "custom-fields-views", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Attio's docs confirm custom fields ('Customize fields to capture exactly what you need to track'), filtering/sorting capabilities, and object/list data modeling that ops users could use to build views without engineering, but evidence is API/docs-centric rather than showing the actual no-admin UI workflow for creating and sharing saved views. missing for 10: explicit documentation of the UI-level 'shared views' feature and permission model confirming non-admin ops users can create/share views without admin involvement.", "evidenceIds": [ "attio-docs-46", "attio-docs-6", "attio-docs-27", "attio-docs-31", "attio-docs-29", "attio-docs-34" ] }, { "productId": "attio", "storyId": "custom-objects", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Attio's docs explicitly support creating custom objects with custom fields, and linking objects via a graph model to build relationships beyond the standard people/company/deal objects (attio-docs-8, attio-docs-9, attio-docs-46, attio-docs-29). This is corroborated by API-level guidance for objects and lists as domain modeling primitives. missing for 10: independent/hands-on third-party confirmation of custom object creation limits or relationship types, and deeper API reference detail on relationship/field-type configuration.", "evidenceIds": [ "attio-docs-8", "attio-docs-9", "attio-docs-46", "attio-docs-29", "attio-docs-14" ] }, { "productId": "attio", "storyId": "dedupe-merge-records", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence pack item mentions duplicate detection or record merging for contacts/companies; docs cover objects, lists, filtering, webhooks, and AI features but nothing about dedupe/merge workflows.", "evidenceIds": [] }, { "productId": "attio", "storyId": "email-templates-sequences", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Attio is a CRM with data model, workflows, AI agents, and API/webhook capabilities, but the evidence pack contains no mention of templated email sending or multi-step outbound sequence/cadence functionality for prospects; only 'draft follow-ups' via AI assistant is mentioned, not automated sequences.", "evidenceIds": [] }, { "productId": "attio", "storyId": "fast-time-to-pipeline", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Attio ships default People/Companies objects and optional Deals that can be enabled instantly (attio-docs-14, attio-docs-13), and marketing copy references a migration checklist and same-week team migration (attio-docs-38, attio-docs-39, attio-docs-44), suggesting some self-serve speed. However, these quotes describe 'we'll map it during onboarding' which implies vendor/human-assisted setup rather than a pure self-serve under-an-hour flow, and there is no evidence of a guided import wizard, templates, or time-to-value benchmarks. Missing for 10: concrete self-serve CSV/import tooling, onboarding time benchmarks, evidence that no implementation partner or vendor assistance is needed.", "evidenceIds": [ "attio-docs-13", "attio-docs-14", "attio-docs-38", "attio-docs-39", "attio-docs-44" ] }, { "productId": "attio", "storyId": "lead-assignment-routing", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Attio's Workflows platform explicitly includes a 'Routing Agent' that 'routes every lead to the right rep or channel' and a 'Scoring Agent' that assigns fit based on ICP criteria, directly supporting automated lead assignment; workflows can also trigger on new record creation. However, evidence is all vendor marketing copy with no configuration detail on round-robin logic, tie-breaking, or capacity balancing, and no independent/hands-on confirmation. Missing for 10: detailed documentation of round-robin/assignment rule configuration options, independent or hands-on validation of the Routing Agent in practice, and evidence of load-balancing or fairness logic.", "evidenceIds": [ "attio-docs-18", "attio-docs-37", "attio-docs-17", "attio-docs-10" ] }, { "productId": "attio", "storyId": "marketplace-integrations", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows Attio has a developer platform for building custom apps, REST API, webhooks, and OAuth, plus an AI/MCP connector, but there is no mention of a prebuilt app marketplace with ready-made Slack, support desk, marketing, or data warehouse integrations that ops users can simply install.", "evidenceIds": [ "attio-docs-1", "attio-docs-2", "attio-docs-7", "attio-probe-1" ] }, { "productId": "attio", "storyId": "multiple-pipelines", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Attio's docs describe lists as a mechanism to 'aggregate records and model business processes' distinct from objects, implying that multiple lists (each potentially with its own stage/status field) can serve as separate pipelines for different products or motions, and deals is an optional, configurable object. However, there is no explicit documentation confirming per-list custom stage sets or multiple concurrent pipelines with distinct stages for different motions. Missing for 10: explicit docs on creating multiple pipelines with independent stage sets, UI screenshots or guides showing per-list stage configuration, and any customer/hands-on evidence of running distinct pipelines for different products.", "evidenceIds": [ "attio-docs-29", "attio-docs-13", "attio-docs-14", "attio-docs-8" ] }, { "productId": "attio", "storyId": "openness-api-parity", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Attio's REST API covers core CRUD on objects/lists, filtering/sorting, webhooks, and OAuth, and there's an official MCP server for AI agent access, suggesting broad parity with UI operations for data management. However, evidence doesn't confirm API parity for newer AI-native workflow builder features (natural-language workflow creation, AI call recording/insights, routing/scoring agents) or reporting/visualization capabilities, and no OpenAPI spec was found to verify full endpoint coverage. Missing for 10: explicit confirmation that all UI-exposed features (AI agents, workflow builder, reporting/dashboards) are API-accessible, and a published OpenAPI spec proving endpoint completeness.", "evidenceIds": [ "attio-docs-2", "attio-docs-6", "attio-docs-7", "attio-docs-27", "attio-docs-31", "attio-probe-2", "attio-probe-3", "attio-docs-25", "attio-docs-20" ] }, { "productId": "attio", "storyId": "openness-full-export", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Attio's REST API (attio-docs-2, attio-docs-4, attio-docs-6) lets a developer read/write and query workspace data, which could technically be used to script a full data export, but there is no documented native 'export all data' feature, no mention of open export formats (CSV/JSON dump), and no explicit portability/exit guarantee. Missing for 10: a documented bulk export/backup feature, explicit open-format export (CSV/JSON), and any statement about data portability upon leaving the platform.", "evidenceIds": [ "attio-docs-2", "attio-docs-4", "attio-docs-6" ] }, { "productId": "attio", "storyId": "openness-open-license", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Attio is a closed-source SaaS CRM product; there is no evidence of any open-licensed source code release, and this is not a category where source availability is a typical offering. This is a wrong-axis question for a proprietary SaaS platform.", "evidenceIds": [] }, { "productId": "attio", "storyId": "openness-self-host", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Attio is a SaaS CRM offered only as a hosted cloud product; there is no evidence of any self-hosted or on-premise deployment option, and self-hosting is not a plausible axis for this product category as evidenced.", "evidenceIds": [] }, { "productId": "attio", "storyId": "privacy-data-residency", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence in the pack mentions data residency, region selection, or storage location choices for Attio workspaces; the evidence pack covers API, objects, workflows, AI features, and MCP but nothing on data residency controls.", "evidenceIds": [] }, { "productId": "attio", "storyId": "privacy-no-training", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack addresses AI-training data usage, opt-out controls, or any privacy policy statement about model training on customer data; this is an applicable privacy-posture axis for an AI-native CRM but no supporting documentation exists in the evidence pack.", "evidenceIds": [] }, { "productId": "attio", "storyId": "privacy-retention-controls", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence pack items address data retention policies, export/deletion controls, or privacy/compliance settings for AI-native data handling; all citations concern API features, CRM data modeling, and workflow automation, not retention/deletion controls.", "evidenceIds": [] }, { "productId": "attio", "storyId": "privacy-telemetry-optout", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence pack items mention telemetry, usage tracking, opt-out settings, or privacy controls of this kind; this is an applicable axis for a SaaS CRM platform but nothing documents it.", "evidenceIds": [] }, { "productId": "attio", "storyId": "reports-dashboards", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Attio's native reporting platform lets users build live dashboards with multiple chart types (line, bar, geospatial) and combine visualizations for team collaboration, plus SQL query access for deeper analysis—directly enabling in-app reporting instead of spreadsheet exports. Missing for 10: no explicit pipeline/conversion-metric examples, no independent/hands-on corroboration of dashboard-building in practice.", "evidenceIds": [ "attio-docs-11", "attio-docs-20", "attio-docs-21", "attio-docs-43", "attio-docs-4" ] }, { "productId": "attio", "storyId": "revenue-forecasting", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Attio's Deal object provides pipeline data (stage, value, close date) and its reporting engine supports custom visualizations/analytics, which could underpin revenue forecasting, but no evidence explicitly documents a forecasting feature, stage-probability weighting, or a forecast report type. Missing for 10: explicit probability-weighted forecast feature, documented forecast reports/dashboards, and any customer/independent evidence of forecasting use.", "evidenceIds": [ "attio-docs-13", "attio-docs-14", "attio-docs-30", "attio-docs-11", "attio-docs-20", "attio-docs-21" ] }, { "productId": "attio", "storyId": "spreadsheet-import", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Marketing chat snippets mention that Attio will 'map it during onboarding' and provide a 'migration checklist' for bringing over existing spreadsheet/deal data, implying some import support, but there is no actual product documentation describing a CSV/spreadsheet import tool, field-mapping UI, validation rules, or safeguards against silently dropped rows. missing for 10: dedicated import/CSV mapping feature docs, validation/error-reporting behavior, evidence of row-loss prevention, independent user confirmation of successful large imports.", "evidenceIds": [ "attio-docs-15", "attio-docs-38", "attio-docs-44", "attio-docs-39" ] }, { "productId": "attio", "storyId": "two-way-email-sync", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence pack shows general contact syncing/enrichment claims and API/webhook infrastructure, but no mention of Gmail or Outlook two-way email sync or automatic email logging to records anywhere in the docs or probes.", "evidenceIds": [] }, { "productId": "attio", "storyId": "visual-pipeline-stages", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Attio ships a native Deal object for pipeline tracking (attio-docs-13,30,33), supports kanban board views alongside tables (attio-docs-34), and lets users customize fields/stages via custom objects and lists that model business processes (attio-docs-8,29,46). This directly matches the pipeline-with-customizable-stages story, though evidence never explicitly names 'drag-and-drop' interaction or shows independent hands-on confirmation. Missing for 10: explicit drag-and-drop UI documentation, independent/third-party hands-on review confirming the kanban interaction works as described.", "evidenceIds": [ "attio-docs-13", "attio-docs-30", "attio-docs-33", "attio-docs-34", "attio-docs-29", "attio-docs-46", "attio-docs-8" ] }, { "productId": "attio", "storyId": "workflow-builder", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Attio documents workflows platform with triggers (e.g., 'when a new deal is created') and automated agents that route leads, score leads, and update records, plus webhooks for real-time notifications and REST API for record updates — covering the core story elements. However, evidence is mostly marketing-page descriptions rather than detailed workflow-builder documentation showing task creation or multi-step conditional logic, and no independent/hands-on confirmation of reliability. Missing for 10: detailed docs on workflow builder UI/logic, explicit task-creation trigger actions, and independent verification of automation reliability.", "evidenceIds": [ "attio-docs-17", "attio-docs-18", "attio-docs-19", "attio-docs-37", "attio-docs-5", "attio-docs-28", "attio-docs-10" ] }, { "productId": "hubspot", "storyId": "agent-enriches-lead", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "HubSpot's REST API supports creating contact records (POST /crm/v3/objects/contacts) and companies/custom objects can be created and updated via the same object APIs, and the official MCP server explicitly grants 'read and write access to your HubSpot CRM data — contacts, deals, engagements, and more' to any MCP-compatible agent, so the create+enrich portions of the story are documented. However, there is no evidence of an owner-assignment field/endpoint being called out, nor any end-to-end example showing an agent orchestrating create→enrich→assign-owner in one flow. Missing for 10: explicit owner-assignment API/MCP action, a documented end-to-end lead-enrichment workflow example, and independent/hands-on confirmation of the MCP server performing writes successfully.", "evidenceIds": [ "hubspot-docs-31", "hubspot-docs-5", "hubspot-docs-30", "hubspot-docs-40", "hubspot-docs-17", "hubspot-docs-18", "hubspot-docs-32", "hubspot-probe-4" ] }, { "productId": "hubspot", "storyId": "agent-preps-account-brief", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "HubSpot's official MCP server explicitly grants read access to contacts, deals, and engagements, and its CRM APIs (contacts, custom objects, account info) plus connected-email logging supply the underlying data (open deals, emails, history) needed for such a brief; this directly supports an AI-native agent pulling account context via MCP or API before a meeting. However, there's no documented end-to-end 'account brief' workflow or example, no explicit deals/engagements API doc cited, and no independent/hands-on evidence the MCP server actually performs this compilation reliably. Missing for 10: a demonstrated brief-generation example, explicit deals/engagements endpoint docs, and third-party corroboration of MCP data-pull quality.", "evidenceIds": [ "hubspot-docs-5", "hubspot-docs-30", "hubspot-docs-40", "hubspot-docs-2", "hubspot-docs-13", "hubspot-docs-57", "hubspot-probe-4" ] }, { "productId": "hubspot", "storyId": "agent-updates-deal-stages", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "HubSpot ships both a native AI capability ('smart deal progression keeps deals moving after every call, with next steps handled for them' and 'Approve automatic CRM updates and follow-up drafts after every meeting') and an official MCP server giving 'any MCP-compatible AI tool or agent secure read and write access to your HubSpot CRM data — contacts, deals, engagements, and more,' directly matching the story of an agent updating deal stages/next steps from email and meeting signals via API or MCP. Missing for 10: explicit deals-object API endpoint documentation (evidence only details contacts/custom-object endpoints), and independent hands-on confirmation that MCP-driven deal-stage updates work as advertised in practice.", "evidenceIds": [ "hubspot-docs-5", "hubspot-docs-14", "hubspot-docs-22", "hubspot-docs-23", "hubspot-docs-30", "hubspot-probe-4" ] }, { "productId": "hubspot", "storyId": "agentic-agent-docs", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "HubSpot's docs explicitly state that agents can 'Fetch the complete documentation index at: https://developers.hubspot.com/docs/llms.txt' and that any doc page can be turned into markdown by appending .md (corroborated by real evidence sources that are themselves .md URLs, e.g. hubspot-docs-47, hubspot-docs-57). However, independent probes found the top-level https://developers.hubspot.com/llms.txt and https://developers.hubspot.com/docs.md both return 404, raising doubt about the accessibility/discoverability of the claimed agent-oriented entry points at the paths most agents would guess. Missing for 10: a probe confirming the specific /docs/llms.txt path actually resolves, and clearer top-level discoverability (root llms.txt) rather than only nested doc-page .md conversion.", "evidenceIds": [ "hubspot-supp-openapi-spec", "hubspot-probe-1", "hubspot-probe-2", "hubspot-docs-57" ] }, { "productId": "hubspot", "storyId": "agentic-ai-insights", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "HubSpot ships Breeze AI features embedded in the product: natural-language report generation ('describe the report you need in plain language, and HubSpot will build it from your actual data'), AI agents for prospecting/deal progression that surface insights and next-step suggestions from CRM data, and content-generation AI. These are native, in-product AI insight/suggestion features rather than external tooling. missing for 10: independent hands-on validation of insight quality/accuracy, and deeper detail on how proactive/contextual the insights are beyond marketing copy.", "evidenceIds": [ "hubspot-docs-35", "hubspot-docs-50", "hubspot-docs-14", "hubspot-docs-22", "hubspot-docs-23", "hubspot-docs-56", "hubspot-docs-7" ] }, { "productId": "hubspot", "storyId": "agentic-autonomous-automation", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "HubSpot ships native Workflows automation that runs processes autonomously on CRM triggers, plus AI agents (e.g., the Prospecting agent) explicitly described as watching accounts for signals and reaching out automatically, and smart deal progression handling next steps without user action — all clearly background/autonomous behaviors. Webhooks and the CRM API further support event-driven automation an AI-native user could wire up. Missing for 10: independent/hands-on verification that these agents run reliably unattended over time, and deeper docs on scheduling/trigger configuration for developer-built autonomous flows.", "evidenceIds": [ "hubspot-docs-12", "hubspot-docs-45", "hubspot-docs-14", "hubspot-docs-22", "hubspot-docs-23", "hubspot-docs-4", "hubspot-docs-56" ] }, { "productId": "hubspot", "storyId": "agentic-builtin-assistant", "verdict": "partial", "quality": 7, "confidence": "medium", "rationale": "HubSpot documents built-in AI agents (Breeze Assistant, Prospecting agent, campaign-planning agent) that can autonomously watch accounts, draft follow-ups, build reports from plain-language requests, and generate content — a clear built-in delegate-to-AI-assistant capability (hubspot-docs-14, 22, 23, 35, 50, 56). However, all evidence is vendor-authored marketing/docs pages with no independent or hands-on corroboration of these agents actually performing delegated tasks reliably. Missing for 10: independent/hands-on verification of the AI assistant executing delegated tasks, and detail on scope/limits of autonomy.", "evidenceIds": [ "hubspot-docs-14", "hubspot-docs-22", "hubspot-docs-23", "hubspot-docs-35", "hubspot-docs-50", "hubspot-docs-56", "hubspot-docs-39" ] }, { "productId": "hubspot", "storyId": "agentic-headless", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "HubSpot exposes a CLI (`npm install -g @hubspot/cli && hs init`) and a full REST API (contacts, custom objects, webhooks) plus a machine-readable OpenAPI spec, all of which can be scripted and run non-interactively in CI/automation pipelines. However, there is no explicit documentation or example showing CI/CD integration, headless CLI usage in pipelines, or automated testing workflows tailored to AI-native/agentic CI use. missing for 10: explicit CI/CD pipeline examples, documented headless/non-interactive CLI flags, and independent evidence of running HubSpot automation in a build pipeline.", "evidenceIds": [ "hubspot-docs-1", "hubspot-docs-16", "hubspot-docs-2", "hubspot-docs-4", "hubspot-supp-openapi-spec", "hubspot-probe-4" ] }, { "productId": "hubspot", "storyId": "agentic-mcp-client", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "All MCP evidence describes HubSpot shipping its own MCP server so external AI tools/agents can call into HubSpot's CRM and developer platform (hubspot-docs-5, hubspot-docs-30, hubspot-docs-40, hubspot-docs-6, hubspot-docs-24, hubspot-probe-4) — i.e., HubSpot as the MCP server, not as an MCP client. The story asks the reverse: can a user plug external MCP servers into HubSpot so HubSpot's own AI features can use their tools. No evidence shows HubSpot's Breeze/AI agents consuming or configuring third-party MCP servers as tool sources.", "evidenceIds": [ "hubspot-docs-5", "hubspot-docs-30", "hubspot-docs-40", "hubspot-docs-6", "hubspot-docs-24", "hubspot-probe-4" ] }, { "productId": "hubspot", "storyId": "agentic-mcp-server", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "HubSpot documents an official MCP server enabling MCP-compatible AI tools/agents to get secure read/write access to CRM data, plus a separate Developer MCP server for agentic dev tools, confirmed by probe-4 finding the docs page live. Missing for 10: independent/hands-on third-party corroboration of the MCP server working in practice, and no llms.txt/openapi discovery worked at the root domain (probes 1-3 failed), though the endpoint itself is documented.", "evidenceIds": [ "hubspot-docs-5", "hubspot-docs-6", "hubspot-docs-24", "hubspot-docs-30", "hubspot-docs-40", "hubspot-probe-4" ] }, { "productId": "hubspot", "storyId": "agentic-nl-commands", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "HubSpot's Breeze AI features let users describe reports in plain language and plan campaigns from a single goal, and its MCP server exposes CRM data to natural-language-driven AI agents — this is genuine natural-language operation of parts of the product. However, coverage is limited to specific modules (reporting, campaigns, prospecting) rather than the whole platform, and there's no independent/hands-on evidence corroborating how well these NL commands work in practice. Missing for 10: broad NL control across core CRM workflows (contacts, deals, workflows) beyond reporting/campaigns, and independent verification of NL command reliability.", "evidenceIds": [ "hubspot-docs-35", "hubspot-docs-50", "hubspot-docs-15", "hubspot-docs-56", "hubspot-docs-5", "hubspot-docs-40" ] }, { "productId": "hubspot", "storyId": "agentic-official-cli", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "HubSpot ships an official CLI (`npm install -g @hubspot/cli && hs init`), documented with install/auth/build steps, and it's a first-class tool used to scaffold and manage projects, including agentic development flows via the Developer MCP server which itself is CLI-based. Missing for 10: independent/hands-on developer corroboration of CLI usage and depth of CLI command coverage beyond install/init.", "evidenceIds": [ "hubspot-docs-1", "hubspot-docs-16", "hubspot-docs-24", "hubspot-docs-6" ] }, { "productId": "hubspot", "storyId": "agentic-public-api", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "HubSpot publishes extensive REST API documentation (CRM objects, contacts, custom objects, webhooks, account info) with concrete endpoint examples (e.g. POST /crm/v3/objects/contacts), a CLI, versioning/deprecation policies, and inline OpenAPI specs per endpoint, plus llms.txt/markdown-friendly docs for agent consumption. missing for 10: independent/hands-on developer corroboration that the public API works as documented in practice, and the root-level llms.txt/openapi probes returned 404 (though a nested docs.md/llms.txt path is referenced in supp evidence), leaving some ambiguity about universal machine-readability.", "evidenceIds": [ "hubspot-docs-31", "hubspot-docs-2", "hubspot-docs-18", "hubspot-docs-57", "hubspot-supp-api-versioning", "hubspot-supp-deprecation-policy", "hubspot-supp-openapi-spec", "hubspot-probe-1", "hubspot-probe-3" ] }, { "productId": "hubspot", "storyId": "agentic-scoped-keys", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack documents HubSpot's MCP server giving broad 'secure read and write access' to CRM data and general account/API mechanics, but nowhere describes scoped, least-privilege API credentials (e.g., granular OAuth scopes or private-app permission scoping) that an AI-native user could issue specifically for an agent.", "evidenceIds": [ "hubspot-docs-5", "hubspot-docs-30", "hubspot-docs-40", "hubspot-docs-47" ] }, { "productId": "hubspot", "storyId": "agentic-sdks", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack documents HubSpot's REST APIs, an OpenAPI-spec-per-endpoint, a CLI (@hubspot/cli), and MCP servers, but nowhere mentions official client SDKs/libraries (e.g., Node.js, Python, PHP, Ruby SDKs) that an AI-native developer would build against. Missing for 10: any documentation of official SDK packages, language coverage, or SDK release/versioning cadence.", "evidenceIds": [ "hubspot-docs-1", "hubspot-docs-16", "hubspot-supp-openapi-spec", "hubspot-supp-api-versioning" ] }, { "productId": "hubspot", "storyId": "agentic-webhooks", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "HubSpot documents a dedicated webhooks journal API allowing third-party integrators to subscribe to real-time events, retrieve historical event data, and manage CRM object snapshots, directly matching the story. Missing for 10: independent/hands-on corroboration of webhook subscription reliability and no explicit mention of AI-agent-specific webhook consumption patterns.", "evidenceIds": [ "hubspot-docs-4" ] }, { "productId": "hubspot", "storyId": "api-interactive-docs", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "HubSpot publishes machine-readable API reference pages (OpenAPI specs, curl/code examples like the contacts POST endpoint, and agent-readable .md/llms.txt paths per hubspot-supp-openapi-spec, hubspot-docs-31, hubspot-docs-57), showing a structured API reference exists. However, there's no evidence of an interactive 'try it' console or runnable execution within the docs, and probes for llms.txt/openapi.json at expected root paths returned 404s, suggesting the interactive/agent-discoverable surface is inconsistent or non-standard. Missing for 10: explicit interactive 'run this call' sandbox UI, confirmation that root-level llms.txt/openapi.json resolve, and independent corroboration of hands-on interactivity.", "evidenceIds": [ "hubspot-supp-openapi-spec", "hubspot-docs-57", "hubspot-docs-31", "hubspot-probe-1", "hubspot-probe-3" ] }, { "productId": "hubspot", "storyId": "api-machine-spec", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "First-party docs show each API reference page embeds a machine-readable OpenAPI 3.0.1 spec (e.g., specs/2026-09/account-account-info-v2026-09.json) and an agent-readable index at /docs/llms.txt, confirming a real OpenAPI-based spec exists per endpoint. However, independent probes for a single top-level downloadable spec (openapi.json, swagger.json, llms.txt at root) all returned 404, suggesting there is no one-shot full-API spec download — only per-endpoint fragments discoverable via docs navigation. Missing for 10: a consolidated single-file OpenAPI document confirmed downloadable, and independent/community verification of successfully fetching it.", "evidenceIds": [ "hubspot-supp-openapi-spec", "hubspot-probe-1", "hubspot-probe-2", "hubspot-probe-3" ] }, { "productId": "hubspot", "storyId": "api-sandbox", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "HubSpot explicitly documents the ability to create up to 10 free test/sandbox accounts to test apps and integrations without affecting real production data, directly matching the story. Missing for 10: no independent/hands-on confirmation of sandbox fidelity or limitations, and no detail on how closely sandbox mirrors production data/schema.", "evidenceIds": [ "hubspot-docs-47" ] }, { "productId": "hubspot", "storyId": "api-versioning-policy", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "HubSpot documents a date-based API versioning scheme (e.g. /crm/2026-09/) where prior versions continue working until an announced end-of-life date, plus a maintained 'Sunsetted and deprecated APIs' page with per-API dates/migration targets and a commitment to announce changes via the Developer Changelog with ample notice. Each endpoint also publishes a machine-readable OpenAPI spec inline, reinforcing an AI-native/versioned-API workflow. Missing for 10: independent/third-party corroboration of the deprecation policy being honored in practice, and the top-level llms.txt/openapi.json probes returned 404 at some paths, slightly undercutting full agent-discoverability claims.", "evidenceIds": [ "hubspot-supp-api-versioning", "hubspot-supp-deprecation-policy", "hubspot-supp-openapi-spec" ] }, { "productId": "hubspot", "storyId": "auto-enrichment", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack covers CRM data unification, deduplication, import, and AI agents, but contains no mention of automatic firmographic/contact enrichment (e.g., Breeze Intelligence or third-party data append) for contact and company records.", "evidenceIds": [] }, { "productId": "hubspot", "storyId": "automation-bulk-operations", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "HubSpot's docs confirm batch/bulk capabilities such as retrieving custom objects in batches, bulk import of multiple object records, and CRM-wide sync/dedup tools, and its MCP server gives AI agents read/write access to CRM data. However, there's no explicit documentation of bulk create/update/delete operations being exposed specifically for AI-agent workflows (e.g., no mention of batch endpoints for contacts/deals via the MCP server) and no independent verification of large-scale bulk performance. Missing for 10: explicit agent-facing bulk write/delete API examples, evidence of batch limits/performance, and independent/hands-on confirmation of bulk operations at scale.", "evidenceIds": [ "hubspot-docs-3", "hubspot-docs-8", "hubspot-docs-38", "hubspot-docs-5", "hubspot-docs-40", "hubspot-docs-10", "hubspot-docs-11" ] }, { "productId": "hubspot", "storyId": "automation-rules-engine", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "HubSpot Workflows (hubspot-docs-12/45) let users define automation rules triggered by events (contact property changes, form submissions, deal stage changes, etc.), and this is complemented by webhooks/event subscription APIs (hubspot-docs-4) for programmatic event-driven automation, plus AI agents (Prospecting agent, deal progression) that act automatically on signals (hubspot-docs-14, hubspot-docs-22, hubspot-docs-23). missing for 10: no detailed documentation of conditional/branching logic specifics or independent hands-on verification of workflow trigger reliability.", "evidenceIds": [ "hubspot-docs-12", "hubspot-docs-45", "hubspot-docs-4", "hubspot-docs-14", "hubspot-docs-22", "hubspot-docs-23" ] }, { "productId": "hubspot", "storyId": "automation-scheduled-jobs", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "HubSpot's Workflows feature lets users automate processes (hubspot-docs-12/45), which is the closest capability to scheduling recurring jobs, but the evidence pack gives no detail on scheduling logic, cron-like recurrence, or how an AI-native user (via MCP/API) would configure or trigger recurring workflows programmatically. Missing for 10: documentation on recurring/scheduled triggers, API/MCP support for creating or managing workflow schedules, and evidence of AI-agent-initiated recurring automation.", "evidenceIds": [ "hubspot-docs-12", "hubspot-docs-45" ] }, { "productId": "hubspot", "storyId": "automation-versioned-workflows", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence confirms HubSpot workflows exist for automation (hubspot-docs-12/45), and general API versioning/deprecation policies are documented, but nothing in the pack describes workflow-level version history, change review, or rollback capability for automations themselves. Missing for 10: workflow revision history UI, diff/review of automation changes, and rollback-to-previous-version functionality.", "evidenceIds": [ "hubspot-docs-12", "hubspot-docs-45", "hubspot-supp-api-versioning" ] }, { "productId": "hubspot", "storyId": "bidirectional-sync-api", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Evidence shows CRUD and batch operations for contacts/custom objects, plus a webhooks journal API for real-time and historical event subscription (a change-detection mechanism), supporting bidirectional sync at scale. However, no evidence cites documented rate limits, and there's no explicit mention of 'upsert' semantics (e.g., idProperty-based upsert) in the API docs provided. Missing for 10: documented rate-limit numbers/headers, explicit upsert endpoint documentation, and independent/hands-on confirmation of scale performance.", "evidenceIds": [ "hubspot-docs-3", "hubspot-docs-4", "hubspot-docs-17", "hubspot-docs-18", "hubspot-docs-32" ] }, { "productId": "hubspot", "storyId": "calendar-meeting-sync", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack covers email inbox connection, contact/deal APIs, imports, and dedup, but nowhere documents a calendar-sync feature that logs meetings onto contact/deal timelines. Without explicit evidence of calendar integration, this applicable CRM capability cannot be credited.", "evidenceIds": [] }, { "productId": "hubspot", "storyId": "contact-company-records", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "HubSpot's docs confirm contacts and companies exist as CRM records with dedup by domain (companies) and email (contacts), the ability to import and associate records across objects (contacts, companies, deals), and email/replies being logged to the CRM — indicating activity capture on records. However, no direct evidence describes a company-record API or a rendered 'activity timeline' UI feature explicitly, only inferred from email-logging and engagement mentions in MCP docs. Missing for 10: explicit documentation of the company object API/endpoints, and explicit description of a unified activity timeline UI on contact/company records.", "evidenceIds": [ "hubspot-docs-8", "hubspot-docs-10", "hubspot-docs-13", "hubspot-docs-21", "hubspot-docs-31", "hubspot-docs-40" ] }, { "productId": "hubspot", "storyId": "crm-migration", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "HubSpot documents import tools for multiple objects (companies, deals, activities, associations), self-service transfer/audit-and-sync for new customers, and automatic/manual deduplication using email/domain or record IDs, which together support migrating records and relationships from another CRM. However, evidence does not confirm preservation of 'owners' (rep/user assignment mapping) during migration, nor explicit historical activity/timeline preservation beyond basic activities import, and there's no independent/hands-on account confirming migration fidelity. missing for 10: evidence of owner/user mapping during import, confirmation of full historical timeline/audit trail preservation, and independent verification of migration outcomes.", "evidenceIds": [ "hubspot-docs-8", "hubspot-docs-9", "hubspot-docs-10", "hubspot-docs-11", "hubspot-docs-27", "hubspot-docs-38" ] }, { "productId": "hubspot", "storyId": "custom-fields-views", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence covers custom objects via the developer API, reporting dashboards with filters, and workflow automation, but there is no evidence of an ops user creating custom fields/properties or building filtered, sorted, shared record list views through the UI without engineering/admin involvement — the closest material (custom objects API, reporting dashboard filters) targets developers or reporting, not object-view customization.", "evidenceIds": [ "hubspot-docs-18", "hubspot-docs-41", "hubspot-docs-42", "hubspot-docs-49" ] }, { "productId": "hubspot", "storyId": "custom-objects", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "HubSpot's docs explicitly cover custom objects: creating/updating records via the custom objects API and retrieving them individually or in batch, letting developers extend beyond contacts/companies/deals. Evidence also shows import/dedup/association support extending to custom objects. Missing for 10: explicit documentation of defining custom fields/properties and relationship/association types on custom objects, and independent hands-on developer corroboration beyond HubSpot's own docs.", "evidenceIds": [ "hubspot-docs-18", "hubspot-docs-3", "hubspot-docs-32", "hubspot-docs-41", "hubspot-docs-11" ] }, { "productId": "hubspot", "storyId": "dedupe-merge-records", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "HubSpot docs confirm automatic deduplication (by email for contacts, domain for companies) plus manual merge via record IDs across contacts, companies, deals, tickets and other objects, directly addressing duplicate detection and merging. Missing for 10: explicit documentation confirming no data loss during merge (e.g., how conflicting field values are preserved) and independent/hands-on confirmation of merge behavior beyond vendor docs.", "evidenceIds": [ "hubspot-docs-10", "hubspot-docs-11", "hubspot-docs-20", "hubspot-docs-48" ] }, { "productId": "hubspot", "storyId": "email-templates-sequences", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "HubSpot docs clearly document connecting an inbox to send one-to-one emails from the CRM and a dedicated sequences tool for sending multi-step, timed email sequences to prospects, both directly accessible from within the CRM. This directly matches the ops persona's need for templated/sequence outreach. Missing for 10: no independent/hands-on corroboration of the sequences UX and no explicit mention of email templates feature alongside sequences.", "evidenceIds": [ "hubspot-docs-13", "hubspot-docs-37", "hubspot-docs-44", "hubspot-docs-52", "hubspot-docs-21" ] }, { "productId": "hubspot", "storyId": "fast-time-to-pipeline", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "HubSpot documents a self-service path — free CRM signup with no expiration, self-service data transfer/import for multiple objects, automatic deduplication, and workflow creation — all achievable without a partner (hubspot-docs-7,9,25,27,29,8,10,12). However, no evidence quantifies time-to-value or confirms a real founder can reach a 'working pipeline with real data' inside one hour; community commentary only addresses marketing/product perception, not onboarding speed. Missing for 10: a documented or independent time-to-pipeline benchmark, and hands-on confirmation that import+dedup+workflow setup is fast enough for non-technical founders without support.", "evidenceIds": [ "hubspot-docs-7", "hubspot-docs-9", "hubspot-docs-25", "hubspot-docs-27", "hubspot-docs-8", "hubspot-docs-10", "hubspot-docs-12", "hubspot-docs-55" ] }, { "productId": "hubspot", "storyId": "lead-assignment-routing", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "HubSpot's documentation confirms a general-purpose workflow automation engine ('Create workflows in HubSpot to automate your processes') that is the underlying mechanism used for lead routing, but the evidence pack contains no explicit mention of assignment rules, lead routing, or round-robin distribution features. Missing for 10: explicit documentation of assignment rules, round-robin lead distribution, or lead-routing-specific workflow actions, and any independent/hands-on confirmation these work as described.", "evidenceIds": [ "hubspot-docs-12", "hubspot-docs-45" ] }, { "productId": "hubspot", "storyId": "marketplace-integrations", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack covers HubSpot's CRM APIs, CLI, MCP servers, import tools, and AI features, but contains no mention of an App Marketplace or prebuilt one-click integrations for Slack, support desks, marketing tools, or data warehouses. While this axis clearly applies to a SaaS platform like HubSpot, there is no evidence in the pack that such a marketplace or prebuilt connector catalog exists or is documented.", "evidenceIds": [] }, { "productId": "hubspot", "storyId": "multiple-pipelines", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "The evidence pack covers CRM data, API objects, MCP servers, workflows, reporting, and deduplication, but contains no mention of deal pipelines, multiple pipeline configuration, or custom stage sets per pipeline/product — the core capability the story asks about.", "evidenceIds": [] }, { "productId": "hubspot", "storyId": "openness-api-parity", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "HubSpot documents a broad, versioned REST API covering core CRM objects, custom objects, contacts, account info, and webhooks (hubspot-docs-2/3/4/17/18/31/32/41/57, hubspot-supp-api-versioning, hubspot-supp-openapi-spec), suggesting solid API/UI parity for core CRM functions. However, there's no evidence that newer UI-surfaced capabilities (Breeze AI reporting builder, prospecting/deal agents, sequences, workflow builder) are exposed via API, and basic agent-discoverability probes for llms.txt/docs.md/top-level openapi.json all 404 (hubspot-probe-1/2/3), undercutting a claim of full UI-API parity for AI-native consumption. missing for 10: documented API endpoints for AI agent features (prospecting agent, Breeze reporting, sequences, workflows), a working top-level machine-readable spec/llms.txt, and independent confirmation of full UI-API feature parity.", "evidenceIds": [ "hubspot-docs-2", "hubspot-docs-3", "hubspot-docs-4", "hubspot-docs-17", "hubspot-docs-31", "hubspot-docs-41", "hubspot-docs-57", "hubspot-supp-api-versioning", "hubspot-supp-openapi-spec", "hubspot-probe-1", "hubspot-probe-2", "hubspot-probe-3", "hubspot-docs-14", "hubspot-docs-35", "hubspot-docs-52" ] }, { "productId": "hubspot", "storyId": "openness-full-export", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "HubSpot's CRM API lets users retrieve contacts and custom objects individually or in batches, and the 'import-and-export' knowledge base implies an export path, but no evidence explicitly documents a full-account data export tool, supported open formats (CSV/JSON dump), or a process for fully leaving with all data intact. The self-service transfer feature described (hubspot-docs-9/27/29) is inbound-only (importing into HubSpot from elsewhere), not outbound.\n\nmissing for 10: dedicated bulk 'export all data' feature, explicit open-format export documentation (CSV/JSON), evidence of account closure/data portability workflow, independent confirmation of successful full data export.", "evidenceIds": [ "hubspot-docs-2", "hubspot-docs-3", "hubspot-docs-8", "hubspot-docs-9", "hubspot-docs-17", "hubspot-docs-18", "hubspot-docs-38" ] }, { "productId": "hubspot", "storyId": "openness-open-license", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "HubSpot is a closed-source SaaS CRM platform; source code availability under an open license is not a plausible axis for this kind of product—no open-source repository or licensing claim exists in the evidence pack.", "evidenceIds": [] }, { "productId": "hubspot", "storyId": "openness-self-host", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "HubSpot is a SaaS-only CRM with no evidence of any self-hostable/open-source core; all docs describe cloud APIs, CLI, and MCP integration against hosted HubSpot accounts, not a deployable open-source package.", "evidenceIds": [] }, { "productId": "hubspot", "storyId": "privacy-data-residency", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack addresses data residency, regional data centers, or storage location options; all citations concern APIs, MCP, CRM features, imports, and general commentary. Missing for 10: any documentation of EU/US data hosting options, residency controls, or region selection for data storage.", "evidenceIds": [] }, { "productId": "hubspot", "storyId": "privacy-no-training", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence pack item addresses AI training data usage, opt-out controls, or privacy policy language about AI model training; the evidence covers unrelated product features (CRM, MCP, reporting, workflows).", "evidenceIds": [] }, { "productId": "hubspot", "storyId": "privacy-retention-controls", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence pack items address data retention policies, GDPR/CCPA deletion requests, data export controls, or configurable retention windows for HubSpot CRM/AI data — the story is applicable to a CRM/AI platform but unevidenced here.", "evidenceIds": [] }, { "productId": "hubspot", "storyId": "privacy-telemetry-optout", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack addresses telemetry or usage-tracking opt-out settings for HubSpot; the docs cover CRM, API, MCP, and product features but nothing about privacy/telemetry controls.", "evidenceIds": [] }, { "productId": "hubspot", "storyId": "reports-dashboards", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "HubSpot's reporting product explicitly supports building custom dashboards/reports on pipeline (sales reports, deal stages), activity (rep performance, coaching insights), and conversion, combining multiple reports per role, with natural-language report building via Breeze Assistant — all within the platform, explicitly framed against spreadsheets ('Your data deserves better than spreadsheets'). Missing for 10: independent/hands-on user corroboration of dashboard-building experience and no detail on conversion-funnel-specific reporting depth.", "evidenceIds": [ "hubspot-docs-34", "hubspot-docs-35", "hubspot-docs-42", "hubspot-docs-43", "hubspot-docs-49", "hubspot-docs-50", "hubspot-docs-51", "hubspot-docs-59", "hubspot-docs-19" ] }, { "productId": "hubspot", "storyId": "revenue-forecasting", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack shows generic sales reporting/dashboards (pre-built reports, custom dashboards, deal-related analytics) but nothing documents a dedicated pipeline forecasting feature that combines deal value, stage probability, and close dates into a revenue forecast. Without that specific capability being evidenced, this applicable CRM axis is unsupported.", "evidenceIds": [ "hubspot-docs-36", "hubspot-docs-43", "hubspot-docs-49", "hubspot-docs-59" ] }, { "productId": "hubspot", "storyId": "spreadsheet-import", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "HubSpot documents import for multiple objects (contacts, companies, deals) with association mapping and automatic/manual deduplication to prevent duplicate rows, plus self-service transfer/audit tooling for new users. However, the evidence does not describe field-mapping UI specifics, explicit validation/error-row reporting, or confirmation that rows are never silently dropped during import. missing for 10: documented field-mapping interface details, explicit row-level validation/error reporting during import, independent/hands-on confirmation that no rows are silently lost.", "evidenceIds": [ "hubspot-docs-8", "hubspot-docs-9", "hubspot-docs-10", "hubspot-docs-11", "hubspot-docs-27" ] }, { "productId": "hubspot", "storyId": "two-way-email-sync", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Docs confirm connecting an individual work email (Gmail/Outlook) to log replies and enable one-to-one email sync to CRM records, which addresses the core of the story. However, evidence doesn't explicitly confirm two-way sync (both sending and receiving auto-logged to right records) or details on matching/logging accuracy, contact-level automation nuances, or independent/hands-on verification. missing for 10: explicit two-way sync confirmation, details on automatic record-matching logic, independent/hands-on verification of reliability.", "evidenceIds": [ "hubspot-docs-13", "hubspot-docs-21", "hubspot-docs-46", "hubspot-docs-54" ] }, { "productId": "hubspot", "storyId": "visual-pipeline-stages", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack contains extensive HubSpot CRM/API/reporting docs but never describes a visual deal pipeline, customizable stages, or drag-and-drop pipeline UI — only generic references to 'deals' as an object type in the MCP/CRM API docs. Since this is a well-known and applicable CRM capability but no supporting evidence is present in the pack, it must be scored as none rather than assumed.", "evidenceIds": [ "hubspot-docs-5", "hubspot-docs-40", "hubspot-docs-7" ] }, { "productId": "hubspot", "storyId": "workflow-builder", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "HubSpot's Workflows product explicitly supports trigger-based automation to update records, create tasks, and send notifications, and this is corroborated by the broader CRM automation ecosystem (deduplication, email sync, sequences) that workflows commonly integrate with. Missing for 10: no independent/hands-on account of building a multi-action trigger workflow (task+notification+record update chain), and docs excerpts are terse marketing-style snippets rather than detailed workflow-builder documentation.", "evidenceIds": [ "hubspot-docs-12", "hubspot-docs-45", "hubspot-docs-10", "hubspot-docs-37" ] }, { "productId": "salesforce", "storyId": "agent-enriches-lead", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Salesforce exposes a documented Data API/CLI (sf data query, sf agent create) and an official MCP server (salesforce-probe-3), and the CRM data model explicitly includes Lead/Account/Contact/Opportunity objects (salesforce-docs-22), which together make an end-to-end lead-enrichment workflow plausible. However, there is no concrete documentation or example showing an agent actually creating a lead, filling company data, and assigning an owner via the API or MCP server in one flow. Missing for 10: a worked example or docs of the specific lead-create+enrich+assign-owner workflow via API/MCP, and any hands-on/independent confirmation it works end-to-end.", "evidenceIds": [ "salesforce-probe-3", "salesforce-probe-4", "salesforce-docs-22", "salesforce-gh-3", "salesforce-gh-8" ] }, { "productId": "salesforce", "storyId": "agent-preps-account-brief", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Salesforce exposes CRM data (accounts, opportunities, emails, activity history) via APIs and has an official MCP server (salesforcecli/mcp) plus a general-purpose CLI capable of data queries, giving an agent plumbing to assemble an account brief. However, there's no documented example, template, or first-party workflow specifically compiling 'open deals + recent emails + history' into a pre-meeting brief — this is inferred capability rather than demonstrated. Missing for 10: a concrete first-party or independent example of an agent generating a pre-meeting account brief combining deals/emails/history, and documentation of the specific API/MCP calls needed to pull email history alongside opportunity and activity data.", "evidenceIds": [ "salesforce-probe-3", "salesforce-probe-4", "salesforce-gh-3", "salesforce-docs-8", "salesforce-docs-22", "salesforce-docs-7" ] }, { "productId": "salesforce", "storyId": "agent-updates-deal-stages", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Salesforce documents an official API/CLI (salesforce-probe-4, salesforce-docs-7) and an official MCP server (salesforce-probe-3, salesforce-docs-28) that can plug into Agentforce, plus Agentforce agents explicitly listed as 'Updating opportunity' (salesforce-docs-31) and automatic email/event syncing (salesforce-docs-8). However, no concrete documentation ties these together into the specific workflow of an agent parsing email/meeting signals to update deal stage and next-step fields end-to-end. Missing for 10: explicit docs/demo of email-or-meeting-signal-driven stage/next-step updates via API or MCP, and independent/hands-on confirmation this works as described.", "evidenceIds": [ "salesforce-probe-3", "salesforce-docs-28", "salesforce-docs-31", "salesforce-docs-8", "salesforce-docs-7", "salesforce-probe-4" ] }, { "productId": "salesforce", "storyId": "agentic-agent-docs", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Direct probe evidence confirms an llms.txt file exists at https://www.salesforce.com/llms.txt returning HTTP 200 with structured agent-oriented content links, and this is corroborated by an official MCP server and CLI ecosystem that agents can also use. Missing for 10: independent third-party confirmation that agents actively consume this llms.txt successfully, and more comprehensive agent-oriented documentation beyond the single probed file.", "evidenceIds": [ "salesforce-probe-1", "salesforce-probe-3", "salesforce-probe-4" ] }, { "productId": "salesforce", "storyId": "agentic-ai-insights", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Sales Cloud ships built-in AI features like lead scoring, predictive forecasting, and AI-powered pipeline insights directly in the CRM UI, backed by named customer results (e.g., Crexi saving 5 hours/day with Sales AI). Missing for 10: independent hands-on review specifically validating insight quality/accuracy, and more detail on how insights surface in-product beyond marketing copy.", "evidenceIds": [ "salesforce-docs-2", "salesforce-docs-3", "salesforce-docs-10", "salesforce-docs-16", "salesforce-docs-17", "salesforce-docs-5" ] }, { "productId": "salesforce", "storyId": "agentic-autonomous-automation", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Salesforce documents Agentforce agents that run 24/7 autonomously across the sales cycle (prospecting to close), with CLI tooling (sf agent create, sf agent activate) and Agent Builder for configuring automated logic, access controls, and integrations with Flows/Apex/MuleSoft. This directly matches background autonomous automation for an AI-native user. missing for 10: independent/hands-on verification that agents genuinely run unattended in production, and more detail on monitoring/error-handling for autonomous runs", "evidenceIds": [ "salesforce-docs-18", "salesforce-docs-21", "salesforce-docs-31", "salesforce-gh-8", "salesforce-gh-9", "salesforce-docs-29", "salesforce-docs-30", "salesforce-docs-32" ] }, { "productId": "salesforce", "storyId": "agentic-builtin-assistant", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Sales Cloud embeds Agentforce agents directly in the CRM to autonomously handle tasks like qualifying leads, updating opportunities, and closing renewals, with natural-language agent building and 24/7 deployment described in first-party docs. Missing for 10: independent/hands-on verification of the assistant's task delegation working reliably in practice, and more detail on the interactive 'delegate a task' UX rather than marketing case studies.", "evidenceIds": [ "salesforce-docs-18", "salesforce-docs-21", "salesforce-docs-31", "salesforce-docs-29", "salesforce-docs-30" ] }, { "productId": "salesforce", "storyId": "agentic-headless", "verdict": "partial", "quality": 7, "confidence": "medium", "rationale": "Salesforce ships an official CLI (sf/@salesforce/cli) with headless-friendly commands like `sf data query`, `sf apex run test`, `sf org create scratch`, and even `sf agent create/activate`, which are the standard mechanism developers use to script and automate Salesforce orgs in CI pipelines. However, the evidence is CLI/platform-level rather than Sales Cloud-specific, and there's no explicit CI/CD pipeline example, GitHub Actions integration doc, or independent hands-on CI report cited. Missing for 10: explicit CI/CD pipeline integration guide or example, independent verification of headless automation in a real CI environment, Sales-Cloud-specific (not just generic platform) automation documentation.", "evidenceIds": [ "salesforce-gh-1", "salesforce-gh-2", "salesforce-gh-3", "salesforce-gh-7", "salesforce-gh-8", "salesforce-gh-9", "salesforce-probe-4" ] }, { "productId": "salesforce", "storyId": "agentic-mcp-client", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Salesforce's Agentforce Builder explicitly lets users find, evaluate, and plug in trusted third-party agents, sub-agents, and MCP servers via AgentExchange, directly enabling agents to use external MCP tools, and Agent Builder also connects to Flows, Apex, MuleSoft APIs, etc. This is first-party documentation without independent hands-on corroboration of the MCP plug-in flow. Missing for 10: independent/community verification of actually connecting an MCP server in Agentforce Builder, and more detail on configuration/setup steps.", "evidenceIds": [ "salesforce-docs-28", "salesforce-docs-29", "salesforce-docs-23" ] }, { "productId": "salesforce", "storyId": "agentic-mcp-server", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Salesforce publishes an official MCP server (salesforce-probe-3: github.com/salesforcecli/mcp) alongside its CLI, and Agentforce Builder documentation explicitly supports plugging in third-party and platform MCP servers (salesforce-docs-28), confirming the platform embraces the MCP standard for agent connectivity. Missing for 10: detailed first-party setup/usage docs for the MCP server itself, and independent/hands-on validation of its functionality beyond the repo's existence.", "evidenceIds": [ "salesforce-probe-3", "salesforce-docs-28", "salesforce-gh-6" ] }, { "productId": "salesforce", "storyId": "agentic-nl-commands", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Salesforce documents natural-language agent building (\"Use natural language and Agent Optimizer to get started quickly\" — salesforce-docs-30) and Agentforce agents executing sales tasks like qualifying leads and closing deals via natural-language-driven automation (salesforce-docs-21, salesforce-docs-31), which supports agentic natural-language operation within Sales Cloud's Agentforce layer. However, this is mostly about configuring/building agents rather than a general natural-language command interface for day-to-day CRM operation by end users, and there's no hands-on/independent confirmation of reliability. Missing for 10: independent verification of natural-language command execution in daily use, clear evidence of a conversational interface for core CRM tasks beyond agent-builder configuration.", "evidenceIds": [ "salesforce-docs-30", "salesforce-docs-21", "salesforce-docs-31", "salesforce-docs-18", "salesforce-docs-29" ] }, { "productId": "salesforce", "storyId": "agentic-official-cli", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Salesforce ships an official, actively documented CLI (@salesforce/cli / sf) with commands for org management, data queries, Apex tests, and even agent creation/activation, corroborated by GitHub docs and independent community praise for its command-line tooling. Missing for 10: deeper AI-native agent workflow examples in the CLI itself and more independent hands-on reviews specifically of newer 'sf agent' subcommands.", "evidenceIds": [ "salesforce-gh-1", "salesforce-gh-2", "salesforce-gh-3", "salesforce-gh-4", "salesforce-gh-6", "salesforce-gh-7", "salesforce-gh-8", "salesforce-gh-9", "salesforce-probe-4", "salesforce-comm-3" ] }, { "productId": "salesforce", "storyId": "agentic-public-api", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Salesforce documents extensive public APIs (REST/SOAP/Apex/Bulk via Platform APIs), a robust official CLI (sf commands for data query, org management, agent creation, apex tests) and even an official MCP server, all confirmed via GitHub tooling and probes, giving AI-native users multiple documented ways to drive the product programmatically. Missing for 10: a discoverable OpenAPI/swagger spec (probe found only 404s) and independent hands-on validation of the public REST API itself beyond CLI tooling.", "evidenceIds": [ "salesforce-docs-7", "salesforce-gh-1", "salesforce-gh-2", "salesforce-gh-3", "salesforce-gh-4", "salesforce-gh-7", "salesforce-gh-8", "salesforce-probe-3", "salesforce-probe-4", "salesforce-comm-3" ] }, { "productId": "salesforce", "storyId": "agentic-scoped-keys", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Salesforce documents attribute-based access control (ABAC) policies that admins can enforce to control what data agents (not just humans) can see, which speaks to least-privilege access for agents, but there is no explicit mention of scoped/least-privilege API credentials, tokens, or connected-app OAuth scopes issued specifically to an agent. Missing for 10: explicit API credential/token scoping mechanism for agents, OAuth scope documentation, and any independent/hands-on confirmation of least-privilege enforcement in practice.", "evidenceIds": [ "salesforce-docs-32" ] }, { "productId": "salesforce", "storyId": "agentic-sdks", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Salesforce offers robust official SDK/CLI tooling (salesforcecli/cli with sf commands for org, data, apex, agent management), a dedicated plugin developer guide, and platform APIs for building apps/agents, corroborated by independent developer testimony praising the CLI, VS Code extensions, and local dev tools. missing for 10: no direct evidence of a language-specific SDK (e.g., Node/Java/Python client libraries) beyond the CLI, and no independent hands-on review of SDK completeness for AI-native workflows specifically.", "evidenceIds": [ "salesforce-gh-1", "salesforce-gh-2", "salesforce-gh-3", "salesforce-gh-6", "salesforce-gh-7", "salesforce-gh-8", "salesforce-docs-7", "salesforce-comm-3", "salesforce-probe-4" ] }, { "productId": "salesforce", "storyId": "agentic-webhooks", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack contains no mention of webhooks, Platform Events, Streaming API, or any push-notification subscription mechanism for Salesforce Sales Cloud; only CLI, MCP server, and marketing content are documented. missing for 10: webhook subscription API/docs, event notification setup guide, any first-party or community confirmation of webhook support.", "evidenceIds": [] }, { "productId": "salesforce", "storyId": "api-interactive-docs", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "There is no evidence of an interactive API reference with runnable examples; the openapi probe returned 404s and no docs mention a try-it-console or embedded runnable examples for the API. Only marketing mentions of 'Discover Salesforce APIs' and CLI tooling exist, which is not an interactive reference experience.", "evidenceIds": [ "salesforce-probe-2", "salesforce-docs-7" ] }, { "productId": "salesforce", "storyId": "api-machine-spec", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack includes an explicit probe showing all standard OpenAPI spec paths (openapi.json, swagger.json, etc.) return 404, and no docs item describes a downloadable machine-readable API spec — only vague marketing copy about 'Discover Salesforce APIs.' No concrete OpenAPI/Swagger artifact is shown to exist.", "evidenceIds": [ "salesforce-probe-2", "salesforce-docs-7" ] }, { "productId": "salesforce", "storyId": "api-sandbox", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "The Salesforce CLI supports scratch org creation (`sf org create scratch`) which spins up isolated dev/test environments separate from production, and includes test/query tooling (`sf apex run test`, `sf data query`) that could be run against such sandboxes. However, no evidence explicitly ties this to an AI-native/agentic workflow or documents a dedicated 'sandbox for AI testing' story beyond generic dev tooling. Missing for 10: explicit documentation of AI-agent-specific sandbox testing workflows, integration between scratch orgs and Agentforce/AI agent testing, and independent corroboration of this specific use case.", "evidenceIds": [ "salesforce-gh-1", "salesforce-gh-4", "salesforce-gh-5", "salesforce-gh-7", "salesforce-gh-3" ] }, { "productId": "salesforce", "storyId": "api-versioning-policy", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack references API versioning, version deprecation timelines, or a documented deprecation policy for Salesforce APIs; the pack only shows CLI/MCP tooling and marketing content. missing for 10: documentation of API version numbering, deprecation schedule/policy, and any changelog or support-lifecycle references.", "evidenceIds": [] }, { "productId": "salesforce", "storyId": "auto-enrichment", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "Evidence covers lead scoring, forecasting, pipeline management, and CRM sync, but no citation mentions auto-enrichment of contact/company records with third-party firmographic or contact data. Missing for 10: any documented data-enrichment feature/integration, evidence of firmographic data append, or contact/company auto-fill from external sources.", "evidenceIds": [] }, { "productId": "salesforce", "storyId": "automation-bulk-operations", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack shows CLI/query commands (sf data query, sf org create scratch) and general AI/automation marketing claims, but nothing documents bulk create/update/delete operations across many records for an AI-native workflow. Missing for 10: explicit bulk API or bulk data manipulation documentation, evidence of batch processing at scale, or AI-agent-triggered bulk operations.", "evidenceIds": [ "salesforce-gh-3", "salesforce-gh-1", "salesforce-docs-7" ] }, { "productId": "salesforce", "storyId": "automation-rules-engine", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Salesforce documents rule-based automation constructs (Built-in Sales Flows and Lead Routing, Agentforce agents triggered across deal-cycle stages, Agent Script Recipes) and CLI/agent tooling (sf agent create/activate) that support event-driven automation, but the evidence is largely marketing copy rather than technical documentation of a rules engine or trigger/condition/action framework a developer could inspect. Missing for 10: concrete docs on defining trigger conditions (e.g., Flow Builder trigger types, Apex triggers) with independent/hands-on verification that automations reliably fire on events, and no community corroboration of automation reliability.", "evidenceIds": [ "salesforce-docs-27", "salesforce-docs-21", "salesforce-docs-18", "salesforce-docs-6", "salesforce-gh-8", "salesforce-gh-9", "salesforce-docs-31" ] }, { "productId": "salesforce", "storyId": "automation-scheduled-jobs", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Sales Cloud advertises built-in Sales Flows, automation of the sales cycle, and 24/7 autonomous agents (salesforce-docs-27, salesforce-docs-11, salesforce-docs-18), implying some workflow/automation scheduling capability, but there is no explicit documentation of an AI-native interface (API/CLI) for creating or managing recurring scheduled jobs — the CLI evidence only shows org/test/agent commands, not job scheduling. missing for 10: explicit docs on scheduled/recurring Flow or batch job creation via API/CLI, AI-native scheduling interface, and independent confirmation of recurring automation working as claimed.", "evidenceIds": [ "salesforce-docs-27", "salesforce-docs-11", "salesforce-docs-18", "salesforce-gh-5", "salesforce-gh-7" ] }, { "productId": "salesforce", "storyId": "automation-versioned-workflows", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence describes versioning, review workflows, or rollback specifically for automations/agents (e.g., Flow version history, agent build rollback); only DevOps Center is mentioned generically without detail on versioning/rollback mechanics.", "evidenceIds": [] }, { "productId": "salesforce", "storyId": "bidirectional-sync-api", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "While Salesforce is known for REST/Bulk APIs, the evidence pack only offers generic marketing lines about 'APIs' and a CLI for org/data querying (salesforce-docs-7, salesforce-gh-3) with no documentation of upsert operations, rate limits, or change-data-capture/streaming for bidirectional sync at scale. Missing for 10: documented rate limits, upsert API details, change detection (CDC/PushTopic/Platform Events) evidence.", "evidenceIds": [ "salesforce-docs-7", "salesforce-gh-3", "salesforce-probe-2" ] }, { "productId": "salesforce", "storyId": "calendar-meeting-sync", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "There's a claimed-docs mention of 'AI Automatically Syncs Emails, Events, and Contacts' implying calendar/event sync into the CRM, but no evidence detailing calendar integration setup, how synced meetings appear specifically on contact/deal (opportunity) timelines, or any hands-on/independent confirmation. Missing for 10: detailed calendar-sync documentation, evidence of meetings appearing on timelines, independent/hands-on corroboration.", "evidenceIds": [ "salesforce-docs-8" ] }, { "productId": "salesforce", "storyId": "contact-company-records", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Salesforce Sales Cloud explicitly lists 'Lead, Account, Contact, and Opportunity Management' as a core capability, implying linked contact/company records, but the evidence pack contains no direct documentation of an activity timeline feature on records or details on how records are linked. missing for 10: explicit documentation/screenshots of activity timeline on contact/account records, independent hands-on confirmation of the linked-record UI.", "evidenceIds": [ "salesforce-docs-22", "salesforce-docs-19", "salesforce-docs-25" ] }, { "productId": "salesforce", "storyId": "crm-migration", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence pack items address CRM migration tooling, data import from competing CRMs, preservation of record ownership, or historical activity data; all evidence covers AI/sales features, CLI/dev tooling, and general community sentiment unrelated to migration.", "evidenceIds": [] }, { "productId": "salesforce", "storyId": "custom-fields-views", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack contains no documentation or citation that ops users can add custom fields, build filtered/sorted views, or share views without going through an admin/dev project — all cited material is generic marketing (AI, pipeline, forecasting) or CLI/developer tooling, not self-service customization UI. Community comment [salesforce-comm-4] even suggests customization in practice requires paid consultants rather than being self-serve, but this is general skepticism rather than a concrete hands-on contradiction, so it doesn't elevate to 'disputed' — it simply reinforces the lack of supporting evidence.", "evidenceIds": [ "salesforce-comm-4", "salesforce-comm-6" ] }, { "productId": "salesforce", "storyId": "custom-objects", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Evidence confirms Salesforce is broadly known for deep customization and has developer tooling (CLI, APIs, VS Code extensions, LWC local dev) that would support building custom objects/fields/relationships, and community input (salesforce-comm-6) explicitly notes Salesforce is 'a king of' customization. However, none of the evidence explicitly documents the Custom Objects/Fields/Schema Builder relationship-modeling feature itself. Missing for 10: explicit docs/screenshots of custom object creation, field types, and relationship (lookup/master-detail) modeling, plus independent hands-on confirmation of this specific capability.", "evidenceIds": [ "salesforce-comm-6", "salesforce-comm-3", "salesforce-docs-7", "salesforce-gh-1", "salesforce-gh-4" ] }, { "productId": "salesforce", "storyId": "dedupe-merge-records", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "The evidence pack contains no mention of duplicate detection, deduplication rules, or merge tools for contacts/accounts (e.g., no reference to Salesforce's native 'Merge Duplicates' or matching/duplicate rule features). Only generic lead/contact/account management mentions (salesforce-docs-22) appear, with no specifics on dedup or merge workflows.", "evidenceIds": [ "salesforce-docs-22" ] }, { "productId": "salesforce", "storyId": "email-templates-sequences", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Marketing copy mentions 'engagement built directly into your CRM' and automatic email syncing, and a community anecdote praises how quickly a timed email could be set up in Salesforce, but there is no explicit documentation of templated email or multi-step sequence/cadence tooling. Missing for 10: explicit feature docs for email templates, cadence/sequence builder, or multi-step engagement workflows, and independent verification beyond a single anecdotal comment.", "evidenceIds": [ "salesforce-docs-19", "salesforce-docs-8", "salesforce-docs-27", "salesforce-comm-2" ] }, { "productId": "salesforce", "storyId": "fast-time-to-pipeline", "verdict": "disputed", "quality": 4, "confidence": "medium", "rationale": "Salesforce offers a self-serve free trial signup (salesforce-docs-15), but hands-on community evidence directly contradicts the claim of quick, partner-free setup: users note Salesforce customization is heavy and 'companies end up paying through the nose for an army of salesforce consultants,' and that it 'will need customizations' and is compared to 'the Jira of CRMs' for being cumbersome. No evidence of a guided, sub-hour data-import-to-pipeline flow exists in the pack. missing for 10: documented quick-start data import wizard, evidence of founders/small teams completing setup without consultants, time-to-value benchmarks.", "evidenceIds": [ "salesforce-docs-15", "salesforce-comm-4", "salesforce-comm-6", "salesforce-comm-8" ] }, { "productId": "salesforce", "storyId": "lead-assignment-routing", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Pricing page explicitly lists 'Built-in Sales Flows and Lead Routing' and lead scoring/management features, indicating assignment/routing capability exists, but no evidence details round-robin logic, configuration specifics, or independent confirmation it works as expected. Missing for 10: documentation of round-robin assignment mechanics, admin setup guide, and hands-on/independent verification of lead routing behavior.", "evidenceIds": [ "salesforce-docs-27", "salesforce-docs-22", "salesforce-docs-17" ] }, { "productId": "salesforce", "storyId": "marketplace-integrations", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Evidence shows Salesforce has a marketplace concept (AgentExchange) where admins can 'find, evaluate, and plug in trusted third-party agents, sub-agents, and MCP servers' (salesforce-docs-28) and pricing tiers reference 'Access to AgentExchange' (salesforce-docs-23), suggesting some app-marketplace capability exists. However, none of the evidence specifically confirms prebuilt Slack, support-desk, marketing, or data-warehouse integrations being installable from this or the classic AppExchange marketplace. Missing for 10: explicit mention of AppExchange, named integrations (Slack, ServiceNow/Zendesk, marketing tools, Snowflake/data warehouses), and any independent confirmation of installation workflow.", "evidenceIds": [ "salesforce-docs-28", "salesforce-docs-23" ] }, { "productId": "salesforce", "storyId": "multiple-pipelines", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "Salesforce Sales Cloud supports customizable sales processes and multiple record types with different stage sets in principle, but the evidence pack contains no mention of multiple pipelines, record-type-based sales processes, or configurable stage sets for different products/motions — only generic AI/forecasting/pipeline-visibility marketing copy and CLI/dev tooling references.", "evidenceIds": [] }, { "productId": "salesforce", "storyId": "openness-api-parity", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Evidence shows Salesforce has a broad API/CLI ecosystem (sf CLI, data query, org management, agent creation) and community praise for developer tooling, plus an MCP server, suggesting programmatic access is extensive. However, there's no explicit documentation or claim of full UI/API feature parity, and the openapi probe returned 404s, leaving the actual scope of API coverage unverified. Missing for 10: explicit API-vs-UI parity documentation, enumeration of UI-only features (if any), and independent confirmation that all sales-cycle actions (forecasting, quoting, agent config) are fully API-accessible.", "evidenceIds": [ "salesforce-docs-7", "salesforce-gh-1", "salesforce-gh-3", "salesforce-gh-8", "salesforce-probe-3", "salesforce-probe-4", "salesforce-probe-2", "salesforce-comm-3" ] }, { "productId": "salesforce", "storyId": "openness-full-export", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence of bulk data export in open/standard formats or a documented data-portability/exit path; CLI (sf data query) supports querying but not evidenced as a full open-format export mechanism. Missing for 10: documented bulk export tools (e.g., Data Loader/Bulk API) producing open formats like CSV/JSON, data portability/exit guarantees, and any independent confirmation of a clean 'leave with your data' workflow.", "evidenceIds": [ "salesforce-gh-3", "salesforce-probe-4" ] }, { "productId": "salesforce", "storyId": "openness-open-license", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Salesforce Sales Cloud is closed-source proprietary SaaS; while a CLI is open-source, the core product source is not available under any open license, and no evidence indicates otherwise.", "evidenceIds": [] }, { "productId": "salesforce", "storyId": "openness-self-host", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Salesforce Sales Cloud is a proprietary multi-tenant SaaS platform; self-hosting the core product is fundamentally outside its architecture/business model, making this a category error rather than a missing feature.", "evidenceIds": [] }, { "productId": "salesforce", "storyId": "privacy-data-residency", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence pack items mention data residency, regional hosting options, or org data location controls for Sales Cloud; only ABAC access control and general AI feature marketing are covered. Salesforce is known to offer data residency options in reality, but this evidence pack contains no documentation of that capability, so verdict must be none. Missing for 10: any documentation of region/data-residency selection, hyperforce or org shard location controls, or data storage compliance options.", "evidenceIds": [ "salesforce-docs-32" ] }, { "productId": "salesforce", "storyId": "privacy-no-training", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "The evidence pack contains no documentation or policy statement addressing whether customer data is used to train AI models or how users can opt out of such training; only ABAC access control policies and generic AI feature marketing are mentioned. Missing for 10: explicit data-usage/training opt-out policy, documentation of a no-training guarantee or toggle, any independent confirmation of such controls.", "evidenceIds": [ "salesforce-docs-32" ] }, { "productId": "salesforce", "storyId": "privacy-retention-controls", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "The evidence pack covers AI sales features, CLI/DevOps tooling, and access-control (ABAC) mentions, but nothing addresses data retention policies, deletion workflows, or how AI-processed data is purged or retained. missing for 10: documentation on data retention schedules, right-to-erasure/deletion tooling, AI-specific data handling/retention policy statements.", "evidenceIds": [] }, { "productId": "salesforce", "storyId": "privacy-telemetry-optout", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence pack items mention telemetry opt-out, usage tracking controls, or any privacy toggle for AI-native usage data collection; ABAC data access controls (salesforce-docs-32) address data visibility, not telemetry opt-out. Missing for 10: any documentation of a telemetry/usage-tracking opt-out mechanism, settings or admin controls for disabling analytics/telemetry collection.", "evidenceIds": [ "salesforce-docs-32" ] }, { "productId": "salesforce", "storyId": "reports-dashboards", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Evidence shows Sales Cloud provides built-in pipeline visibility, forecasting, and a dashboard view (salesforce-docs-3, salesforce-docs-9, salesforce-docs-10, salesforce-docs-20) rather than requiring spreadsheet export, supporting the core of the story. However, there is no explicit documentation of a report/dashboard builder tool, activity reporting, or conversion-rate analytics specifically, so the coverage of the full story is only partial. missing for 10: dedicated report-builder documentation, activity-metrics reporting evidence, conversion funnel analytics, and independent/hands-on corroboration of dashboard customization.", "evidenceIds": [ "salesforce-docs-3", "salesforce-docs-9", "salesforce-docs-10", "salesforce-docs-20" ] }, { "productId": "salesforce", "storyId": "revenue-forecasting", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Salesforce Sales Cloud explicitly offers Predictive Forecasting, Advanced Forecast & Pipeline Management, and Opportunity Management features that combine pipeline value, stage probabilities, and close dates for revenue forecasting, backed by named product features in pricing docs. Missing for 10: independent hands-on validation of forecasting accuracy and no detailed walkthrough of how stage probability/close date roll up into forecast numbers.", "evidenceIds": [ "salesforce-docs-16", "salesforce-docs-20", "salesforce-docs-9", "salesforce-docs-22", "salesforce-docs-3" ] }, { "productId": "salesforce", "storyId": "spreadsheet-import", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence in the pack addresses spreadsheet/CSV import, field mapping, validation, or handling of failed/skipped rows during data import — the pack only covers AI sales features, CLI tooling, and general community sentiment. This is a fair onboarding-migration axis for a CRM, but nothing here demonstrates it.", "evidenceIds": [] }, { "productId": "salesforce", "storyId": "two-way-email-sync", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Salesforce Sales Cloud pricing docs list \"AI Automatically Syncs Emails, Events, and Contacts\" as a feature, implying Gmail/Outlook two-way sync and activity logging, but there is no detail on setup, reliability, or which records emails log to, nor any independent/hands-on confirmation. missing for 10: detailed docs on Einstein Activity Capture/Gmail-Outlook integration setup, confirmation of two-way sync behavior, independent user validation that emails log to correct records.", "evidenceIds": [ "salesforce-docs-8" ] }, { "productId": "salesforce", "storyId": "visual-pipeline-stages", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Docs confirm pipeline/opportunity management, forecasting, and stage-based sales cycle tracking (salesforce-docs-3, -20, -22, -24), which implies a Kanban-style pipeline view exists in Sales Cloud, but no evidence specifically describes drag-and-drop stage updates or customizable stage configuration UI. Missing for 10: explicit documentation or screenshot/hands-on confirmation of drag-and-drop pipeline board interactions and customizable stage setup, independent corroboration of this specific UX feature.", "evidenceIds": [ "salesforce-docs-3", "salesforce-docs-20", "salesforce-docs-22", "salesforce-docs-24" ] }, { "productId": "salesforce", "storyId": "workflow-builder", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Salesforce Sales Cloud includes Flow/automation ('Built-in Sales Flows and Lead Routing') and community evidence confirms trigger-based automation like timed emails is easy to build, supporting record updates, tasks, and notifications. However, the evidence pack lacks first-party documentation specifically detailing trigger-based workflow builders (e.g., Flow Builder, Process Builder) with concrete examples of update/create/notify actions chained together. missing for 10: detailed first-party docs on Flow Builder/trigger automation mechanics, independent hands-on verification of multi-action workflows (update+task+notification) working end-to-end.", "evidenceIds": [ "salesforce-docs-27", "salesforce-comm-2", "salesforce-docs-11" ] }, { "productId": "twenty", "storyId": "agent-enriches-lead", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Twenty documents an MCP server (twenty-docs-32) and AI agents that can 'enrich records with data from external sources' and execute multi-step tasks (twenty-docs-56, twenty-docs-5), plus a developer API capable of creating custom-object records (twenty-docs-8, twenty-docs-22) and workflows that 'auto-enrich new contacts with data from external APIs' (twenty-docs-14). However, there is no explicit documentation of an agent assigning a record owner as part of this flow, nor a concrete end-to-end example (lead creation + enrichment + owner assignment) via API or MCP, and no independent/hands-on confirmation that the MCP server performs this workflow. Missing for 10: explicit owner-assignment step in agent/API flow, a documented end-to-end example combining all three actions, independent verification of MCP server behavior.", "evidenceIds": [ "twenty-docs-32", "twenty-docs-56", "twenty-docs-5", "twenty-docs-14", "twenty-docs-8", "twenty-docs-22", "twenty-docs-19" ] }, { "productId": "twenty", "storyId": "agent-preps-account-brief", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Twenty provides the necessary building blocks — GraphQL/REST APIs and a documented MCP server (twenty-docs-32) for programmatic access, automatic linking of emails/calendar events to Company/Person records (twenty-docs-4, twenty-docs-52, twenty-docs-58), and AI agents that can answer questions, enrich records, and execute multi-step tasks within permissions (twenty-docs-5, twenty-docs-18, twenty-docs-56) — which together could let an agent assemble open deals, emails, and history into a brief. However, there is no concrete documentation of an actual 'account brief' workflow, no example of the MCP server's specific tools/resources for querying deals+emails+history in one call, and no hands-on evidence this composite use case has been built or tested. Missing for 10: a documented end-to-end example or MCP tool spec for compiling a pre-meeting brief, and independent/hands-on confirmation of the AI agent successfully synthesizing deals+emails+history.", "evidenceIds": [ "twenty-docs-32", "twenty-docs-5", "twenty-docs-18", "twenty-docs-56", "twenty-docs-4", "twenty-docs-52", "twenty-docs-58", "twenty-docs-8" ] }, { "productId": "twenty", "storyId": "agent-updates-deal-stages", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Twenty documents the necessary building blocks — an MCP server (twenty-docs-32), REST/GraphQL API with full CRUD on custom fields like deal stage (twenty-docs-8, twenty-docs-22), automatic email/calendar linkage to CRM records (twenty-docs-4, twenty-docs-52, twenty-docs-58), and AI agents that 'execute multi-step tasks autonomously' including enriching records (twenty-docs-5, twenty-docs-56) plus workflow triggers on record changes (twenty-docs-3, twenty-docs-13). However, no evidence explicitly describes an agent reading email/meeting content and then updating deal stage or 'next steps' fields specifically — this exact pipeline-management workflow is not documented as a first-party example. Missing for 10: an explicit example/workflow showing an agent parsing email or meeting signals and writing deal-stage/next-steps updates via API or MCP, and any independent/hands-on confirmation this works end-to-end.", "evidenceIds": [ "twenty-docs-32", "twenty-docs-5", "twenty-docs-56", "twenty-docs-4", "twenty-docs-52", "twenty-docs-8", "twenty-docs-13", "twenty-docs-3" ] }, { "productId": "twenty", "storyId": "agentic-agent-docs", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "A direct probe confirms llms.txt is live at docs.twenty.com/llms.txt returning HTTP 200 with structured navigation content, and Twenty's docs are also organized in agent-friendly markdown (.md endpoints) referenced throughout the evidence pack. Missing for 10: no independent/community confirmation of an agent successfully consuming llms.txt in practice.", "evidenceIds": [ "twenty-probe-1" ] }, { "productId": "twenty", "storyId": "agentic-ai-insights", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Twenty ships a natural-language AI chatbot that queries CRM records, summarizes information, and finds answers without building filters, plus AI agents that enrich records and execute multi-step tasks autonomously within permission boundaries. This directly delivers AI-generated insights/suggestions from the user's own data inside the product. Missing for 10: independent/hands-on validation of the AI chatbot and agent quality (only vendor docs), and no evidence of proactive/unprompted suggestions beyond query-driven and record-enrichment use cases.", "evidenceIds": [ "twenty-docs-5", "twenty-docs-18", "twenty-docs-19", "twenty-docs-56" ] }, { "productId": "twenty", "storyId": "agentic-autonomous-automation", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Twenty's workflow engine supports triggers on schedules, record changes, and webhooks, chaining actions including AI Agent steps, code execution, and delays—enabling automations that run autonomously in the background without user intervention. Docs further describe AI agents executing multi-step tasks autonomously (enrichment, chat) within a permission model. Missing for 10: independent/hands-on verification that scheduled/background workflows run reliably at scale, and detail on monitoring or retry/error handling for failed autonomous runs.", "evidenceIds": [ "twenty-docs-3", "twenty-docs-13", "twenty-docs-5", "twenty-docs-56", "twenty-docs-19", "twenty-docs-35" ] }, { "productId": "twenty", "storyId": "agentic-builtin-assistant", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Twenty documents built-in AI agents that operate autonomously within the CRM—answering questions, enriching records, and executing multi-step tasks—scoped by the user's permission model, plus a natural-language AI chatbot for querying data, both delegated to within the product itself. Missing for 10: independent/hands-on verification of the AI assistant's real-world reliability and no community evidence corroborating this specific AI feature (community feedback predates the AI feature and is unrelated).", "evidenceIds": [ "twenty-docs-5", "twenty-docs-18", "twenty-docs-19", "twenty-docs-56", "twenty-docs-13" ] }, { "productId": "twenty", "storyId": "agentic-headless", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Twenty can be self-hosted via a single Docker Compose command and exposes full REST/GraphQL APIs (including a Metadata API) for programmatic, UI-less interaction, which supports scripted/automated deployment and data operations. However, there is no explicit documentation of a headless mode, CI pipeline integration, or automated testing workflow — the evidence only covers deployment and API access, not CI-oriented usage. Missing for 10: explicit CI/CD examples, headless execution mode, automated test-runner support, and independent confirmation of running unattended in pipelines.", "evidenceIds": [ "twenty-docs-10", "twenty-docs-26", "twenty-docs-36", "twenty-docs-8", "twenty-docs-22", "twenty-docs-23" ] }, { "productId": "twenty", "storyId": "agentic-mcp-client", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The only MCP-related evidence is a pricing table line item 'MCP server | Yes' (twenty-docs-32), which indicates Twenty exposes an MCP server for others to call its own tools — not that Twenty acts as an MCP client that can plug in external MCP servers so its AI agents can use their tools. No documentation describes configuring or connecting external MCP servers within Twenty's AI agent framework (twenty-docs-5, twenty-docs-18, twenty-docs-56 describe agents but only mention internal actions like enrichment, not external MCP tool integration).", "evidenceIds": [ "twenty-docs-32", "twenty-docs-5", "twenty-docs-18", "twenty-docs-56" ] }, { "productId": "twenty", "storyId": "agentic-mcp-server", "verdict": "full", "quality": 5, "confidence": "low", "rationale": "Twenty's pricing page explicitly lists 'MCP server | Yes | Yes | Yes' across all plans, confirming an official MCP server offering that would let AI agents connect. However, this is the only evidence — there's no dedicated documentation page explaining setup, capabilities, or authentication for the MCP server, and no independent/hands-on corroboration of it working. Missing for 10: dedicated MCP server docs/setup guide, independent verification that it works, details on scope/permissions for MCP connections.", "evidenceIds": [ "twenty-docs-32" ] }, { "productId": "twenty", "storyId": "agentic-nl-commands", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Twenty's docs describe a built-in AI chatbot that lets users 'ask questions about your data in natural language' to query records, summarize info, and avoid building complex filters, plus autonomous AI agents that execute multi-step tasks within the CRM under the user's permission model. This directly satisfies the natural-language operation story for an AI-native user. Missing for 10: independent/hands-on verification of the chatbot's reliability and no community reports confirming it works as documented in practice.", "evidenceIds": [ "twenty-docs-18", "twenty-docs-5", "twenty-docs-56", "twenty-docs-19" ] }, { "productId": "twenty", "storyId": "agentic-official-cli", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Twenty ships an official CLI (`npx create-twenty-app`, `npx twenty app:publish`) documented in the GitHub README for scaffolding apps and defining objects/fields/views as code, satisfying the 'official CLI' axis. Missing for 10: independent/hands-on corroboration of the CLI's reliability, and documentation of broader CLI capabilities beyond app scaffolding/publishing (e.g., data or workflow management from the CLI).", "evidenceIds": [ "twenty-gh-1", "twenty-gh-2", "twenty-gh-4", "twenty-gh-5", "twenty-gh-6" ] }, { "productId": "twenty", "storyId": "agentic-public-api", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Twenty documents a developer-first public API with both REST and GraphQL endpoints, auto-generated per-workspace docs, a Metadata API for programmatic schema changes, batching support, and scoped API keys — plus community confirmation that the REST API works hands-on. missing for 10: independent verification of documentation completeness/quality (probe found no discoverable OpenAPI spec at standard paths) and more third-party corroboration beyond one HN comment.", "evidenceIds": [ "twenty-docs-8", "twenty-docs-22", "twenty-docs-23", "twenty-docs-24", "twenty-docs-25", "twenty-docs-41", "twenty-comm-1", "twenty-probe-2" ] }, { "productId": "twenty", "storyId": "agentic-scoped-keys", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Twenty's docs explicitly state API keys can be scoped to a specific role to limit access (twenty-docs-24), backed by granular RBAC at object/field/record level (twenty-docs-7, twenty-docs-39, twenty-docs-54) and an explicit permission model constraining AI agents to only what the user/role can view (twenty-docs-19, twenty-docs-5). This directly supports issuing least-privilege credentials for an agent. Missing for 10: independent/hands-on verification that role-scoped keys work as documented, and no explicit agent-specific key-issuance workflow beyond general role scoping.", "evidenceIds": [ "twenty-docs-24", "twenty-docs-7", "twenty-docs-39", "twenty-docs-19", "twenty-docs-5" ] }, { "productId": "twenty", "storyId": "agentic-sdks", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Twenty offers a developer-first REST/GraphQL API with auto-generated docs, a Metadata API, an official CLI (`create-twenty-app`) for scaffolding apps as code, and an MCP server offering (listed on pricing), all of which support AI-native builders. However, there is no explicit 'official SDK' (e.g., published npm/pip client library) mentioned, and a probe found no discoverable OpenAPI spec, undercutting the auto-generated-docs claim. Missing for 10: named official SDK packages in specific languages, independent/hands-on confirmation of building against these APIs, and a working OpenAPI/schema endpoint.", "evidenceIds": [ "twenty-docs-8", "twenty-docs-22", "twenty-docs-23", "twenty-gh-1", "twenty-gh-4", "twenty-docs-32", "twenty-probe-2" ] }, { "productId": "twenty", "storyId": "agentic-webhooks", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Twenty's workflow engine can trigger on record changes/schedules/incoming webhooks and chain an 'HTTP request' step (e.g., Slack alert on deal stage change), effectively enabling outbound webhook-style notifications for events — but there's no documented first-class 'webhook subscription' API where an external AI agent registers a URL to be notified of arbitrary CRM events. Missing for 10: explicit webhook subscription/registration endpoint or events API, documentation of supported event types/payloads for outbound webhooks, and independent confirmation this works reliably.", "evidenceIds": [ "twenty-docs-3", "twenty-docs-13", "twenty-docs-14", "twenty-docs-35" ] }, { "productId": "twenty", "storyId": "api-interactive-docs", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Docs mention a 'developer-first API' with 'auto-generated documentation per workspace' for both GraphQL and REST endpoints (twenty-docs-8), implying some interactive per-workspace API reference, but there is no explicit description of runnable/try-it-out examples, and a probe for a standard OpenAPI/Swagger endpoint at the docs domain returned 404s (inconclusive since it wasn't the per-workspace endpoint). Missing for 10: explicit confirmation of an interactive 'try it out' console, screenshots or docs describing runnable code examples, and independent corroboration that the auto-generated docs are interactive rather than static.", "evidenceIds": [ "twenty-docs-8", "twenty-probe-2" ] }, { "productId": "twenty", "storyId": "api-machine-spec", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Docs state the API is REST + GraphQL with 'auto-generated documentation per workspace' (twenty-docs-8), implying some machine-readable spec exists, and the Metadata API can describe the schema programmatically (twenty-docs-23/43). However, no evidence confirms a concrete OpenAPI/Swagger file is downloadable, and a direct probe for standard OpenAPI paths on the docs site returned 404s, leaving the claim unconfirmed. Missing for 10: a documented/downloadable OpenAPI or GraphQL SDL export endpoint, and hands-on confirmation that the 'auto-generated documentation per workspace' is actually machine-readable (e.g., JSON schema) rather than just human-readable docs.", "evidenceIds": [ "twenty-docs-8", "twenty-docs-23", "twenty-docs-43", "twenty-probe-2" ] }, { "productId": "twenty", "storyId": "api-sandbox", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence of a sandbox/staging environment, test workspace, or non-production mode for safely testing AI agents or workflows separate from live data. Self-hosting via Docker Compose could theoretically allow spinning up a separate instance, but this is never documented as a sandbox testing feature. missing for 10: dedicated sandbox/staging environment, data seeding/test-mode tooling, documentation of testing AI agents against non-production data.", "evidenceIds": [] }, { "productId": "twenty", "storyId": "api-versioning-policy", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence documents REST/GraphQL APIs with auto-generated docs and metadata endpoints, but there is no mention of API versioning scheme or a documented deprecation policy anywhere in the pack; probe results even show openapi spec endpoints returning 404.", "evidenceIds": [ "twenty-docs-8", "twenty-docs-22", "twenty-docs-23", "twenty-probe-2" ] }, { "productId": "twenty", "storyId": "auto-enrichment", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Docs mention enrichment only as an example built via custom Workflows (HTTP request to an external API) and via AI Agents that can 'enrich records with data from external sources,' but there's no evidence of a built-in, native firmographic/contact enrichment provider or one-click integration—it requires the ops user (or a dev) to configure a workflow or agent with a third-party data source. Missing for 10: a native/pre-built enrichment integration (e.g., built-in data provider), independent/hands-on confirmation that enrichment works as advertised, and detail on what firmographic data fields are actually populated.", "evidenceIds": [ "twenty-docs-14", "twenty-docs-56", "twenty-docs-5", "twenty-docs-19" ] }, { "productId": "twenty", "storyId": "automation-bulk-operations", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Twenty's REST and GraphQL APIs explicitly support batching up to 60 records per request for create/update/delete, plus GraphQL batch upsert, and CSV/XLSX/API import with unlimited records for large-scale migrations, alongside export up to 20,000 records — directly enabling bulk operations across many items. Missing for 10: independent/hands-on verification of batch API limits in practice and no documented bulk-delete-via-filter or bulk-edit-in-UI feature beyond import/export and API batching.", "evidenceIds": [ "twenty-docs-25", "twenty-docs-9", "twenty-docs-59", "twenty-docs-29", "twenty-docs-27", "twenty-docs-37" ] }, { "productId": "twenty", "storyId": "automation-rules-engine", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Twenty's Workflows feature explicitly supports rule-based automation: triggers on record changes, schedules, manual actions, or incoming webhooks, chaining actions like record operations, HTTP requests, code, branches, AI Agent steps, Slack alerts, and enrichment — a clear rules-trigger-actions automation engine documented with concrete examples (deal stage → Slack alert, new contact → enrichment). Missing for 10: independent hands-on verification of workflow reliability/complexity limits beyond docs and one general community note about alpha-stage issues (not specific to workflows).", "evidenceIds": [ "twenty-docs-3", "twenty-docs-13", "twenty-docs-14", "twenty-docs-35", "twenty-docs-42", "twenty-docs-51" ] }, { "productId": "twenty", "storyId": "automation-scheduled-jobs", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Twenty's workflow engine explicitly supports schedule-based triggers alongside record changes, manual actions, and webhooks, and workflows can chain multi-step actions (HTTP, code, branches, AI agent, delay) enabling recurring automation chains. Missing for 10: independent/hands-on confirmation of recurrence configuration (e.g., cron intervals) and no community validation of schedule-trigger reliability.", "evidenceIds": [ "twenty-docs-3", "twenty-docs-13", "twenty-docs-35" ] }, { "productId": "twenty", "storyId": "automation-versioned-workflows", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "The evidence describes Twenty's workflow builder (triggers, chaining actions, code steps) but contains no mention of version history, change review, or rollback capability for workflows/automations. Missing for 10: any documentation of workflow version tracking, diff/review UI, or rollback/undo mechanism for automations.", "evidenceIds": [ "twenty-docs-13", "twenty-docs-35", "twenty-docs-42" ] }, { "productId": "twenty", "storyId": "bidirectional-sync-api", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Docs show REST/GraphQL batching (up to 60 records) with GraphQL batch upsert, a Metadata API, and workflow triggers on record changes/webhooks that could support change detection, plus import/export capabilities for large-scale sync. However, no documented API rate limits are provided anywhere in the evidence, and community feedback flags the REST API as 'alpha' with unspecified issues, undercutting confidence in scale reliability. missing for 10: explicit documented rate limits, dedicated change-detection/webhook-for-sync documentation beyond generic workflow triggers, independent verification of sync at scale.", "evidenceIds": [ "twenty-docs-25", "twenty-docs-23", "twenty-docs-59", "twenty-docs-29", "twenty-docs-3", "twenty-comm-1" ] }, { "productId": "twenty", "storyId": "calendar-meeting-sync", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Docs describe connecting Google Workspace/Microsoft 365 accounts so calendar events automatically appear on relevant CRM records (contacts/deals), with filtering controls; calendar view is also supported in record timelines. missing for 10: no independent/hands-on confirmation that calendar sync specifically (vs. email sync) populates deal timelines, and no explicit mention of deal-object calendar linking beyond Company/People.", "evidenceIds": [ "twenty-docs-4", "twenty-docs-47", "twenty-docs-15", "twenty-docs-52", "twenty-docs-58" ] }, { "productId": "twenty", "storyId": "contact-company-records", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Twenty's docs confirm core CRM objects (Company/Person) with custom relations, email/calendar auto-linking to records, and workflow/API support, which supports linked-record management, but there is no explicit documentation of a unified 'activity timeline' feature showing notes, emails, calls, and tasks chronologically per record. Community evidence is limited to general alpha-stage caveats, not specific timeline testing. Missing for 10: explicit documentation or screenshots of an activity timeline UI per record, independent/hands-on verification of timeline behavior, and confirmation of what activity types (calls, notes, tasks) populate it.", "evidenceIds": [ "twenty-docs-11", "twenty-docs-52", "twenty-docs-58", "twenty-docs-47", "twenty-comm-1" ] }, { "productId": "twenty", "storyId": "crm-migration", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Twenty documents CSV/XLSX/API import with field mapping, duplicate detection, and error handling, plus relation-matching via unique fields (id, email, domain) to preserve links between records like Company/Person — covering the core 'records and relationships' part of migration. However, there's no documented mechanism for preserving record owners (assigning imported records to specific users) or historical activity/timeline data during import, and no case study of an actual CRM-to-CRM migration succeeding end-to-end. Missing for 10: explicit owner-field mapping/preservation during import, migration of activity history/notes/timestamps, and independent evidence of a successful full CRM migration.", "evidenceIds": [ "twenty-docs-27", "twenty-docs-28", "twenty-docs-37", "twenty-docs-45", "twenty-docs-59", "twenty-docs-9" ] }, { "productId": "twenty", "storyId": "custom-fields-views", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Docs clearly show custom objects/fields (20+ types, unlimited custom objects), table/kanban/calendar views with AND/OR filtering, multi-field sort, grouping, and saved custom views — all configurable in-app without dev involvement, plus community corroboration that customization was 'very promising' and easy to set up. Missing for 10: explicit documentation of 'sharing' a saved view with specific teammates/permissions (only role-based permissions and workspace-level dashboard sharing are documented, not view-sharing specifics) and independent hands-on confirmation of the filter/sort/save-view workflow itself.", "evidenceIds": [ "twenty-docs-1", "twenty-docs-34", "twenty-docs-11", "twenty-docs-33", "twenty-docs-12", "twenty-comm-1" ] }, { "productId": "twenty", "storyId": "custom-objects", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "Twenty's docs extensively cover creating custom objects, custom fields (20+ types), and building custom relations (including many-to-many) between any objects, with custom objects receiving first-class treatment (API endpoints, views, permissions, workflows) identical to built-ins. This is corroborated by hands-on community feedback praising the customization as 'very promising.' Missing for 10: deeper independent/hands-on verification of complex relationship modeling beyond a single HN mention, and no third-party technical review of the metadata/schema API in practice.", "evidenceIds": [ "twenty-docs-1", "twenty-docs-11", "twenty-docs-12", "twenty-docs-33", "twenty-docs-22", "twenty-docs-23", "twenty-comm-1" ] }, { "productId": "twenty", "storyId": "dedupe-merge-records", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Docs confirm duplicate detection during CSV/API import (twenty-docs-9), but there is no evidence of a dedicated merge tool or workflow for combining existing duplicate Contact/Company records without losing data — only prevention-at-import is documented. missing for 10: explicit merge UI/feature for existing duplicates, data-preservation guarantees during merge, independent/hands-on confirmation of merge behavior.", "evidenceIds": [ "twenty-docs-9", "twenty-docs-27" ] }, { "productId": "twenty", "storyId": "email-templates-sequences", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Twenty's workflow engine can chain a 'Send email' step with Delay and Branch steps, which could technically be assembled into a multi-step email sequence, and email sync auto-links messages to CRM records — but there is no documented email-template feature, no dedicated 'sequence/cadence' tool for prospects, and no hands-on evidence this is actually used this way. Missing for 10: dedicated templated-email/sequence builder for outbound prospecting, evidence of template management, and independent confirmation of ops teams using workflows this way.", "evidenceIds": [ "twenty-docs-13", "twenty-docs-42", "twenty-docs-52", "twenty-docs-58" ] }, { "productId": "twenty", "storyId": "fast-time-to-pipeline", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Docs show fast signup ('spin up a workspace in under a minute'), CSV/XLSX/API import with field mapping and dedup, quick custom-object/pipeline setup via kanban/table views, and one-command self-host — all consistent with rapid, self-serve onboarding without a partner. However, there's no explicit case study or benchmark confirming an actual 'under one hour to working pipeline with real data' outcome, and a hands-on HN review notes Twenty felt 'pretty alpha-version' with small issues that prevented it from fully working for their use case, tempering confidence in a frictionless first hour. Missing for 10: a concrete time-boxed onboarding case study/testimonial, and independent confirmation that data import/pipeline setup reliably completes in under an hour without hitting the rough edges the community mentioned.", "evidenceIds": [ "twenty-gh-3", "twenty-docs-9", "twenty-docs-27", "twenty-docs-37", "twenty-docs-34", "twenty-docs-26", "twenty-comm-1" ] }, { "productId": "twenty", "storyId": "lead-assignment-routing", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Twenty's workflow engine (record-change triggers, branches, record operations, code) could theoretically be scripted to assign owners, but there is no documented assignment-rule or round-robin lead-routing feature anywhere in the evidence pack.", "evidenceIds": [ "twenty-docs-3", "twenty-docs-13", "twenty-docs-14" ] }, { "productId": "twenty", "storyId": "marketplace-integrations", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "Twenty supports connecting to external tools via Zapier (5,000+ apps) and lets developers build/publish apps for the community, plus workflow actions like Slack alerts, but there's no evidence of a curated app marketplace with one-click prebuilt integrations specifically for Slack, support desk, marketing, or data warehouse tools — these have to be built as workflows or via Zapier rather than installed as packaged apps. Missing for 10: a dedicated marketplace UI, named prebuilt connectors for support desk/marketing/warehouse categories, and evidence of one-click install rather than custom workflow/code setup.", "evidenceIds": [ "twenty-docs-16", "twenty-docs-14", "twenty-docs-17", "twenty-gh-2", "twenty-gh-4" ] }, { "productId": "twenty", "storyId": "multiple-pipelines", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Twenty's docs show building blocks that could support multiple pipelines — unlimited custom objects with custom fields (twenty-docs-1, twenty-docs-33), kanban/table/calendar views with grouping and saved views (twenty-docs-34), and workflow triggers per object (twenty-docs-12) — but there is no explicit documentation of a native 'multiple pipelines with distinct stage sets' feature (e.g. a dedicated Opportunities/Deals module supporting several independently configured pipelines). missing for 10: explicit docs describing a pipeline/deal-stage object with support for multiple named pipelines each having its own stage set, and confirmation this works out-of-the-box rather than via manual custom-object/kanban configuration.", "evidenceIds": [ "twenty-docs-1", "twenty-docs-33", "twenty-docs-34", "twenty-docs-12" ] }, { "productId": "twenty", "storyId": "openness-api-parity", "verdict": "partial", "quality": 7, "confidence": "medium", "rationale": "Docs claim strong API parity — custom objects get identical REST/GraphQL endpoints, views, permissions, and workflow triggers as built-in objects, plus a Metadata API to programmatically change the data model itself, and API-based imports/exports (twenty-docs-8,12,22,23,41,59). However, no evidence explicitly confirms full API control over dashboards, view configuration (kanban/calendar), or workflow authoring — these are described only as UI-driven, and one community report notes the REST API 'worked ok' but the product was 'pretty alpha-version' with unspecified small issues. missing for 10: explicit docs/proof that dashboards, saved views, and workflow definitions can be created/edited via API rather than only through the UI, and independent confirmation beyond one mixed community report.", "evidenceIds": [ "twenty-docs-8", "twenty-docs-12", "twenty-docs-22", "twenty-docs-23", "twenty-docs-41", "twenty-docs-59", "twenty-comm-1" ] }, { "productId": "twenty", "storyId": "openness-full-export", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Twenty explicitly documents export of workspace data for backups/migration with 'no lock-in', supports CSV/XLSX export/import, self-hosting via Docker, and open REST/GraphQL APIs for full data access, giving AI-native users a clear path to extract data in open formats and leave. Missing for 10: independent hands-on verification of export completeness/fidelity and no mention of export format limits beyond CSV (e.g., no JSON/SQL dump documented) or corroboration outside vendor docs.", "evidenceIds": [ "twenty-docs-9", "twenty-docs-29", "twenty-docs-38", "twenty-docs-37", "twenty-docs-8", "twenty-docs-10", "twenty-docs-44" ] }, { "productId": "twenty", "storyId": "openness-open-license", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Twenty's source is hosted publicly on GitHub (twentyhq/twenty) and documented as usable with standard React/TypeScript stack ('no proprietary languages, no gatekeeping'), and community discussion explicitly confirms the project is licensed AGPLv3, an OSI-approved open license. This directly satisfies an AI-native user's ability to read the source under an open license, with self-host instructions reinforcing full source availability. Missing for 10: no direct citation of the LICENSE file text itself and no confirmation whether any enterprise-only modules are closed-source, so full completeness of the open-source surface isn't independently verified.", "evidenceIds": [ "twenty-gh-1", "twenty-gh-2", "twenty-comm-3", "twenty-docs-40", "twenty-docs-10" ] }, { "productId": "twenty", "storyId": "openness-self-host", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "Twenty provides clear first-party self-hosting docs, a single Docker Compose install command, and even an install script, with docs explicitly framing self-hosting as a use case for privacy-conscious organizations wanting to own their data end to end; community evidence corroborates it as easy to set up. Missing for 10: independent hands-on verification of the full self-hosted core feature set (AI, workflows) at parity with cloud beyond initial setup reports.", "evidenceIds": [ "twenty-docs-10", "twenty-docs-26", "twenty-docs-36", "twenty-docs-44", "twenty-docs-53", "twenty-comm-1" ] }, { "productId": "twenty", "storyId": "privacy-data-residency", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Twenty doesn't offer an explicit region-selection setting, but self-hosting via Docker Compose lets privacy-conscious users run the entire stack on their own infrastructure, effectively letting them choose where data lives. This is an indirect residency control rather than a built-in region picker for the cloud offering. Missing for 10: explicit cloud data-residency/region selection UI, documented data center regions, compliance certifications (GDPR/SOC2) tied to specific regions.", "evidenceIds": [ "twenty-docs-10", "twenty-docs-44", "twenty-docs-53", "twenty-docs-36" ] }, { "productId": "twenty", "storyId": "privacy-no-training", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Twenty offers self-hosting so an organization can keep full control of its data ('own your data end to end'), which indirectly prevents third-party AI training on it, and permission-scoped AI agent access limits what data agents can see. However, there is no explicit statement, opt-out setting, or policy about excluding user data from AI model training on the cloud/hosted offering. missing for 10: explicit no-training data policy, cloud-hosted opt-out toggle, independent confirmation of data-handling practices for AI features.", "evidenceIds": [ "twenty-docs-44", "twenty-docs-53", "twenty-docs-19", "twenty-docs-10" ] }, { "productId": "twenty", "storyId": "privacy-retention-controls", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Twenty offers data export ('Export your data anytime — no lock-in', up to 20,000 records/export) and self-hosting for full data ownership, which gives some control over data, but there is no explicit documentation of retention policies or deletion controls (e.g., record purge, right-to-be-forgotten, TTL settings) tailored to AI-native use. Missing for 10: explicit data retention policy settings, record/field deletion controls, GDPR-style erasure workflow, and any AI-specific retention/deletion controls.", "evidenceIds": [ "twenty-docs-38", "twenty-docs-29", "twenty-docs-44", "twenty-docs-53" ] }, { "productId": "twenty", "storyId": "privacy-telemetry-optout", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack mentions telemetry, usage tracking, analytics collection, or an opt-out setting; self-hosting is mentioned but does not itself confirm control over telemetry data collection.", "evidenceIds": [] }, { "productId": "twenty", "storyId": "reports-dashboards", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Twenty provides native custom dashboards with configurable chart types, filters, aggregation, and grouping over pipeline/activity data, with real-time widgets for pipeline health, team performance, and revenue trends — all built in-app without needing spreadsheet exports (twenty-docs-6, twenty-docs-20, twenty-docs-21, twenty-docs-57, twenty-docs-48). Data export is offered only as an optional side capability, not a requirement for reporting. Missing for 10: independent/hands-on validation of dashboard depth and reporting accuracy (only vendor docs cited, and community evidence [twenty-comm-1] notes general 'alpha-version' rough edges without specifically addressing dashboards).", "evidenceIds": [ "twenty-docs-6", "twenty-docs-20", "twenty-docs-21", "twenty-docs-57", "twenty-docs-48", "twenty-docs-46", "twenty-comm-1" ] }, { "productId": "twenty", "storyId": "revenue-forecasting", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Twenty provides the building blocks—custom fields for deal value/stage/close date, dashboards with configurable charts, filters, aggregation, and grouping, and docs explicitly mention tracking 'pipeline health, team performance, revenue trends'—but there is no dedicated forecasting feature that models stage-probability-weighted revenue projections; a founder would need to manually configure fields and dashboard aggregations to approximate this. Missing for 10: a native weighted-pipeline forecast report, explicit stage-probability calculation logic, and any hands-on evidence of this being used for revenue forecasting.", "evidenceIds": [ "twenty-docs-6", "twenty-docs-20", "twenty-docs-57", "twenty-docs-1", "twenty-docs-46" ] }, { "productId": "twenty", "storyId": "spreadsheet-import", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Docs describe CSV/XLSX/XLS import with column-to-field mapping, duplicate detection, and an error-review UI that highlights bad rows in yellow for in-place fixing rather than silent dropping, plus API-based bulk import for larger migrations. Missing for 10: independent/hands-on verification that no rows are silently lost during real-world large or messy imports, and no detail on what happens to unresolved/invalid rows beyond the UI flagging step.", "evidenceIds": [ "twenty-docs-9", "twenty-docs-27", "twenty-docs-28", "twenty-docs-37", "twenty-docs-45", "twenty-docs-59" ] }, { "productId": "twenty", "storyId": "two-way-email-sync", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Twenty's docs explicitly describe connecting Google Workspace or Microsoft 365 accounts so emails and calendar events automatically appear on and link to matching Company/People CRM records, with filters to control what gets imported. This is documented first-party functionality directly matching the story, though there is no independent/hands-on confirmation of two-way sync reliability specifically for email. Missing for 10: independent or hands-on verification of the email sync feature itself (the community evidence found only mentions general alpha rough edges, not this feature specifically).", "evidenceIds": [ "twenty-docs-4", "twenty-docs-15", "twenty-docs-52", "twenty-docs-58", "twenty-docs-47" ] }, { "productId": "twenty", "storyId": "visual-pipeline-stages", "verdict": "partial", "quality": 7, "confidence": "medium", "rationale": "Docs confirm kanban board views alongside table/calendar views, customizable fields/objects for building deal stages, and workflows that can trigger on stage changes (e.g., Slack alert when 'a deal reaches a certain stage'), which together support a visual pipeline with configurable stages. However, no evidence explicitly confirms drag-and-drop interaction on the kanban board itself, and community feedback flags the product as 'pretty alpha-version' with unspecified issues. Missing for 10: explicit documentation/screenshot of drag-and-drop card movement between stages, and independent hands-on confirmation that pipeline stage customization works smoothly in practice.", "evidenceIds": [ "twenty-docs-2", "twenty-docs-34", "twenty-docs-14", "twenty-docs-13", "twenty-comm-1" ] }, { "productId": "twenty", "storyId": "workflow-builder", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Twenty's docs directly describe trigger-based workflows (record changes, schedules, manual, webhooks) that can chain record operations, send email, HTTP requests, code, branches, and specifically cite examples like Slack alerts on deal stage changes and auto-enriching contacts, matching the ops story's update/create/notify pattern. Missing for 10: independent hands-on validation of workflow reliability in production (community evidence flags general 'alpha' rough edges) and no explicit dedicated 'create task' workflow action example beyond generic record operations.", "evidenceIds": [ "twenty-docs-3", "twenty-docs-13", "twenty-docs-14", "twenty-docs-35", "twenty-docs-42", "twenty-comm-1" ] } ]