[ { "productId": "agentmail", "storyId": "agent-email-end-to-end", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "AgentMail documents a hosted MCP server exposing inbox, message, thread, draft, and attachment tools, plus a full API/CLI for creating inboxes, reading/searching threads, drafting (with human-in-the-loop review), and sending messages with attachments — enabling any MCP-compatible agent (Claude, ChatGPT, custom) to triage and send email end to end. missing for 10: independent hands-on verification of an external agent completing a full read-triage-send workflow via the MCP connection (only vendor docs and probes confirm the endpoint, no third-party usage report).", "evidenceIds": [ "agentmail-docs-12", "agentmail-docs-23", "agentmail-probe-3", "agentmail-docs-16", "agentmail-docs-3", "agentmail-docs-5", "agentmail-docs-25", "agentmail-docs-4" ] }, { "productId": "agentmail", "storyId": "agentic-agent-docs", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "AgentMail hosts a live llms.txt file (verified HTTP 200) with a clear agent-oriented summary of its docs, and its entire documentation set is written in agent-consumable .md format (e.g., quickstart.md, messages.md) alongside an OpenAPI spec, MCP server, and CLI docs, making it easy for an agent to be pointed at and consume its docs. Missing for 10: no independent/community confirmation of an agent successfully navigating llms.txt end-to-end.", "evidenceIds": [ "agentmail-probe-1", "agentmail-probe-2", "agentmail-docs-1", "agentmail-probe-3" ] }, { "productId": "agentmail", "storyId": "agentic-ai-insights", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "AgentMail is an email infrastructure API for AI agents, not an analytics/insights product; the evidence shows email inbox/message/thread management, search, and MCP/CLI integrations but no AI-generated insights or suggestions surfaced from user data. This story is a category error for an email API product.", "evidenceIds": [] }, { "productId": "agentmail", "storyId": "agentic-autonomous-automation", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "AgentMail provides the building blocks for background automation—webhooks and persistent WebSocket connections that push email events in real time instead of requiring polling—so an agent can react autonomously to inbound mail without a human in the loop. However, AgentMail itself is just email infrastructure; there's no evidence of a built-in scheduler, workflow engine, or persistent agent runtime that executes autonomous logic—that has to be built by the user on top of the webhook/websocket feed. Missing for 10: evidence of a native scheduling/automation engine, documented autonomous background job execution, or independent confirmation that these mechanisms reliably drive unattended agent workflows.", "evidenceIds": [ "agentmail-docs-6", "agentmail-docs-19", "agentmail-docs-7", "agentmail-docs-20" ] }, { "productId": "agentmail", "storyId": "agentic-builtin-assistant", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "AgentMail is an email infrastructure/API product for building AI agents that use email, not a product with its own built-in AI assistant to delegate tasks to. The 'delegate tasks to a built-in AI assistant' axis is a category error here—AgentMail provides the plumbing (inboxes, MCP tools, webhooks) for external agents to use, but does not itself ship an assistant a user converses with.", "evidenceIds": [] }, { "productId": "agentmail", "storyId": "agentic-headless", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "AgentMail is fundamentally API/SDK-driven ('Create, manage, and operate email inboxes entirely via API'), with a documented OpenAPI spec, official CLI, and webhook/websocket event delivery that support scripted, non-interactive automation pipelines. No explicit CI/CD example or pipeline walkthrough is given, so full CI-specific validation is inferred rather than directly documented. Missing for 10: an explicit CI/CD pipeline example or GitHub Actions integration, and independent confirmation of headless use in production automation.", "evidenceIds": [ "agentmail-docs-14", "agentmail-docs-13", "agentmail-docs-6", "agentmail-docs-19", "agentmail-probe-2", "agentmail-probe-4" ] }, { "productId": "agentmail", "storyId": "agentic-mcp-client", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "AgentMail is an email infrastructure/API product for agents, not itself an agentic runtime that consumes external tools. Its only MCP-related capability is hosting its own MCP server so other agents can call AgentMail's tools (docs-12/23), not acting as an MCP client that plugs in third-party MCP servers — so this client-side story is a category error for this product.", "evidenceIds": [ "agentmail-docs-12", "agentmail-docs-23", "agentmail-probe-3" ] }, { "productId": "agentmail", "storyId": "agentic-mcp-server", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "AgentMail is a service/API product (not itself an agent), so the MCP-server axis applies, and docs confirm a hosted official MCP server at https://mcp.agentmail.to/mcp exposing inbox, message, thread, draft, and attachment tools to any compatible client, corroborated by a probe hit. Missing for 10: independent/hands-on confirmation that the MCP server works reliably in practice beyond first-party docs.", "evidenceIds": [ "agentmail-docs-12", "agentmail-docs-23", "agentmail-probe-3" ] }, { "productId": "agentmail", "storyId": "agentic-nl-commands", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "AgentMail exposes a hosted MCP server with inbox/message/thread/draft tools that lets any MCP-compatible AI agent operate the product via natural language, and also ships a CLI for no-code operations. However, there's no first-party chat/NL interface of its own, nor independent evidence of successful natural-language operation in practice. Missing for 10: hands-on demonstration of natural-language command execution, a dedicated conversational UI beyond MCP tool-calling.", "evidenceIds": [ "agentmail-docs-12", "agentmail-docs-23", "agentmail-docs-13", "agentmail-probe-3", "agentmail-probe-4" ] }, { "productId": "agentmail", "storyId": "agentic-official-cli", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "AgentMail documents an official CLI (docs.agentmail.to/integrations/cli) that lets users create inboxes, send messages, and manage threads without writing code, corroborated by a probe confirming the page exists. Missing for 10: no independent/community hands-on confirmation of CLI usage or installation details beyond the docs themselves.", "evidenceIds": [ "agentmail-docs-13", "agentmail-probe-4" ] }, { "productId": "agentmail", "storyId": "agentic-public-api", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "AgentMail is explicitly an API-first product: docs describe registering agents via API, creating inboxes, sending/searching messages, webhooks, permissions, etc., and a live OpenAPI spec is confirmed at docs.agentmail.to/openapi.json. This gives strong first-party and probe-verified evidence of a documented, comprehensive public API. Missing for 10: independent third-party hands-on validation of the API itself (community feedback focuses on website/pricing, not API usage).", "evidenceIds": [ "agentmail-docs-1", "agentmail-docs-14", "agentmail-probe-2", "agentmail-probe-1", "agentmail-docs-6" ] }, { "productId": "agentmail", "storyId": "agentic-scoped-keys", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Docs explicitly describe scoped API keys restricted to a single pod or inbox, per-customer pods with scoped keys for multi-tenancy, and a dedicated Permissions feature to restrict what an API key can do — directly matching the least-privilege credential story. Missing for 10: independent/hands-on verification that scoping actually enforces restrictions in practice, and detail on granularity of permission types beyond pod/inbox scope.", "evidenceIds": [ "agentmail-docs-9", "agentmail-docs-10", "agentmail-docs-24", "agentmail-docs-21" ] }, { "productId": "agentmail", "storyId": "agentic-sdks", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "AgentMail is fundamentally an API-first product with dedicated docs, OpenAPI spec, quickstart showing API key/SDK registration, and popovers showing SDK examples praised by a community reviewer, confirming real SDK-based building. Missing for 10: explicit list of language-specific SDKs (e.g. Python/TS/Go) and independent third-party developer testimonials beyond the dashboard praise.", "evidenceIds": [ "agentmail-docs-1", "agentmail-docs-14", "agentmail-probe-2", "agentmail-comm-7" ] }, { "productId": "agentmail", "storyId": "agentic-webhooks", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "AgentMail's docs explicitly support webhook subscriptions: registering a URL to receive POST requests on email events instead of polling, avoiding the need for constant API checks. This is a first-party documented, core feature directly matching the story. Missing for 10: independent/hands-on confirmation that webhooks work reliably in practice.", "evidenceIds": [ "agentmail-docs-6", "agentmail-docs-19" ] }, { "productId": "agentmail", "storyId": "ai-drafts-in-my-voice", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "AgentMail provides Draft objects and human-in-the-loop review (an agent can create a Draft for a human to approve before sending), but there is no evidence that AgentMail itself learns or applies the user's personal voice/tone when generating drafts — it is an email infrastructure/API for agents, not a personalization/writing-style engine.", "evidenceIds": [ "agentmail-docs-16", "agentmail-docs-4" ] }, { "productId": "agentmail", "storyId": "ai-inbox-answers", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "AgentMail is developer infrastructure (an email API/MCP server) for building agent-driven email workflows, not an end-user assistant that answers grounded questions across inbox and calendar. Evidence shows full-text search across threads and MCP tool exposure (docs-5, docs-12), but there is no calendar integration anywhere in the evidence, and no shipped assistant/chat interface that synthesizes 'who said what' or 'what's outstanding' answers for a user.", "evidenceIds": [ "agentmail-docs-5", "agentmail-docs-12", "agentmail-docs-14" ] }, { "productId": "agentmail", "storyId": "ai-triage-labels", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "AgentMail provides developer primitives (Labels, Lists, full-text search, webhooks) that a developer could use to build inbox triage, but there is no evidence of AgentMail itself performing AI-driven auto-labeling, categorization, or surfacing-what-needs-attention out of the box — Labels are described as manually tracked conversation states, not an automated triage engine, and no docs describe a built-in AI classifier or steerable/auditable triage policy.", "evidenceIds": [ "agentmail-docs-17", "agentmail-docs-18", "agentmail-docs-5", "agentmail-docs-6" ] }, { "productId": "agentmail", "storyId": "api-interactive-docs", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "AgentMail exposes a machine-readable OpenAPI spec (agentmail-probe-2) and its docs site includes language-switchable code snippets (Python/curl) plus SDK example popovers praised by users (agentmail-comm-2, agentmail-comm-7), suggesting an interactive reference. However, there is no evidence of a true 'try it now' runnable/executable API console, and independent reports note the docs site itself is slow and glitchy (agentmail-comm-1, agentmail-comm-3), undermining a smooth interactive experience. Missing for 10: confirmation of an actual runnable/sandboxed request execution feature, and resolution of the reported performance/UX issues on the docs site.", "evidenceIds": [ "agentmail-probe-2", "agentmail-comm-2", "agentmail-comm-7", "agentmail-comm-1", "agentmail-comm-3" ] }, { "productId": "agentmail", "storyId": "api-machine-spec", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "A probe confirms the OpenAPI spec is live and machine-readable at https://docs.agentmail.to/openapi.json (HTTP 200, contains \"openapi\" key), backed by documented API-first design. Missing for 10: no independent third-party corroboration of spec completeness or SDK auto-generation from it.", "evidenceIds": [ "agentmail-probe-2", "agentmail-docs-14" ] }, { "productId": "agentmail", "storyId": "api-sandbox", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence of a dedicated sandbox/test environment separate from production; the docs describe creating inboxes on-demand, but nothing indicates an isolated test mode that avoids touching real production data or sending real emails.", "evidenceIds": [] }, { "productId": "agentmail", "storyId": "api-versioning-policy", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows an OpenAPI spec and general API docs, but there is no mention anywhere of API versioning scheme or a documented deprecation policy for endpoints.", "evidenceIds": [] }, { "productId": "agentmail", "storyId": "assignment-and-routing", "verdict": "na", "quality": 0, "confidence": "medium", "rationale": "AgentMail is an email infrastructure API built for provisioning per-agent inboxes and automating agent-driven email flows, not a human shared-inbox/helpdesk tool with teammate assignment or ownership routing rules. Its team-oriented primitives (Pods, Labels, Lists, scoped API keys) are for tenant/agent segmentation and message-state tracking, not for a team-lead assigning conversations to human teammates.", "evidenceIds": [ "agentmail-docs-9", "agentmail-docs-17", "agentmail-docs-18" ] }, { "productId": "agentmail", "storyId": "automation-bulk-operations", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Docs confirm the platform is fully API-driven and explicitly supports creating 'tens, hundreds, or even thousands' of inboxes on demand, implying agents can script bulk creation, but there's no documented dedicated bulk/batch endpoint for messages, threads, or other items (e.g., bulk send, bulk label, bulk delete). Missing for 10: dedicated batch/bulk API endpoints for messages/threads, documented rate-limit or batching guidance, hands-on evidence of bulk operations at scale.", "evidenceIds": [ "agentmail-docs-2", "agentmail-docs-14", "agentmail-docs-13" ] }, { "productId": "agentmail", "storyId": "automation-rules-engine", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "AgentMail exposes event-driven infrastructure (webhooks and websockets) so external code can react to inbox events, and Lists provide simple automatic allow/block rules on senders/domains, but there's no built-in rule engine for defining conditional 'if X then do Y' automations inside the product itself — the actual rule logic must be implemented by the developer/agent consuming the webhook. missing for 10: a native rules/automation engine (e.g. conditional triggers on subject/content beyond allow-block lists), and independent confirmation that webhook-driven automation works reliably in production.", "evidenceIds": [ "agentmail-docs-6", "agentmail-docs-19", "agentmail-docs-7", "agentmail-docs-18", "agentmail-docs-17" ] }, { "productId": "agentmail", "storyId": "automation-scheduled-jobs", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "AgentMail is an email infrastructure/API product for agents (inboxes, messages, webhooks, MCP tools), not a workflow/job scheduling or automation-orchestration platform; scheduling recurring jobs is outside its product category and would be handled by an external orchestrator consuming its API.", "evidenceIds": [] }, { "productId": "agentmail", "storyId": "automation-versioned-workflows", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "AgentMail is an email API/infrastructure product for AI agents, not an automation-authoring platform with a build/version history; versioning, reviewing, and rolling back 'automations' is not a coherent concept for this product's category — it has no workflow/automation builder to version or roll back.", "evidenceIds": [] }, { "productId": "agentmail", "storyId": "beyond-email-channels", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "AgentMail is an email-only API/infrastructure product for AI agents; there is no evidence or claim of SMS, WhatsApp, social, or live-chat channel support—email is its sole channel by design, making this a category mismatch rather than a missing feature.", "evidenceIds": [] }, { "productId": "agentmail", "storyId": "bulk-triage-actions", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "AgentMail's docs describe programmatic labeling, threading, and search, but there is no evidence of any UI or bulk API operation for selecting many conversations at once and archiving/labeling/marking done in a single action; the product is positioned as an agent-facing API rather than a human triage inbox with bulk controls.", "evidenceIds": [ "agentmail-docs-17", "agentmail-docs-5" ] }, { "productId": "agentmail", "storyId": "calendar-inside-client", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "AgentMail is an email API/infrastructure product for AI agents, not a calendar or email client with a UI for viewing calendars or invites; the evidence only covers inbox/message/thread APIs, webhooks, MCP, and CLI tooling, with no calendar functionality mentioned. This is a category mismatch, not a missing feature.", "evidenceIds": [] }, { "productId": "agentmail", "storyId": "full-history-import", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "AgentMail is an email API/infrastructure product built for AI agents to create and operate inboxes programmatically, not a consumer mail client or migration tool; importing mail history/contacts from another provider is a category error for this product type.", "evidenceIds": [] }, { "productId": "agentmail", "storyId": "instant-search-operators", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Docs confirm full-text search across sender, recipients, subject, and body with relevance ranking, covering the core 'ranked results' and 'across full mail history' aspects. However, there's no evidence of specific search operators (e.g., date ranges, boolean logic) or advanced filters, and no independent benchmarking of speed/precision. missing for 10: documented search operators/filters syntax, evidence of performance at scale, independent verification of search speed/precision.", "evidenceIds": [ "agentmail-docs-5" ] }, { "productId": "agentmail", "storyId": "internal-comments-mentions", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "AgentMail is an email API/infrastructure product for AI agents, not a team collaboration or internal messaging tool; the story asks for internal side-thread commenting/@mentions features which are outside its product category (email inbox management API).", "evidenceIds": [] }, { "productId": "agentmail", "storyId": "keyboard-first-speed", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "AgentMail's docs focus entirely on API/SDK/CLI/webhook/MCP functionality for building agent email workflows; there is no mention anywhere of keyboard shortcuts, a command palette, or any interactive UI navigation features for power users. Community evidence actually describes the dashboard/website as laggy and slow to load (WebGL errors, noticeable lag vs. other sites), directly undercutting the 'fast enough to never wait' requirement even if such an interface existed.", "evidenceIds": [ "agentmail-comm-1", "agentmail-comm-2", "agentmail-comm-3", "agentmail-docs-13" ] }, { "productId": "agentmail", "storyId": "masked-aliases", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "AgentMail is a developer infrastructure product for giving AI agents email identities and inboxes, not a consumer privacy/alias-masking service for humans hiding their real address from sign-ups and strangers; the entire evidence pack is about agent inbox provisioning, APIs, webhooks, and multi-tenancy for building agent products, not personal alias/masked-address privacy protection.", "evidenceIds": [] }, { "productId": "agentmail", "storyId": "multi-account-unified", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "AgentMail is a developer API for provisioning and operating new email inboxes for AI agents, not a personal multi-account client for consolidating existing Gmail/Microsoft 365/IMAP accounts. Its IMAP/SMTP feature runs the opposite direction — letting external clients connect INTO an AgentMail-created inbox — not aggregating a switcher's pre-existing provider accounts into one interface, so the 'switcher consolidating accounts' story is a category mismatch for this product.", "evidenceIds": [ "agentmail-docs-8", "agentmail-docs-14" ] }, { "productId": "agentmail", "storyId": "offline-access", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "AgentMail is a cloud email API/service for AI agents, not an offline-capable client application; there is no concept of local offline access with sync-on-reconnect in this product category or evidence pack.", "evidenceIds": [] }, { "productId": "agentmail", "storyId": "open-protocol-access", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "AgentMail documents IMAP/SMTP compatibility, letting any standard mail client (Outlook, Thunderbird, Apple Mail) connect to an AgentMail inbox, which supports the open-protocol reachability part of the story. However, there is no mention of JMAP support or of a standards-based export/data-portability mechanism for migrating mail elsewhere. Missing for 10: JMAP protocol support, documented mailbox/data export or migration tooling, and independent confirmation that IMAP/SMTP access works reliably in practice.", "evidenceIds": [ "agentmail-docs-8" ] }, { "productId": "agentmail", "storyId": "openness-api-parity", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "AgentMail is explicitly API-first ('Create, manage, and operate email inboxes entirely via API'), with a documented OpenAPI spec, CLI, and MCP server all built atop the same API surface (inboxes, messages, threads, drafts, webhooks, attachments, permissions, pods) — no UI-exclusive features are mentioned anywhere in the docs. missing for 10: an explicit statement or independent test confirming 1:1 parity between the dashboard UI and API (e.g., that every dashboard action maps to a documented endpoint).", "evidenceIds": [ "agentmail-docs-14", "agentmail-probe-2", "agentmail-docs-13", "agentmail-probe-4", "agentmail-docs-9", "agentmail-docs-10", "agentmail-docs-24" ] }, { "productId": "agentmail", "storyId": "openness-full-export", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "AgentMail supports connecting standard IMAP/SMTP clients (Outlook, Thunderbird, Apple Mail), which gives users open-protocol access to their mailbox data rather than lock-in to a proprietary format, and the OpenAPI spec/CLI allow programmatic retrieval of messages. However there is no explicit documented 'export all data' or account-portability/data-takeout feature, and no evidence of exporting threads/attachments in bulk open formats. Missing for 10: explicit bulk export/backup tooling, documented data-portability guarantees, and confirmation of full account deletion with data takeout.", "evidenceIds": [ "agentmail-docs-8", "agentmail-probe-2", "agentmail-docs-13" ] }, { "productId": "agentmail", "storyId": "openness-open-license", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of AgentMail's source code being open or under an open-source license; it is a hosted API/SaaS product with documented API, SDKs, CLI, and MCP server but no mention of source availability or licensing.", "evidenceIds": [] }, { "productId": "agentmail", "storyId": "openness-self-host", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "AgentMail is presented entirely as a hosted API/SaaS product (docs describe hosted MCP server, hosted API, dashboards) with no documentation of a self-hosted deployment option; a community comment even notes a competitor markets itself as 'a self-hosted drop-in replacement' for AgentMail, implying AgentMail itself lacks this capability.", "evidenceIds": [ "agentmail-docs-14", "agentmail-docs-12", "agentmail-comm-9" ] }, { "productId": "agentmail", "storyId": "privacy-data-residency", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence in the pack mentions data residency, regional storage options, or compliance controls for choosing where data is stored; the docs cover inboxes, messaging, webhooks, MCP, and multi-tenancy but nothing about region selection.", "evidenceIds": [] }, { "productId": "agentmail", "storyId": "privacy-no-training", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence in the pack addresses data-training opt-out, AI model training policies, or privacy controls regarding use of email data for training; the docs focus on API/product functionality, not data-privacy commitments.", "evidenceIds": [] }, { "productId": "agentmail", "storyId": "privacy-retention-controls", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "The evidence pack covers AgentMail's inbox/messaging, permissions, and multi-tenancy features but contains no mention of data retention policies, deletion controls, or privacy/compliance settings for stored emails or attachments.", "evidenceIds": [] }, { "productId": "agentmail", "storyId": "privacy-telemetry-optout", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence in the pack mentions telemetry, usage tracking, analytics opt-out, or any privacy/data-collection controls for AgentMail; the docs and community items focus on email/API features, pricing, and site performance instead.", "evidenceIds": [] }, { "productId": "agentmail", "storyId": "read-statuses", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence anywhere in the pack mentions read receipts, open tracking, or delivery/open status for sent messages; AgentMail's docs cover inboxes, threads, webhooks, drafts, labels, etc., but nothing about tracking whether a recipient opened an email.", "evidenceIds": [] }, { "productId": "agentmail", "storyId": "scheduled-send-undo", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence anywhere in the pack of scheduled sending or an undo-send grace window; AgentMail's documented features cover inboxes, messages, drafts, threads, webhooks, and human-in-the-loop review, but nothing about delayed/scheduled send or send-cancellation.", "evidenceIds": [] }, { "productId": "agentmail", "storyId": "self-host-option", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "AgentMail is documented as a hosted email API/service (custom domains, hosted MCP server, webhooks) with no mention anywhere of a self-hosted deployment option; a competitor's marketing even highlights itself as the 'self-hosted drop-in replacement' for AgentMail, implying AgentMail itself is cloud-only.", "evidenceIds": [ "agentmail-docs-11", "agentmail-docs-12", "agentmail-comm-9" ] }, { "productId": "agentmail", "storyId": "share-availability", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "AgentMail is an email API/infrastructure product for AI agents to send/receive messages; it has no calendar or scheduling/availability features. Sharing availability or inserting bookable meeting times is a calendar-integration capability entirely outside its product category (email inbox management, not scheduling).", "evidenceIds": [] }, { "productId": "agentmail", "storyId": "shared-team-inbox", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "AgentMail's docs describe agent-centric inboxes, cc/bcc human-in-the-loop oversight, drafts for approval, and per-tenant Pods, but nothing indicates a shared inbox/team-channel experience where multiple human team members view the same conversation state together. No evidence of shared inbox dashboards, team member roles, or collaborative conversation views for a team-lead's team.", "evidenceIds": [ "agentmail-docs-4", "agentmail-docs-9", "agentmail-docs-16", "agentmail-docs-17", "agentmail-docs-21" ] }, { "productId": "agentmail", "storyId": "snippets-templates", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "AgentMail is an API/infrastructure product for agent-driven email (inboxes, messages, drafts, attachments, webhooks) with no evidence of a saved snippets/templates library or variable-substitution feature for composing replies; nothing in the docs mentions reusable templates or canned responses.", "evidenceIds": [] }, { "productId": "agentmail", "storyId": "snooze-and-reminders", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "AgentMail is an email API/infrastructure product for AI agents, not an inbox UI or triage tool with snooze/reminder scheduling features; this story applies to end-user email client apps, not a developer email API.", "evidenceIds": [] }, { "productId": "agentmail", "storyId": "split-inbox-triage", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "AgentMail is a developer-facing email API/infrastructure product for building AI-agent inboxes, not a human-facing email client with a personal triage UI; the story assumes an end-user inbox view split into priority streams, which is a different product category. Labels/Lists exist as programmable primitives an agent developer could use, but there is no evidence of a shipped power-user inbox-triage UI, so this axis doesn't fit the product's role.", "evidenceIds": [ "agentmail-docs-17", "agentmail-docs-18" ] }, { "productId": "agentmail", "storyId": "tracker-blocking", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "AgentMail is an email API/infrastructure product for AI agents, not a consumer email client that a 'switcher' persona would adopt to protect against sender tracking pixels; the story's framing (client-side anti-tracking, pixel blocking) is a wrong axis for this developer-facing API product.", "evidenceIds": [] }, { "productId": "fastmail", "storyId": "agent-email-end-to-end", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Fastmail exposes a fully documented JMAP API with OAuth2/Bearer token auth and API tokens (fastmail-docs-1,2,5,38,41) that could let a custom-built agent read, query, and send mail via standard HTTP, satisfying the 'my own agent' case. But there is no evidence of an official MCP server, ChatGPT/Claude connector, or any first-party documented integration enabling Claude or ChatGPT specifically to triage/draft/send end-to-end — probes for llms.txt and OpenAPI discovery both returned 404 (fastmail-probe-1, fastmail-probe-2). Missing for 10: official MCP server or Claude/ChatGPT plugin, documented end-to-end agent workflow (triage+draft+send), and independent evidence of an AI agent actually operating through this API.", "evidenceIds": [ "fastmail-docs-1", "fastmail-docs-2", "fastmail-docs-5", "fastmail-docs-38", "fastmail-docs-41", "fastmail-probe-1", "fastmail-probe-2" ] }, { "productId": "fastmail", "storyId": "agentic-agent-docs", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "A direct probe confirms no llms.txt exists (404) and no openapi/agent-oriented discovery docs were found either; while JMAP API docs exist, there is no evidence of an llms.txt or agent-oriented documentation entry point.", "evidenceIds": [ "fastmail-probe-1", "fastmail-probe-2" ] }, { "productId": "fastmail", "storyId": "agentic-ai-insights", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of any AI-generated insights, summaries, or suggestions within Fastmail's product; the evidence pack covers JMAP protocol, filters, search, aliases, masked email, and other traditional email features but nothing about AI-driven analysis of user data.", "evidenceIds": [] }, { "productId": "fastmail", "storyId": "agentic-autonomous-automation", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Fastmail's Filters & Rules feature provides server-side automation that runs autonomously in the background without user intervention, and JMAP API tokens plus EventSource/WebPush push notifications allow building custom automated workflows (e.g., an agent reacting to new mail events). However, there is no evidence of purpose-built AI-agent automation tooling, scheduled/triggered agent workflows, or third-party AI automation integrations. Missing for 10: dedicated AI/agent automation framework or examples, evidence of autonomous multi-step workflows beyond simple filters, independent confirmation of using JMAP for agentic background tasks.", "evidenceIds": [ "fastmail-docs-6", "fastmail-docs-28", "fastmail-docs-3", "fastmail-docs-19", "fastmail-docs-5", "fastmail-docs-22", "fastmail-docs-38" ] }, { "productId": "fastmail", "storyId": "agentic-builtin-assistant", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is \"none\", never \"na\". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)", "evidenceIds": [] }, { "productId": "fastmail", "storyId": "agentic-headless", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Fastmail exposes a documented JMAP API and API tokens/OAuth for programmatic access (fastmail-docs-1,2,5,22,40), and community evidence confirms it can be driven via SMTP/app passwords for scripted/automated sending (fastmail-comm-11), which supports headless use in scripts or CI. However, there is no explicit CI/headless-mode documentation, no official CLI, and community feedback notes it isn't built for large-scale automated/transactional use. Missing for 10: dedicated CI/automation documentation or examples, an official CLI, and confirmation of headless reliability at scale.", "evidenceIds": [ "fastmail-docs-1", "fastmail-docs-2", "fastmail-docs-5", "fastmail-docs-40", "fastmail-comm-11" ] }, { "productId": "fastmail", "storyId": "agentic-mcp-client", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is \"none\", never \"na\". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)", "evidenceIds": [] }, { "productId": "fastmail", "storyId": "agentic-mcp-server", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Fastmail exposes JMAP and API tokens for developers, but there is no evidence of an official MCP server or endpoint that lets AI agents connect natively; probes for machine-readable spec files (llms.txt, openapi) both return 404.", "evidenceIds": [ "fastmail-docs-1", "fastmail-docs-5", "fastmail-probe-1", "fastmail-probe-2" ] }, { "productId": "fastmail", "storyId": "agentic-nl-commands", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of any natural-language command interface, chat assistant, or NL-to-action layer in Fastmail; the product exposes a structured JMAP API and traditional GUI/keyboard shortcuts, not NL commands. Probes for llms.txt and OpenAPI (which could hint at AI-native tooling) returned 404s, further indicating absence.", "evidenceIds": [ "fastmail-probe-1", "fastmail-probe-2", "fastmail-docs-8" ] }, { "productId": "fastmail", "storyId": "agentic-official-cli", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Evidence shows JMAP API, tokens, and OAuth support, but there is no mention of an official CLI tool for Fastmail; probes for llms.txt/openapi also returned 404s, and no CLI is referenced anywhere in docs or community posts.", "evidenceIds": [] }, { "productId": "fastmail", "storyId": "agentic-public-api", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Fastmail publishes JMAP, an open, documented API protocol with a discoverable session endpoint, standard OAuth2/Bearer auth, API tokens, push via EventSource/WebPush, and a dedicated dev docs page (fastmail.com/dev), giving AI-native users a clear, standards-based way to programmatically drive the product. Missing for 10: no evidence of an OpenAPI/Swagger spec or llms.txt (probes returned 404s) and no independent third-party corroboration of API robustness beyond vendor docs.", "evidenceIds": [ "fastmail-docs-1", "fastmail-docs-2", "fastmail-docs-3", "fastmail-docs-4", "fastmail-docs-5", "fastmail-docs-38", "fastmail-docs-40", "fastmail-docs-41" ] }, { "productId": "fastmail", "storyId": "agentic-scoped-keys", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Fastmail provides API tokens (fastmail-docs-5/22) and OAuth2/Bearer token support (fastmail-docs-2/41) for JMAP access, and community evidence confirms real-world scoped 'app passwords' limited to a single protocol like SMTP (fastmail-comm-11), showing least-privilege credential issuance works in practice. However, the docs are only titles with no detail on fine-grained scope configuration for agent-specific use cases, and there's no explicit agent/AI-oriented credential guidance. Missing for 10: detailed scope/permission granularity documentation, explicit agent-use-case guidance, and independent hands-on verification of scoping API tokens (not just app passwords) for AI agents.", "evidenceIds": [ "fastmail-docs-5", "fastmail-docs-22", "fastmail-docs-2", "fastmail-docs-41", "fastmail-comm-11" ] }, { "productId": "fastmail", "storyId": "agentic-sdks", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Fastmail documents the JMAP protocol and a developer API page, but the evidence never mentions any official SDKs (client libraries) for languages/frameworks — only raw protocol specs, API tokens, and a dev docs page. Probes for machine-readable API discovery (llms.txt, openapi) also 404, reinforcing the absence of packaged SDK tooling.", "evidenceIds": [ "fastmail-docs-40", "fastmail-docs-5", "fastmail-probe-1", "fastmail-probe-2" ] }, { "productId": "fastmail", "storyId": "agentic-webhooks", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Fastmail's JMAP API supports push/event notification via EventSource (SSE) and WebPush, which lets clients subscribe to mailbox changes without polling — a webhook-adjacent mechanism (docs-3, docs-19). However, there's no explicit documentation of a classic webhook (HTTP callback URL registration) API, and no independent/hands-on confirmation of setting up such subscriptions. Missing for 10: explicit webhook callback-URL registration docs, third-party confirmation of push reliability, and any mention of 'webhook' terminology in official docs.", "evidenceIds": [ "fastmail-docs-3", "fastmail-docs-19", "fastmail-docs-38", "fastmail-docs-40" ] }, { "productId": "fastmail", "storyId": "ai-drafts-in-my-voice", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence anywhere in the pack of AI-drafted replies, tone/voice matching, or generative reply features; Fastmail's evidence covers JMAP API, templates, filters, and general email management, not AI drafting.", "evidenceIds": [] }, { "productId": "fastmail", "storyId": "ai-inbox-answers", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "There is no evidence of any Fastmail-native AI assistant, chat interface, or grounded Q&A feature over inbox/calendar content; evidence only covers JMAP API access, standard mail features, and general product satisfaction. A third party could build such an assistant using JMAP/API tokens, but no evidence shows Fastmail itself offers this capability.", "evidenceIds": [ "fastmail-docs-1", "fastmail-docs-5", "fastmail-docs-40" ] }, { "productId": "fastmail", "storyId": "ai-triage-labels", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Evidence covers Fastmail's rule-based Filters & Rules, search, and JMAP API access, but there is no mention of AI-driven triage, auto-labeling, categorization, or a steerable/auditable AI assistant surfacing important emails. Absence of evidence for this applicable capability means it does not deliver the story.", "evidenceIds": [ "fastmail-docs-6", "fastmail-docs-28", "fastmail-docs-7" ] }, { "productId": "fastmail", "storyId": "api-interactive-docs", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Fastmail provides JMAP protocol documentation and a developer docs page (fastmail-docs-40), but there is no evidence of an interactive API reference with runnable/try-it-now examples; probes for OpenAPI/Swagger specs and llms.txt both returned 404s (fastmail-probe-1, fastmail-probe-2), indicating no such interactive tooling exists.", "evidenceIds": [ "fastmail-docs-40", "fastmail-probe-1", "fastmail-probe-2" ] }, { "productId": "fastmail", "storyId": "api-machine-spec", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "Fastmail's JMAP protocol provides a machine-readable session/capabilities discovery endpoint (/.well-known/jmap) and points to formal JMAP specs, plus a general 'API Documentation' page, which partially satisfies the spirit of a machine-readable API description even though it isn't an OpenAPI document. However, direct probes for openapi.json/swagger.json/llms.txt all return 404, showing no actual downloadable OpenAPI-equivalent artifact is published. Missing for 10: an actual downloadable OpenAPI/Swagger/JSON-Schema file, confirmation that fastmail.com/dev/ hosts a structured machine-readable spec rather than prose docs, and independent verification of spec completeness.", "evidenceIds": [ "fastmail-docs-1", "fastmail-docs-40", "fastmail-probe-1", "fastmail-probe-2" ] }, { "productId": "fastmail", "storyId": "api-sandbox", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of a sandbox, staging, or test environment for developers to use with the JMAP API separate from production data; docs only describe production API access via OAuth/Bearer tokens.", "evidenceIds": [] }, { "productId": "fastmail", "storyId": "api-versioning-policy", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows Fastmail's JMAP API and documentation (session discovery, OAuth, API tokens, dev docs) but no mention of API versioning scheme or a documented deprecation policy; probes for openapi/llms.txt also 404, suggesting no machine-readable spec exists either.", "evidenceIds": [ "fastmail-docs-1", "fastmail-docs-40", "fastmail-probe-1", "fastmail-probe-2" ] }, { "productId": "fastmail", "storyId": "assignment-and-routing", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Fastmail's docs confirm mail routing via Filters & Rules, which lets a team-lead direct incoming mail to specific folders/addresses, but there is no evidence of any conversation-assignment feature (assigning a thread to a specific teammate with ownership tracking) anywhere in the pack. Missing for 10: conversation/ticket assignment to teammates, ownership/status indicators, any shared-inbox collaboration UI beyond basic filters.", "evidenceIds": [ "fastmail-docs-6", "fastmail-docs-28" ] }, { "productId": "fastmail", "storyId": "automation-bulk-operations", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "JMAP's design (single HTTP request with a `methodCalls` array for query/fetch/send, fastmail-docs-38) inherently supports batching many operations together, and filters/rules (fastmail-docs-6) allow rule-based bulk processing of mail. However, there's no explicit documentation of a bulk-update/bulk-delete API pattern, no example of bulk operations across large item sets, and no independent evidence of this being used for AI-native bulk workflows. Missing for 10: explicit bulk operation API examples (e.g., bulk delete/move across many message IDs), documented limits/performance for large batches, and independent confirmation of successful bulk automation use.", "evidenceIds": [ "fastmail-docs-38", "fastmail-docs-6", "fastmail-docs-4" ] }, { "productId": "fastmail", "storyId": "automation-rules-engine", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Fastmail's Filters & Rules feature lets users define rule-based automations (e.g., move/tag/forward on incoming mail conditions), which satisfies a basic version of 'rules trigger actions on events.' However, this is a traditional email-filter system, not framed for AI-native/agentic use, and there's no evidence of programmatic rule creation via API/JMAP, webhook-triggered actions, or AI-specific automation hooks beyond generic push/EventSource notifications. Missing for 10: API-driven rule creation/management, AI-agent-specific triggers or actions, and richer automation beyond mail filtering.", "evidenceIds": [ "fastmail-docs-6", "fastmail-docs-28", "fastmail-docs-3", "fastmail-comm-5" ] }, { "productId": "fastmail", "storyId": "automation-scheduled-jobs", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence of scheduling recurring jobs/workflows; only email-specific automation like Filters & Rules, Scheduled Send (one-time), and Snooze are documented, none of which support recurring automated workflows or job scheduling via API/JMAP. missing for 10: recurring job/workflow scheduler, cron-like automation, evidence of JMAP being used to trigger scheduled/recurring tasks.", "evidenceIds": [ "fastmail-docs-6", "fastmail-docs-17", "fastmail-docs-supp-1" ] }, { "productId": "fastmail", "storyId": "automation-versioned-workflows", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of any versioning, review, or rollback mechanism for automations (e.g., Filters & Rules history, change logs, or undo for automation configs); Fastmail's docs cover creating filters but nothing about version control or reverting changes.", "evidenceIds": [ "fastmail-docs-6", "fastmail-docs-28" ] }, { "productId": "fastmail", "storyId": "beyond-email-channels", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is \"none\", never \"na\". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)", "evidenceIds": [] }, { "productId": "fastmail", "storyId": "bulk-triage-actions", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Fastmail's documented Keyboard Shortcuts and Filters & Rules pages imply an interface that supports quick, multi-message actions, but no citation explicitly describes selecting multiple conversations for bulk archive/label/mark-done in one action. missing for 10: explicit documentation or hands-on evidence of multi-select checkboxes, bulk archive/label/mark-done actions, and confirmation of conversation-view group actions.", "evidenceIds": [ "fastmail-docs-8", "fastmail-docs-27", "fastmail-docs-6", "fastmail-docs-28" ] }, { "productId": "fastmail", "storyId": "calendar-inside-client", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Fastmail's docs confirm built-in Calendar with event and invitation handling directly in the mail/webmail client (fastmail-docs-14/34), and JMAP supports calendar via CalDAV replacement (fastmail-docs-42), consistent with an integrated calendar app alongside email. However, evidence lacks hands-on/community confirmation of the invite-response and event-creation UX specifically. Missing for 10: independent/community corroboration of calendar RSVP and event-creation workflow, and detail on UI integration depth.", "evidenceIds": [ "fastmail-docs-14", "fastmail-docs-34", "fastmail-docs-42" ] }, { "productId": "fastmail", "storyId": "full-history-import", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Fastmail has a documented 'Import your mail' tool plus IMAP fetch/forwarding options for migrating mail from other providers, and community reports confirm an easy migration tool and IMAP-based fetching from Gmail. However, evidence does not clearly cover contacts import, and community feedback flags that filters/rules migration is notably harder ('migrating filters and rules over on the other hand...'). Missing for 10: explicit contacts-import documentation, confirmation of complete mail history fidelity, and stronger independent verification of a smooth full-history+contacts migration.", "evidenceIds": [ "fastmail-docs-13", "fastmail-docs-25", "fastmail-comm-4", "fastmail-comm-5", "fastmail-docs-24" ] }, { "productId": "fastmail", "storyId": "instant-search-operators", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Fastmail has a dedicated 'Searching your mail' help article confirming search is a first-class feature, and JMAP's fast query/fetch model implies backend efficiency, but the evidence pack never details actual search operators, filter syntax, ranking behavior, or performance across full mail history. missing for 10: documented search operator syntax (from:, subject:, has:attachment etc.), evidence of ranked/relevance-based results, benchmarks or user reports on search speed across large mail archives, independent corroboration of search precision.", "evidenceIds": [ "fastmail-docs-7", "fastmail-docs-37", "fastmail-docs-4", "fastmail-docs-38" ] }, { "productId": "fastmail", "storyId": "internal-comments-mentions", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of any internal comment/annotation or @mention feature attached to emails in Fastmail; evidence only covers standard email features (filters, search, aliases, JMAP protocol) and none mention side-thread discussion or team collaboration around a message.", "evidenceIds": [] }, { "productId": "fastmail", "storyId": "keyboard-first-speed", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Fastmail documents a dedicated keyboard shortcuts feature and JMAP-based sync architecture emphasizing speed, and community feedback corroborates the interface being notably fast ('a ton faster' than alternatives). However, there is no evidence of a command palette or comprehensive shortcut coverage claims, and no hands-on confirmation of full keyboard-only operation. Missing for 10: explicit command-palette feature, evidence of exhaustive/comprehensive shortcut coverage beyond a single help article, independent benchmarking of UI responsiveness under load.", "evidenceIds": [ "fastmail-docs-8", "fastmail-docs-27", "fastmail-docs-4", "fastmail-comm-6", "fastmail-comm-13" ] }, { "productId": "fastmail", "storyId": "masked-aliases", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Fastmail's Masked Email feature (fastmail-docs-18/29) directly delivers per-signup masked addresses so real address stays hidden, plus separate alias setup docs (fastmail-docs-12/36), and community testimony confirms real-world use for throwaway/sketchy sites (fastmail-comm-1). missing for 10: independent hands-on verification of masked-email creation flow beyond docs and a single community mention, and no detail on limits/edge cases of masked addresses.", "evidenceIds": [ "fastmail-docs-18", "fastmail-docs-29", "fastmail-docs-12", "fastmail-docs-36", "fastmail-comm-1" ] }, { "productId": "fastmail", "storyId": "multi-account-unified", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Fastmail explicitly documents importing mail from other providers and 'fetching mail from Gmail like a mail client' (IMAP-style pull), plus a 'Logging in to multiple accounts' feature and a dedicated Gmail-migration guide, and community reports confirm smooth Gmail-to-Fastmail migrations. However, evidence never mentions Microsoft 365/Exchange connectivity specifically, doesn't show a true unified single-inbox view merging external accounts (vs. separate logins), and one commenter notes migrating filters/rules doesn't come over cleanly. Missing for 10: explicit Microsoft 365/M365 account linking, detail on whether multiple accounts appear merged in one inbox view, and independent verification of multi-provider IMAP account aggregation beyond Gmail.", "evidenceIds": [ "fastmail-comm-4", "fastmail-comm-5", "fastmail-docs-13", "fastmail-docs-15", "fastmail-docs-24" ] }, { "productId": "fastmail", "storyId": "offline-access", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Fastmail has a dedicated 'Offline support' help article and a documented behavior detail (snoozed messages only reappear once back online, implying local caching + resync), which supports reading/writing offline with sync on reconnect. However, the evidence pack only gives titles/snippets, not confirmation that full-text search works offline or exactly how conflict resolution/sync works, and there's no independent hands-on test confirming offline compose/search reliability. Missing for 10: detailed doc content on offline search, independent verification of offline write/compose queuing and reconnection sync behavior, and confirmation across web/mobile clients.", "evidenceIds": [ "fastmail-docs-16", "fastmail-docs-33", "fastmail-docs-supp-2", "fastmail-docs-4" ] }, { "productId": "fastmail", "storyId": "open-protocol-access", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Fastmail documents JMAP (open standard) and IMAP/SMTP access via API tokens/app passwords, plus import/export tooling for migration, and community reports confirm SMTP/IMAP interoperability with other providers (e.g., fetching Gmail via IMAP, app passwords for SMTP). This directly supports open-protocol reachability and avoiding lock-in. Missing for 10: explicit documentation of full mail export/backup format standards (e.g., mbox/EML export) and independent verification of IMAP feature parity beyond anecdotal mentions.", "evidenceIds": [ "fastmail-docs-1", "fastmail-docs-21", "fastmail-docs-23", "fastmail-docs-5", "fastmail-docs-13", "fastmail-comm-4", "fastmail-comm-11", "fastmail-comm-5" ] }, { "productId": "fastmail", "storyId": "openness-api-parity", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Fastmail's JMAP API is well-documented for core mail operations (session discovery, OAuth, push via EventSource, single-roundtrip method calls) and JMAP also natively covers contacts/calendar, giving broad coverage beyond typical webmail APIs. However, the evidence never confirms API parity for many UI-only features referenced in docs (masked email management, snooze, templates, filters/rules configuration, scheduled send) — these are documented as UI/help features without corresponding API examples. missing for 10: explicit API endpoints/examples for masked email, snooze, filters, templates, scheduled send parity; independent developer confirmation that all UI actions are API-reachable.", "evidenceIds": [ "fastmail-docs-1", "fastmail-docs-4", "fastmail-docs-38", "fastmail-docs-40", "fastmail-docs-18", "fastmail-docs-6", "fastmail-docs-supp-1" ] }, { "productId": "fastmail", "storyId": "openness-full-export", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Fastmail's evidence shows JMAP is an open, non-proprietary standard with full API access (session object, method calls, OAuth tokens) that could in principle be used to pull out all mail data, and there's a dedicated 'Open source and standards' page, but there is no explicit documentation of a one-click full data export/backup feature (mail+contacts+calendar) for leaving the service — only 'Import your mail' guidance is evidenced. missing for 10: documented full-account export/backup tool covering mail, contacts, and calendar; explicit data-portability/GDPR export docs; independent confirmation of successful full export.", "evidenceIds": [ "fastmail-docs-21", "fastmail-docs-23", "fastmail-docs-1", "fastmail-docs-40", "fastmail-docs-13" ] }, { "productId": "fastmail", "storyId": "openness-open-license", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Fastmail is a proprietary commercial email service; while it supports open standards like JMAP and has a page titled 'Open source and standards' (fastmail-docs-23), there is no evidence that Fastmail's own product source code is published under an open license for users/AI agents to read.", "evidenceIds": [ "fastmail-docs-23", "fastmail-docs-21" ] }, { "productId": "fastmail", "storyId": "openness-self-host", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is \"none\", never \"na\". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)", "evidenceIds": [] }, { "productId": "fastmail", "storyId": "privacy-data-residency", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "The evidence pack contains no mention of data residency, regional storage options, or where Fastmail's servers/data centers are located; nothing addresses letting users choose a storage region. missing for 10: any documentation of regional data residency options, data center locations, or user controls for choosing where data is stored.", "evidenceIds": [] }, { "productId": "fastmail", "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 explicit privacy commitment regarding AI model training on user email data. missing for 10: any AI-training data policy, opt-out mechanism, or explicit statement that user data is not used to train AI models.", "evidenceIds": [] }, { "productId": "fastmail", "storyId": "privacy-retention-controls", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence pack items address data retention policies, account deletion, data export/erasure controls, or AI-specific data handling for training/processing. The pack covers JMAP API, features, and general reviews but nothing on retention/deletion controls.", "evidenceIds": [] }, { "productId": "fastmail", "storyId": "privacy-telemetry-optout", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence pack item discusses telemetry, usage tracking, analytics opt-out, or any privacy settings specific to AI-native data collection controls; the docs focus on JMAP/API features and general email functionality.", "evidenceIds": [] }, { "productId": "fastmail", "storyId": "read-statuses", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence in the pack mentions read receipts, delivery/open tracking, or any similar feature in Fastmail's composing/sending tools or documentation.", "evidenceIds": [] }, { "productId": "fastmail", "storyId": "scheduled-send-undo", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Fastmail has dedicated first-party docs for both 'Scheduled Send' and 'Undo send' features, directly matching the story's requirements. Missing for 10: independent/hands-on corroboration of the undo grace-window mechanics or scheduling UX details beyond doc titles.", "evidenceIds": [ "fastmail-docs-17", "fastmail-docs-10", "fastmail-docs-30", "fastmail-docs-31" ] }, { "productId": "fastmail", "storyId": "self-host-option", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is \"none\", never \"na\". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)", "evidenceIds": [] }, { "productId": "fastmail", "storyId": "share-availability", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence only shows generic 'Calendar events and invitations' documentation (RSVP/invite handling) with no mention of an availability-sharing or booking-link feature akin to scheduling assistants; no docs or community reports describe inserting bookable meeting slots into emails.", "evidenceIds": [ "fastmail-docs-14", "fastmail-docs-34" ] }, { "productId": "fastmail", "storyId": "shared-team-inbox", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "Evidence covers JMAP protocol, personal productivity features, and multi-account login, but there is no mention of shared inboxes, team channels, or shared conversation state features for teams. Fastmail's docs reference 'Logging in to multiple accounts' which is about one user accessing several separate accounts, not shared team visibility into the same inbox.", "evidenceIds": [ "fastmail-docs-15", "fastmail-docs-26" ] }, { "productId": "fastmail", "storyId": "snippets-templates", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Fastmail documents a dedicated \"Templates\" feature for saved replies, supporting the core ask of inserting canned text instead of retyping, but the evidence pack gives only the article title with no detail on variable substitution or attachment inclusion. missing for 10: documentation confirming template variables (e.g. name/date placeholders), attachment support within templates, and any independent/hands-on confirmation of these specifics.", "evidenceIds": [ "fastmail-docs-9", "fastmail-docs-32" ] }, { "productId": "fastmail", "storyId": "snooze-and-reminders", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Fastmail's docs confirm a snooze feature that resurfaces messages at a chosen time, including behavior when offline, which covers the 'snooze conversations' half of the story. However there is no evidence of a 'nudge'/follow-up reminder that resurfaces a thread specifically if nobody replies — snoozing is time-based, not reply-tracking. missing for 10: evidence of a no-reply-triggered follow-up reminder feature, independent confirmation of snooze behavior beyond the offline-support note.", "evidenceIds": [ "fastmail-docs-supp-1", "fastmail-docs-supp-2" ] }, { "productId": "fastmail", "storyId": "split-inbox-triage", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Fastmail's Filters & Rules can route mail (e.g. newsletters, calendar invites) into separate folders/labels, and saved searches let a power-user build custom views, giving a rough approximation of prioritized streams — but the evidence never shows a dedicated multi-pane/tabbed 'focused inbox' UI or explicit stream-based triage ordering like Gmail's Priority Inbox or Outlook's Focused Inbox. missing for 10: a documented feature for simultaneous multi-stream inbox views, automatic 'important' classification, and evidence of ordering triage by priority rather than by folder/search separately.", "evidenceIds": [ "fastmail-docs-6", "fastmail-docs-28", "fastmail-docs-7", "fastmail-docs-37", "fastmail-docs-14", "fastmail-docs-34" ] }, { "productId": "fastmail", "storyId": "tracker-blocking", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack mentions blocking tracking pixels/read receipts, image proxying, or any specific transparency documentation about mail data handling; general privacy sentiment from community comments (fastmail-comm-3) is too vague to establish this specific capability.", "evidenceIds": [] }, { "productId": "missive", "storyId": "agent-email-end-to-end", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Missive documents an official MCP server (missive-probe-4) that lets external AI apps like Claude, ChatGPT, or Cursor connect and act on conversations, contacts, calendar, and drafts with configurable permissions (missive-docs-1, missive-docs-20), including summarizing inboxes, drafting replies, and triaging conversations against a CRM (missive-docs-21, missive-docs-22). However, explicit end-to-end 'send' capability via the agent is not directly documented, and there is no independent/hands-on corroboration of the full read-triage-draft-send loop working in practice. Missing for 10: explicit documentation of agent-initiated sending (not just drafting), and third-party/hands-on verification of the full workflow.", "evidenceIds": [ "missive-docs-1", "missive-docs-20", "missive-docs-21", "missive-docs-22", "missive-docs-27", "missive-docs-42", "missive-probe-4" ] }, { "productId": "missive", "storyId": "agentic-agent-docs", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Direct probes show no llms.txt, no docs.md, and no OpenAPI spec exposed at expected locations (all 404), and no evidence of agent-oriented documentation formats being offered elsewhere; while Missive has an MCP server (a different axis), there's no proof an agent can be pointed at llms.txt or similar agent-readable docs.", "evidenceIds": [ "missive-probe-1", "missive-probe-2", "missive-probe-3" ] }, { "productId": "missive", "storyId": "agentic-ai-insights", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Missive's AI assistant can summarize inboxes, draft replies, and triage conversations against connected data (CRM, docs) via MCP, and can compose/reply/translate with AI, which counts as AI-generated insights/suggestions from data. However, evidence is mostly marketing copy without hands-on demonstration of proactive 'insights' (e.g., analytics-driven suggestions) and no independent corroboration of quality or accuracy. missing for 10: independent/hands-on verification of insight quality, concrete examples of proactive analytics-style insights beyond summarization/drafting, and detail on how suggestions are surfaced in UI.", "evidenceIds": [ "missive-docs-21", "missive-docs-22", "missive-docs-49", "missive-docs-16", "missive-docs-27" ] }, { "productId": "missive", "storyId": "agentic-autonomous-automation", "verdict": "partial", "quality": 7, "confidence": "medium", "rationale": "Missive documents rule-based workflow automation (up to 1000 rules) and long-running AI assistant sessions that operate in the background with a session tab showing progress ('no longer need babysitting'), plus agent-driven triage of conversations against a CRM before a human looks at them — evidence of autonomous background automation. However, there's no independent/hands-on confirmation of reliability or scope of autonomy, and details on triggers/scheduling for rules are thin. Missing for 10: independent corroboration of autonomous execution reliability, deeper documentation on rule triggers/scheduling and failure handling.", "evidenceIds": [ "missive-docs-11", "missive-docs-25", "missive-docs-36", "missive-docs-2", "missive-docs-34", "missive-docs-22", "missive-docs-20" ] }, { "productId": "missive", "storyId": "agentic-builtin-assistant", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Missive documents a built-in AI Assistant/Copilot that can compose, reply, translate, triage conversations against CRM data, and run extended 'sessions' with a visible status tab, plus access internal tools via MCP — all delegatable from within the product (missive-docs-49, missive-docs-34, missive-docs-22, missive-docs-16, missive-docs-52). Missing for 10: independent/hands-on evidence of actual task delegation outcomes and more detail on assistant capabilities/limits beyond first-party changelog blurbs.", "evidenceIds": [ "missive-docs-49", "missive-docs-34", "missive-docs-22", "missive-docs-16", "missive-docs-52", "missive-docs-2", "missive-docs-21" ] }, { "productId": "missive", "storyId": "agentic-headless", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Missive exposes a REST API, webhooks, and a documented MCP server that let external systems and AI agents trigger actions without using the UI, which could be scripted from CI/automation pipelines. However there is no evidence of an official CLI, headless mode, Docker/container deployment, or CI-specific documentation/examples for running Missive itself in automated pipelines. Missing for 10: dedicated CLI or headless execution mode, CI/CD integration guides, and independent confirmation of automation-in-CI use cases.", "evidenceIds": [ "missive-docs-31", "missive-docs-15", "missive-docs-11", "missive-docs-47", "missive-probe-4" ] }, { "productId": "missive", "storyId": "agentic-mcp-client", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Missive documents a clear custom-MCP flow: users add a 'Custom MCP' server with a URL and auth, and 'connect any MCP-compatible server to Missive's AI Copilot' to let the assistant use internal APIs, databases, or custom tooling, alongside pre-built MCP integrations (Notion, Linear, Attio, Lindy.ai). Missing for 10: independent/hands-on verification of the custom MCP connection flow beyond vendor docs, and more detail on tool invocation limits or reliability.", "evidenceIds": [ "missive-docs-16", "missive-docs-17", "missive-docs-18", "missive-docs-27", "missive-docs-42", "missive-intdir-1", "missive-intdir-2" ] }, { "productId": "missive", "storyId": "agentic-mcp-server", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "Missive explicitly documents an official MCP server that lets external AI apps (Claude, ChatGPT, Cursor) connect and act on conversations, contacts, calendar, and drafts with configurable permissions, and a dedicated docs page for the MCP server is confirmed to exist via probe. Missing for 10: independent/hands-on third-party confirmation that external agents successfully connect and operate via this server.", "evidenceIds": [ "missive-docs-1", "missive-docs-20", "missive-probe-4", "missive-docs-47" ] }, { "productId": "missive", "storyId": "agentic-nl-commands", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Missive's AI Assistant/Copilot and MCP integration let users issue natural-language requests (e.g., 'Ask Claude to summarize your inbox and draft replies,' 'compose, reply, and translate messages with AI') and let external AI apps act on conversations, contacts, calendar, and drafts through natural language via Claude/ChatGPT/Cursor. The command bar also supports quick text-based commands for actions like snoozing. Missing for 10: independent/hands-on user validation of natural-language accuracy and no detailed listing of all supported natural-language actions beyond marketing copy.", "evidenceIds": [ "missive-docs-1", "missive-docs-20", "missive-docs-21", "missive-docs-22", "missive-docs-34", "missive-docs-49", "missive-docs-3", "missive-docs-supp-3" ] }, { "productId": "missive", "storyId": "agentic-official-cli", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Missive is an email/collaboration app offering REST API, webhooks, and MCP integrations, but no evidence anywhere in the pack mentions an official CLI tool for interacting with Missive. Probes for docs/openapi manifests return 404s, and no CLI-related changelog or docs entries exist.", "evidenceIds": [ "missive-docs-31", "missive-docs-39", "missive-probe-1", "missive-probe-2", "missive-probe-3" ] }, { "productId": "missive", "storyId": "agentic-public-api", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Missive documents a REST API, webhooks, UI integrations, and custom channels for developers (missive-docs-31/39/15), plus an official MCP server exposing conversations, contacts, calendar, and drafts to AI apps like Claude/ChatGPT/Cursor (missive-docs-1/20, missive-probe-4). This gives AI-native users a documented, programmatic way to drive the product beyond the UI. Missing for 10: a discoverable OpenAPI/swagger spec or llms.txt (all probed and 404'd) and independent third-party corroboration of API robustness.", "evidenceIds": [ "missive-docs-31", "missive-docs-39", "missive-docs-15", "missive-docs-1", "missive-docs-20", "missive-probe-4", "missive-docs-47" ] }, { "productId": "missive", "storyId": "agentic-scoped-keys", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Missive's MCP integration explicitly notes external AI apps connect \"with the permissions you choose\" (missive-docs-20) and custom MCP setup lets you \"choose an authentication method\" (missive-docs-17), implying some scoped access control for agents. However, there's no documentation of granular API-key scopes, role-based permission tiers, or a dedicated credential-issuance UI for least-privilege agent access. Missing for 10: explicit scoped API key/token generation flow, documented permission levels/roles for agents, and independent confirmation that scoping is enforced in practice.", "evidenceIds": [ "missive-docs-20", "missive-docs-17", "missive-docs-47", "missive-docs-16" ] }, { "productId": "missive", "storyId": "agentic-sdks", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Missive documents a REST API, webhooks, custom channels, and MCP integrations for developers, but no evidence anywhere mentions official client SDKs (e.g. language libraries) for building against Missive; probes even show 404s for OpenAPI/spec files that would typically back SDK generation.", "evidenceIds": [ "missive-docs-31", "missive-docs-39", "missive-probe-3", "missive-probe-1", "missive-probe-2" ] }, { "productId": "missive", "storyId": "agentic-webhooks", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Missive's developer tools page explicitly lists webhooks alongside REST API and custom channels, confirming the capability exists, but there is no detail on event types, subscription setup, payload format, or independent corroboration of webhook usage. Missing for 10: documented list of subscribable event types, webhook setup/config instructions, security/signing details, and third-party confirmation of reliability.", "evidenceIds": [ "missive-docs-31", "missive-docs-39" ] }, { "productId": "missive", "storyId": "ai-drafts-in-my-voice", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Missive documents AI compose/reply features (\"Quickly compose, reply, and translate messages with AI directly in Missive\" and \"Ask Claude to summarize your inbox and draft replies\") confirming AI drafting exists, but there is no evidence describing tone/voice personalization or that drafts are tuned to the user's own writing style versus generic boilerplate. Missing for 10: evidence of voice/tone learning or personalization, hands-on examples showing draft quality matches user's style, independent corroboration of draft usefulness.", "evidenceIds": [ "missive-docs-49", "missive-docs-21", "missive-docs-16" ] }, { "productId": "missive", "storyId": "ai-inbox-answers", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Missive's AI Assistant/MCP integration lets external AI apps (Claude, ChatGPT, Cursor) act on conversations, contacts, calendar, and drafts, and docs explicitly mention asking Claude to summarize the inbox and draft replies — directly supporting cross-inbox Q&A grounded in Missive data. However, evidence doesn't demonstrate calendar-specific querying depth or explicit 'what's outstanding' style aggregate reasoning across the whole inbox, and there's no independent/hands-on validation of answer groundedness or accuracy. Missing for 10: concrete examples of calendar-integrated Q&A, evidence of multi-conversation aggregate answers, and independent corroboration of answer quality/groundedness.", "evidenceIds": [ "missive-docs-1", "missive-docs-20", "missive-docs-21", "missive-docs-16", "missive-docs-27" ] }, { "productId": "missive", "storyId": "ai-triage-labels", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Missive's AI Assistant/MCP integration explicitly supports agent-driven triage ('Let an agent triage new conversations against your CRM before you look at them'), inbox summarization, and rule-based automation (up to 1000 rules), and provides audit trails via action logs and a session tab showing assistant activity, plus permission-scoped access for steering behavior. However, there's no explicit mention of automatic labeling/categorization as a distinct AI feature (only manual rules), and no independent/hands-on evidence confirming triage quality works as advertised. Missing for 10: explicit auto-labeling/categorization feature description, hands-on validation of triage accuracy, and clearer UI for reviewing/adjusting AI triage decisions beyond session logs.", "evidenceIds": [ "missive-docs-22", "missive-docs-21", "missive-docs-2", "missive-docs-34", "missive-docs-9", "missive-docs-20", "missive-docs-11", "missive-docs-36" ] }, { "productId": "missive", "storyId": "api-interactive-docs", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Missive documents a REST API and developer tools, but there is no evidence of an interactive API reference or runnable examples; explicit probes for openapi/swagger specs all returned 404s, indicating no interactive API explorer exists.", "evidenceIds": [ "missive-docs-15", "missive-docs-31", "missive-probe-3" ] }, { "productId": "missive", "storyId": "api-machine-spec", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Probes for OpenAPI/Swagger spec files at standard locations all returned 404, and no evidence pack item mentions a downloadable machine-readable API spec despite Missive having a REST API and developer docs.", "evidenceIds": [ "missive-probe-3", "missive-docs-31", "missive-docs-39" ] }, { "productId": "missive", "storyId": "api-sandbox", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence of any sandbox, staging, or test environment offered by Missive; all MCP/API access documented operates directly against live conversations, contacts, calendars, and drafts (missive-probe-rt-2), with no mention of a non-production mode for testing.", "evidenceIds": [] }, { "productId": "missive", "storyId": "api-versioning-policy", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "There is a REST API and MCP integrations documented, but no evidence of API versioning scheme or any documented deprecation policy; probes for openapi/spec files all 404. missing for 10: versioning scheme documentation, explicit deprecation/backward-compatibility policy, changelog of breaking API changes.", "evidenceIds": [ "missive-docs-15", "missive-docs-31", "missive-probe-3" ] }, { "productId": "missive", "storyId": "assignment-and-routing", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Missive's docs explicitly describe assigning conversations to a team or specific person while maintaining visibility (missive-docs-6), shared inboxes/distribution lists (missive-docs-32, missive-docs-28), and automated routing via rules (up to 1000 rules per missive-docs-11/25/36), directly matching the story's ask for explicit ownership assignment and rule-based routing. Missing for 10: independent/hands-on corroboration of rule-based mail routing in practice, and more detail on how rule conditions/criteria are configured.", "evidenceIds": [ "missive-docs-6", "missive-docs-11", "missive-docs-25", "missive-docs-36", "missive-docs-32", "missive-docs-28" ] }, { "productId": "missive", "storyId": "automation-bulk-operations", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Missive documents rule-based automation ('Up to 1000 rules') and API/MCP access that could act across many items, plus a bulk auto-archive list feature, but there is no direct evidence of a bulk-select/bulk-action UI or bulk API endpoint for acting on many conversations/contacts at once. Missing for 10: explicit bulk-action UI documentation, bulk API/webhook examples, and independent confirmation of scale-limits for automation across many items.", "evidenceIds": [ "missive-docs-25", "missive-docs-36", "missive-docs-44", "missive-docs-15", "missive-docs-16" ] }, { "productId": "missive", "storyId": "automation-rules-engine", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Missive confirms a native Rules feature (\"Automate your workflows\", \"Up to 1000 rules\", and documentation referencing 'how to set up a rule') that lets users define automation triggered by events, plus webhooks/API for event-driven actions. However, the evidence pack lacks concrete documentation of what trigger events or actions rules support, no hands-on examples of rule configuration, and no independent corroboration of automation depth or reliability. missing for 10: detailed rule trigger/action catalog, hands-on walkthrough of rule creation, independent user validation of automation reliability.", "evidenceIds": [ "missive-docs-3", "missive-docs-11", "missive-docs-25", "missive-docs-36", "missive-docs-31" ] }, { "productId": "missive", "storyId": "automation-scheduled-jobs", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Missive documents an AI Assistant, MCP integrations, and an event-triggered 'rules' automation engine (up to 1000 rules) for workflows, but nothing in the evidence describes scheduling recurring/cron-style jobs or timed recurring AI workflows — rules appear to be trigger-based, not time-scheduled. missing for 10: any mention of a scheduler, cron-like recurrence, or time-based recurring job configuration for AI/assistant workflows.", "evidenceIds": [ "missive-docs-11", "missive-docs-25", "missive-docs-36", "missive-docs-16", "missive-docs-27" ] }, { "productId": "missive", "storyId": "automation-versioned-workflows", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Missive documents rules/automations, an activity log, and AI session tabs, but there is no evidence of any version history, review workflow, or rollback mechanism for automations/rules — no changelog history for rules, no diff/versioning UI, no undo/rollback feature mentioned anywhere.", "evidenceIds": [] }, { "productId": "missive", "storyId": "beyond-email-channels", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Pricing docs explicitly list \"Email, SMS, social accounts\" as channels handled in the same inbox, and developer docs mention support for \"custom channels\" via API, confirming Missive unifies email with at least SMS and social channels. However, there is no explicit evidence of native WhatsApp or live-chat channel support, only generic 'custom channels' extensibility. Missing for 10: explicit WhatsApp integration, native live-chat channel, and independent confirmation of multi-channel unification in practice.", "evidenceIds": [ "missive-docs-56", "missive-docs-31", "missive-docs-39" ] }, { "productId": "missive", "storyId": "bulk-triage-actions", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack covers command bar search, snoozing, canned responses, MCP/AI assistant integration, and team collaboration features, but nothing documents multi-select bulk actions (archive/label/mark done across many conversations at once). Missing for 10: any docs or changelog entry describing bulk selection UI, keyboard multi-select, or batch archive/label/mark-done operations.", "evidenceIds": [ "missive-docs-supp-2", "missive-docs-supp-3" ] }, { "productId": "missive", "storyId": "calendar-inside-client", "verdict": "partial", "quality": 2, "confidence": "low", "rationale": "The only calendar-related evidence is indirect: MCP changelog entries note that external AI apps can 'act on your conversations, contacts, calendar, and drafts,' implying Missive holds calendar data, but there is no documentation of an in-app calendar view, RSVP/invite response flow, or event-creation UI comparable to inbox features. Missing for 10: dedicated calendar panel/view docs, invite accept/decline UI, and event creation flow evidence — only an AI-assistant-access mention exists.", "evidenceIds": [ "missive-docs-1", "missive-docs-20" ] }, { "productId": "missive", "storyId": "full-history-import", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack discusses importing mail history or contacts from another provider/client (e.g., Gmail/Outlook migration, IMAP sync, contact import tools). Evidence covers AI/MCP features, collaboration, search filters, and pricing but nothing about onboarding migration or historical data import.", "evidenceIds": [] }, { "productId": "missive", "storyId": "instant-search-operators", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Evidence confirms Missive has search filters (Type: Internal/External, Date range) and a command-bar search that can query across messages, contacts, or a specific label, but there is no documentation of search operators (from:, subject:, boolean, etc.), relevance ranking, or explicit assurance of full-history indexing/performance at scale. Missing for 10: documented search operator syntax, ranked-results behavior, evidence of speed/precision across large mail archives, and independent corroboration of search quality.", "evidenceIds": [ "missive-docs-4", "missive-docs-38", "missive-docs-supp-3" ] }, { "productId": "missive", "storyId": "internal-comments-mentions", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Missive's docs point to team collaboration around conversations — 'collaborate behind the scenes without changing your workflow', 'chat with your team' in groups/spaces, and 'compose emails together, get reviewed in real time' — which align with discussing a message internally rather than forwarding it. However, none of the evidence explicitly names a side-thread comment feature or @mention tagging mechanic attached to a message. missing for 10: explicit documentation of inline comment threads on conversations, explicit @mention functionality, and independent/hands-on confirmation that this replaces forwarding workflows.", "evidenceIds": [ "missive-docs-30", "missive-docs-48", "missive-docs-8", "missive-docs-51", "missive-docs-7", "missive-docs-6" ] }, { "productId": "missive", "storyId": "keyboard-first-speed", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Missive documents a command bar (⌘/Ctrl+K) supporting search, snooze, and other quick commands, plus configurable swipe/keyboard shortcuts, which is direct evidence of keyboard-driven command palette functionality. However, there's no comprehensive shortcut list, no dedicated performance benchmarks, and community comments call the UI 'unintuitive' with 'design flaws' though also 'snappy' — mixed signal on speed/polish. Missing for 10: a full documented shortcut reference covering all major actions, explicit performance/latency claims, and independent hands-on confirmation of speed and keyboard completeness.", "evidenceIds": [ "missive-docs-supp-2", "missive-docs-supp-3", "missive-comm-4", "missive-comm-5" ] }, { "productId": "missive", "storyId": "masked-aliases", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence anywhere in the pack of email aliasing, masked/burner address generation, or similar identity-protection features for switchers; Missive is an email client/collaboration tool, and evidence covers team inboxes, MCP/AI integrations, and SSO, none of which address address masking.", "evidenceIds": [] }, { "productId": "missive", "storyId": "multi-account-unified", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Evidence only touches this obliquely: contacts management explicitly 'syncs with Office 365 and Google' (missive-docs-23), and shared/team inboxes are documented (missive-docs-32, missive-docs-28), implying multi-account consolidation, but there is no explicit documentation in the pack of connecting Gmail, Microsoft 365, and generic IMAP accounts as email sources worked from one unified inbox. Missing for 10: explicit account-connection docs for Gmail/O365/IMAP email (not just contacts sync), and confirmation that all provider types can be combined in one inbox view.", "evidenceIds": [ "missive-docs-23", "missive-docs-32", "missive-docs-28" ] }, { "productId": "missive", "storyId": "offline-access", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack addresses offline mode, local caching of email data, offline search, or sync-on-reconnect behavior; all citations concern MCP/AI integrations, team collaboration, and pricing features unrelated to offline reliability.", "evidenceIds": [] }, { "productId": "missive", "storyId": "open-protocol-access", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack contains no mention of IMAP, JMAP, or SMTP access for user mailboxes, nor any standards-based export functionality; all connectivity evidence is about REST API, webhooks, and MCP integrations for AI/automation, not about open mail protocol interoperability or data portability for switchers.", "evidenceIds": [] }, { "productId": "missive", "storyId": "openness-api-parity", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "Missive documents a REST API, webhooks, and an MCP server that can act on conversations, contacts, calendar, and drafts (missive-docs-15, missive-docs-31, missive-docs-45, missive-probe-4), suggesting broad but not explicitly complete UI/API parity — there is no vendor claim of 1:1 feature parity, and the OpenAPI spec could not be located via standard probes (missive-probe-3), making it hard to verify full API surface coverage against UI capabilities like snoozing, canned responses, or command-bar search (missive-docs-supp-1/3/4) which are not mentioned as API-exposed. Missing for 10: an explicit vendor statement of full UI/API parity, a discoverable OpenAPI/schema reference, and evidence that UI-only features (snoozing, canned responses, command bar actions) are also API-accessible.", "evidenceIds": [ "missive-docs-15", "missive-docs-31", "missive-docs-45", "missive-probe-3", "missive-probe-4", "missive-docs-supp-1", "missive-docs-supp-4" ] }, { "productId": "missive", "storyId": "openness-full-export", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "The evidence pack shows a REST API, webhooks, and MCP integrations for connecting external tools, but nothing documents a bulk data-export feature or open-format (mbox/CSV/JSON) export enabling a user to fully extract their mail, contacts, and conversation history and leave the platform. Probes for docs/API artifacts (llms.txt, openapi) also 404, further indicating no dedicated export-and-leave capability is documented.", "evidenceIds": [ "missive-docs-15", "missive-docs-31", "missive-probe-1", "missive-probe-2", "missive-probe-3" ] }, { "productId": "missive", "storyId": "openness-open-license", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Missive is a closed-source commercial email/collaboration SaaS; no evidence anywhere in the pack of an open-source license or public source repository, and probes for typical openness indicators (llms.txt, docs.md, openapi) all 404. No indication source code is available under any license.", "evidenceIds": [ "missive-probe-1", "missive-probe-2", "missive-probe-3" ] }, { "productId": "missive", "storyId": "openness-self-host", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Missive is a cloud-hosted SaaS collaboration/email product; evidence shows data routes through Missive's own servers (missive-comm-1) and no docs mention any self-hosting/on-prem deployment option anywhere in the extensive feature/pricing/docs pack.", "evidenceIds": [ "missive-comm-1" ] }, { "productId": "missive", "storyId": "privacy-data-residency", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack mentions data residency, region selection, or geographic storage location controls; features like IP restrictions and SSO relate to access control, not data storage location. Missing for 10: any mention of regional data hosting options, residency guarantees, or storage location configuration.", "evidenceIds": [] }, { "productId": "missive", "storyId": "privacy-no-training", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack addresses any AI-training opt-out, data-usage policy for AI model training, or privacy controls specific to preventing training on user data. The pack covers MCP integrations, AI assistant features, and collaboration tools, but nothing about training data exclusion or a documented privacy commitment on this axis.", "evidenceIds": [] }, { "productId": "missive", "storyId": "privacy-retention-controls", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence describes any data retention or deletion controls (e.g., configurable retention periods, right-to-delete, data purge options) for Missive or its AI/MCP features; the only related community note concerns data routing through servers via TLS, not retention/deletion policy.", "evidenceIds": [ "missive-comm-1" ] }, { "productId": "missive", "storyId": "privacy-telemetry-optout", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence pack item addresses telemetry/usage-tracking opt-out settings, privacy controls, or data-collection disclosures for Missive; the closest related content (comm-1) merely notes emails route through Missive's servers, which is unrelated to telemetry opt-out. This is an applicable axis for a SaaS product but no supporting evidence exists.", "evidenceIds": [] }, { "productId": "missive", "storyId": "read-statuses", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack mentions read receipts, email open tracking, or notifications about recipient opens/views; the pack covers collaboration, MCP/AI integrations, and admin features but nothing about tracking email opens.", "evidenceIds": [] }, { "productId": "missive", "storyId": "scheduled-send-undo", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack mentions scheduled sending or an undo-send grace window; the pack covers MCP integrations, collaboration features, snoozing, and canned responses but nothing about send scheduling or send-delay/undo functionality.", "evidenceIds": [] }, { "productId": "missive", "storyId": "self-host-option", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Missive is a cloud-hosted SaaS collaboration/email platform with no documented self-hosting option; community evidence confirms mail data routes through Missive's own servers (missive-comm-1), and no docs mention on-premise or self-hosted deployment.", "evidenceIds": [ "missive-comm-1" ] }, { "productId": "missive", "storyId": "share-availability", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "The evidence pack shows Missive's MCP integration can 'act on... calendar' generally, but there is no mention of any feature to share availability, generate scheduling links, or insert bookable meeting times into an email — a distinct capability from generic calendar access.", "evidenceIds": [] }, { "productId": "missive", "storyId": "shared-team-inbox", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "Missive's core product docs directly describe shared/team inboxes with multiple people working the same inbox without conflict, conversation assignment while maintaining visibility, distribution-list-to-shared-inbox mapping, per-action audit logging, and dedicated team spaces/channels — exactly the shared-conversation-state model the story describes (missive-docs-6, missive-docs-9, missive-docs-19, missive-docs-28, missive-docs-32, missive-docs-35, missive-docs-30/48). Independent community commentary corroborates it is used specifically for team email collaboration (missive-comm-3), and no evidence contradicts the shared-inbox mechanics themselves (complaints found are about general UX/bugs, not this capability). Missing for 10: a hands-on third-party account specifically confirming real-time shared conversation-state syncing across users (vs. general collaboration praise).", "evidenceIds": [ "missive-docs-6", "missive-docs-9", "missive-docs-19", "missive-docs-28", "missive-docs-32", "missive-docs-35", "missive-docs-30", "missive-comm-3" ] }, { "productId": "missive", "storyId": "snippets-templates", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Missive's canned responses/templates feature explicitly supports saving reusable replies, inserting them via keystrokes/command bar, sharing across teams, and customizing with a variables templating engine (recipient name, etc.), directly matching the story; MCP/API docs also confirm drafts resolve template variables like {{ user.name }}. missing for 10: explicit first-party documentation confirming attachments can be bundled/saved within a canned response/template, and independent hands-on corroboration of the templating workflow.", "evidenceIds": [ "missive-docs-supp-4", "missive-docs-supp-5", "missive-docs-45", "missive-docs-50" ] }, { "productId": "missive", "storyId": "snooze-and-reminders", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Missive's docs clearly document snoozing a conversation until a specific time so it resurfaces in the Inbox, including quick access via swipe or command bar (missive-docs-supp-1, missive-docs-supp-2). However, there is no evidence of a distinct 'follow-up reminder' feature that resurfaces a thread specifically if nobody replies (as opposed to a fixed snooze time) — the story's reply-tracking trigger is unevidenced. Missing for 10: documentation of a no-reply-triggered follow-up reminder mechanism, and any independent/hands-on confirmation of snooze/reminder reliability.", "evidenceIds": [ "missive-docs-supp-1", "missive-docs-supp-2" ] }, { "productId": "missive", "storyId": "split-inbox-triage", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Missive's docs mention rule automation (up to 1000 rules), team spaces, and shared/team inboxes, which could be used to organize conversations by category, but there is no explicit documentation of a dedicated 'streams' or 'focused inbox' feature that lets a user split a single inbox into priority-ordered views (important, team, newsletters, calendar invites) as described in the story. missing for 10: explicit inbox-view/stream creation feature, priority-based triage ordering, and evidence of calendar-invite handling as a distinct stream.", "evidenceIds": [ "missive-docs-11", "missive-docs-25", "missive-docs-36", "missive-docs-19", "missive-docs-32", "missive-docs-6" ] }, { "productId": "missive", "storyId": "tracker-blocking", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence pack item mentions tracking-pixel blocking, image-loading proxying, or a documented privacy policy explaining what Missive does with mail data. The only related community evidence shows a user learning mail routes through Missive's servers and declining ('Thanks, but I pass'), which does not demonstrate a pixel-blocking feature or proactive transparency documentation.", "evidenceIds": [ "missive-comm-1" ] }, { "productId": "shortwave", "storyId": "agent-email-end-to-end", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Shortwave documents an internal AI Assistant that reads/drafts/searches email, and it can act as an MCP *client* connecting its own AI to external apps (Slack, GitHub, Zapier, etc.), but there is no evidence Shortwave exposes itself as an MCP server or documented API that lets an external agent (Claude, ChatGPT, or a custom agent) read/triage/draft/send mail through it. Probes confirm no llms.txt, no docs.md, and no OpenAPI/Swagger endpoint, indicating no documented external-agent connection surface.", "evidenceIds": [ "shortwave-docs-3", "shortwave-docs-12", "shortwave-docs-19", "shortwave-docs-30", "shortwave-probe-1", "shortwave-probe-2", "shortwave-probe-3" ] }, { "productId": "shortwave", "storyId": "agentic-agent-docs", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Direct probes show no llms.txt or agent-oriented docs endpoint exists (404s across llms.txt, docs-md, openapi paths), and no other evidence mentions such agent-facing documentation.", "evidenceIds": [ "shortwave-probe-1", "shortwave-probe-2", "shortwave-probe-3" ] }, { "productId": "shortwave", "storyId": "agentic-ai-insights", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Shortwave delivers AI-generated insights directly in-product: Instant Summaries appear atop threads, AI Assistant reads threads/searches history/checks calendar to surface answers, Ghostwriter offers inline autocomplete suggestions, and custom AI filters/triggers auto-label and organize emails based on AI analysis. These are well-documented first-party features spanning summarization, suggestion, and automated insight generation across the inbox. Missing for 10: independent hands-on validation of insight quality/accuracy and no third-party review confirming these AI insights work reliably in practice beyond vendor claims.", "evidenceIds": [ "shortwave-docs-14", "shortwave-docs-23", "shortwave-docs-12", "shortwave-docs-28", "shortwave-docs-13", "shortwave-docs-17", "shortwave-docs-15", "shortwave-docs-29" ] }, { "productId": "shortwave", "storyId": "agentic-autonomous-automation", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Shortwave explicitly supports triggers that draft replies, add comments, organize threads into todos when emails arrive, plus custom AI filters running as background scripts and Tasklet integration to auto-act on emails—these run autonomously without user initiation. However, evidence is all vendor-sourced with no independent verification of reliability or scope of autonomy. Missing for 10: independent/hands-on confirmation of trigger reliability, detail on trigger configuration UI, and evidence of complex multi-step autonomous workflows beyond simple triggers.", "evidenceIds": [ "shortwave-docs-1", "shortwave-docs-15", "shortwave-docs-36", "shortwave-docs-3", "shortwave-docs-4" ] }, { "productId": "shortwave", "storyId": "agentic-builtin-assistant", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Shortwave has a built-in AI assistant/executive assistant that can read threads, write drafts, search email history, check calendar, run custom AI filters, and take multi-step actions via triggers and MCP integrations without leaving the inbox — clearly delegatable task execution. Missing for 10: independent hands-on validation of end-to-end delegated task completion (beyond vendor blog claims) and details on reliability/error handling.", "evidenceIds": [ "shortwave-docs-12", "shortwave-docs-28", "shortwave-docs-15", "shortwave-docs-1", "shortwave-docs-4", "shortwave-docs-19", "shortwave-docs-36" ] }, { "productId": "shortwave", "storyId": "agentic-headless", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is \"none\", never \"na\". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)", "evidenceIds": [] }, { "productId": "shortwave", "storyId": "agentic-mcp-client", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Shortwave explicitly documents connecting to any MCP server via 'Add custom integration' to let its AI Assistant use those tools, with first-party blog docs and pricing page confirming MCP support alongside built-in integrations. Missing for 10: independent hands-on verification of the MCP setup flow and no detail on tool-call reliability/limits beyond marketing docs.", "evidenceIds": [ "shortwave-docs-3", "shortwave-docs-18", "shortwave-docs-19", "shortwave-docs-30", "shortwave-docs-32", "shortwave-comm-14" ] }, { "productId": "shortwave", "storyId": "agentic-mcp-server", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Shortwave documents letting its own AI Assistant connect out to third-party MCP servers ('Add custom integration', point to an MCP server of your choice) — this is MCP-client behavior, not Shortwave exposing an official MCP server that external agents could connect to. As a SaaS email product, offering an official MCP server for outside agents is a fair, applicable axis, but no evidence pack item shows such a server (docs/openapi/llms.txt probes all 404).", "evidenceIds": [ "shortwave-docs-3", "shortwave-docs-18", "shortwave-docs-32", "shortwave-probe-1", "shortwave-probe-2", "shortwave-probe-3" ] }, { "productId": "shortwave", "storyId": "agentic-nl-commands", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Shortwave's AI Assistant lets users operate the inbox via natural language—reading threads, writing drafts, searching email history, checking calendar, and running custom AI filters written in plain English—directly in the product's core value proposition. Docs consistently describe this as the primary UX (chat-based assistant, plain-English filter scripts, natural-language triggers).\n\nmissing for 10: independent/hands-on verification specifically of the natural-language command interface's reliability (community evidence focuses on UI/pricing/privacy, not NL command execution quality).", "evidenceIds": [ "shortwave-docs-12", "shortwave-docs-15", "shortwave-docs-28", "shortwave-docs-4", "shortwave-docs-19", "shortwave-docs-1" ] }, { "productId": "shortwave", "storyId": "agentic-official-cli", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Shortwave is an AI email client product, not a developer tool/platform where an official CLI is a natural offering; no evidence suggests it ships or intends a CLI, and the product's interaction model is web/app-based with MCP integrations rather than command-line workflows.", "evidenceIds": [] }, { "productId": "shortwave", "storyId": "agentic-public-api", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Shortwave's evidence only shows it acting as an MCP *client* (connecting its AI Assistant to other apps' MCP servers) or integrating with third-party APIs like Zapier/GitHub — none of this constitutes Shortwave itself exposing a documented public API for external developers to drive the product. Direct probes for llms.txt, docs-as-markdown, and OpenAPI/Swagger specs all returned 404s, confirming no discoverable public API surface.", "evidenceIds": [ "shortwave-docs-3", "shortwave-docs-18", "shortwave-docs-30", "shortwave-probe-1", "shortwave-probe-2", "shortwave-probe-3" ] }, { "productId": "shortwave", "storyId": "agentic-scoped-keys", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Shortwave's evidence covers MCP/app integrations and AI assistant features, but there is no mention of scoped or least-privilege API credential issuance, API key management, or granular permission controls for agents; probes confirm no public API/OpenAPI spec exists. Community comments even note complaints about over-broad permission requests rather than scoped credentials, reinforcing absence of this capability.", "evidenceIds": [ "shortwave-probe-1", "shortwave-probe-2", "shortwave-probe-3", "shortwave-comm-3" ] }, { "productId": "shortwave", "storyId": "agentic-sdks", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of any official SDKs for developers; probes for llms.txt, docs.md, and OpenAPI/swagger specs all returned 404, and the evidence pack only documents MCP-based integrations for end-user workflows (Slack, Notion, Zapier) rather than a developer SDK.", "evidenceIds": [ "shortwave-probe-1", "shortwave-probe-2", "shortwave-probe-3" ] }, { "productId": "shortwave", "storyId": "agentic-webhooks", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Shortwave's evidence covers triggers, MCP integrations, and Zapier connections, but nothing describes outbound webhooks that let an AI-native user subscribe to Shortwave events; no webhook API, subscription endpoint, or event schema is documented, and OpenAPI/llms.txt probes returned 404s.", "evidenceIds": [ "shortwave-docs-1", "shortwave-docs-3", "shortwave-probe-3" ] }, { "productId": "shortwave", "storyId": "ai-drafts-in-my-voice", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Shortwave's AI Assistant explicitly 'writes drafts' and Ghostwriter autocompletes replies as you type, confirming AI-drafted replies are a core capability. However, no evidence specifically shows the AI learns or mimics the user's personal voice/tone (vs. generic suggestions or template-based AI Snippets), so the 'own voice' personalization claim is unverified. Missing for 10: explicit documentation of voice/tone personalization or learning from user's writing style, and independent user reports confirming drafts sound authentically like them rather than generic AI text.", "evidenceIds": [ "shortwave-docs-12", "shortwave-docs-28", "shortwave-docs-13", "shortwave-docs-17", "shortwave-docs-5" ] }, { "productId": "shortwave", "storyId": "ai-inbox-answers", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Docs directly describe the AI Assistant reading threads, writing drafts, searching entire email history, and checking calendar — matching the grounded cross-inbox/calendar Q&A story. Community evidence corroborates fast search/summaries and real usage, though no independent hands-on confirmation of complex multi-thread grounded reasoning exists. Missing for 10: independent hands-on verification of accuracy/groundedness across large inboxes, and detail on how calendar+email context are combined in answers.", "evidenceIds": [ "shortwave-docs-12", "shortwave-docs-28", "shortwave-docs-14", "shortwave-comm-8" ] }, { "productId": "shortwave", "storyId": "ai-triage-labels", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Shortwave ships custom AI filters that auto-label, star, and archive using plain-English scripts, plus Bundles/Splits to categorize inbox by importance and one-click identification of important emails/todos, directly matching the triage story; community feedback corroborates the bundling/importance-sorting feature as effective ('top shelf'). Steerability is evidenced via the plain-English filter scripts, but missing for 10: explicit audit-trail/log of AI triage decisions and independent verification of filter reliability at scale.", "evidenceIds": [ "shortwave-docs-15", "shortwave-docs-29", "shortwave-docs-9", "shortwave-docs-33", "shortwave-comm-4" ] }, { "productId": "shortwave", "storyId": "api-interactive-docs", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Shortwave is an email client, not a developer platform with an API reference; probes for llms.txt, docs.md, and OpenAPI specs all returned 404s, and no evidence mentions any interactive API documentation or runnable code examples.", "evidenceIds": [ "shortwave-probe-1", "shortwave-probe-2", "shortwave-probe-3" ] }, { "productId": "shortwave", "storyId": "api-machine-spec", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Direct probes for OpenAPI/swagger specs and llms.txt all returned 404s, and no docs mention a machine-readable API spec.", "evidenceIds": [ "shortwave-probe-3", "shortwave-probe-1", "shortwave-probe-2" ] }, { "productId": "shortwave", "storyId": "api-sandbox", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Shortwave is an AI-native email client, not a developer platform or API product; there is no concept of a sandbox vs. production environment for testing in this context, so this axis is a category error for this product type.", "evidenceIds": [] }, { "productId": "shortwave", "storyId": "api-versioning-policy", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of any public API, versioning scheme, or deprecation policy; probes for OpenAPI/llms.txt/docs endpoints all returned 404s, and no docs mention versioned APIs.", "evidenceIds": [ "shortwave-probe-1", "shortwave-probe-2", "shortwave-probe-3" ] }, { "productId": "shortwave", "storyId": "assignment-and-routing", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Shortwave offers team comments and @mention to loop teammates into a thread (giving them access to the email) and custom AI filters that can label/archive/star via plain-English rules, but there is no evidence of an explicit 'assign conversation to teammate' ownership feature or rule-based routing of incoming mail to specific team members/inboxes. missing for 10: explicit conversation assignment/ownership feature, mail routing rules tied to teammates, evidence of shared/team inbox queue management.", "evidenceIds": [ "shortwave-docs-10", "shortwave-docs-11", "shortwave-docs-15", "shortwave-comm-4" ] }, { "productId": "shortwave", "storyId": "automation-bulk-operations", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Shortwave's custom AI filters ('automatically label, star, archive, and more with scripts you write in plain English') and one-click sweep of non-important emails/todos (docs-15, docs-29) directly support automated actions applied across many inbox items at once, and triggers (docs-1) extend this to organizing threads into todos in bulk. However, there's no explicit documentation of a true multi-select bulk-action UI, batch limits, or independent hands-on confirmation that these AI filters reliably scale across large volumes of email. Missing for 10: explicit bulk-select/apply workflow docs, scale/performance evidence, and independent user corroboration of bulk automation working as advertised.", "evidenceIds": [ "shortwave-docs-15", "shortwave-docs-29", "shortwave-docs-1" ] }, { "productId": "shortwave", "storyId": "automation-rules-engine", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Shortwave documents explicit rule/trigger automation: triggers that draft replies when emails arrive, custom AI filters written in plain English that auto-label/star/archive, and Tasklet integration that takes automatic actions on emails as they arrive. This directly matches defining rules that fire on events (email arrival) with automated actions. Missing for 10: independent/hands-on verification that these triggers work reliably in practice, and more detail on rule complexity/limits beyond marketing copy.", "evidenceIds": [ "shortwave-docs-1", "shortwave-docs-15", "shortwave-docs-36" ] }, { "productId": "shortwave", "storyId": "automation-scheduled-jobs", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Shortwave offers event-based 'triggers' (auto-draft replies, add comments, organize todos) and custom AI filters that run automatically in plain English, which are a form of automation, but these are reactive triggers on incoming events rather than true time-based recurring/scheduled jobs — the only scheduling feature documented (Scheduled Send) is a one-time future send, not a recurring workflow. Missing for 10: explicit recurring/cron-style scheduling of AI workflows, documentation of periodic digest or repeat-interval automations, and independent confirmation that triggers can run on a time-based recurring cadence rather than only on email arrival.", "evidenceIds": [ "shortwave-docs-1", "shortwave-docs-15", "shortwave-docs-7", "shortwave-docs-36" ] }, { "productId": "shortwave", "storyId": "automation-versioned-workflows", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Shortwave offers AI filters, triggers, and MCP integrations for automation, but there is no evidence of version history, review workflows, diffs, or rollback capability for these automations.", "evidenceIds": [] }, { "productId": "shortwave", "storyId": "beyond-email-channels", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is \"none\", never \"na\". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)", "evidenceIds": [] }, { "productId": "shortwave", "storyId": "bulk-triage-actions", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Shortwave's docs mention bulk-oriented behaviors—custom AI filters that automatically label/star/archive matching emails, and a one-click 'sweep away the rest' declutter action—that imply multi-conversation bulk actions, but there is no explicit mention of manually multi-selecting conversations and applying archive/label/mark-done in one stroke. Missing for 10: explicit multi-select UI documentation, confirmation that labels/archive/done can be applied simultaneously to a manual selection, and independent/hands-on confirmation of this specific workflow.", "evidenceIds": [ "shortwave-docs-15", "shortwave-docs-29" ] }, { "productId": "shortwave", "storyId": "calendar-inside-client", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Shortwave's AI assistant is documented to 'check your calendar' and integrate with Calendar as one of many connected apps, implying some calendar visibility inside the client, but there is no evidence of responding to invites or creating events without leaving the email client. missing for 10: explicit calendar view/UI, invite RSVP handling, and event-creation workflow evidence.", "evidenceIds": [ "shortwave-docs-12", "shortwave-docs-28", "shortwave-docs-24" ] }, { "productId": "shortwave", "storyId": "full-history-import", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "Shortwave is built directly on Gmail's APIs, so it can pull in an existing Gmail account's aliases and signatures (one user reported it 'imported all my aliases and signatures' during onboarding), but this is only a Gmail-to-Shortwave migration, not import from another provider/client like Outlook or Yahoo — a security-focused user explicitly noted 'it only works with Google servers.' Additionally, a documented free-plan limitation caps historical search import at 90 days, undercutting 'complete mail history.' Missing for 10: evidence of contacts import, support for non-Gmail providers, and confirmation that paid plans truly import full history without gaps.", "evidenceIds": [ "shortwave-comm-8", "shortwave-comm-10", "shortwave-comm-11", "shortwave-comm-3" ] }, { "productId": "shortwave", "storyId": "instant-search-operators", "verdict": "disputed", "quality": 4, "confidence": "medium", "rationale": "Shortwave's AI assistant is documented to 'search your entire email history' (shortwave-docs-12/28), but community evidence shows the free plan doesn't import emails older than 90 days before signup for search, contradicting the 'full mail history' claim, and no evidence describes search operators, advanced filters, or ranked-result mechanics. Missing for 10: documented search operators/filters syntax, ranking algorithm details, confirmation that paid tiers truly cover unlimited history without caveats.", "evidenceIds": [ "shortwave-docs-12", "shortwave-docs-28", "shortwave-comm-10" ] }, { "productId": "shortwave", "storyId": "internal-comments-mentions", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Shortwave's Team Comments feature explicitly lets teammates privately discuss an email in-app rather than forwarding, with @mentions that grant the mentioned teammate access to the comment and the email — directly matching the story. Missing for 10: independent/hands-on corroboration of the comment-thread UX beyond vendor blog posts, and detail on comment threading/notification mechanics.", "evidenceIds": [ "shortwave-docs-10", "shortwave-docs-11", "shortwave-docs-37", "shortwave-docs-34", "shortwave-docs-1" ] }, { "productId": "shortwave", "storyId": "keyboard-first-speed", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "The evidence pack contains no mentions of keyboard shortcuts, a command palette, or performance/speed benchmarks — all citations focus on AI features, integrations, and collaboration tools. Absence of evidence for this applicable axis (email clients commonly tout keyboard-driven UX, e.g. Superhuman comparisons appear in community items) yields 'none' rather than 'na'.", "evidenceIds": [] }, { "productId": "shortwave", "storyId": "masked-aliases", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence Shortwave offers email aliasing, masked addresses, or similar identity-protection features for sign-ups; the pack only covers AI assistant, integrations, and inbox management features unrelated to address masking.", "evidenceIds": [] }, { "productId": "shortwave", "storyId": "multi-account-unified", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence Shortwave supports connecting multiple providers (Gmail, Microsoft 365, IMAP) from one inbox; in fact the founder explicitly states they integrate only with Gmail's APIs ('not IMAP'), and a user confirms 'it only works with Google servers.' This directly contradicts the multi-provider switcher story rather than merely lacking support for it.", "evidenceIds": [ "shortwave-comm-1", "shortwave-comm-11" ] }, { "productId": "shortwave", "storyId": "offline-access", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "The founder states Gmail API integration enables 'offline handling' alongside real-time sync, implying some offline capability, but there's no detail on offline search, offline composing, or how changes reconcile on reconnect. missing for 10: documentation of offline read/search functionality, offline draft writing, and sync-conflict resolution behavior.", "evidenceIds": [ "shortwave-comm-1" ] }, { "productId": "shortwave", "storyId": "open-protocol-access", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Shortwave's own founder states they integrate via Gmail's proprietary APIs 'not IMAP,' and there is no mention anywhere in docs of JMAP, SMTP-level access, or standards-based export tooling — the product only works atop Google's servers (also confirmed by a security-focused user noting 'it only works with Google servers'). No evidence of any open-protocol mail access or portable export path exists in the pack.", "evidenceIds": [ "shortwave-comm-1", "shortwave-comm-11" ] }, { "productId": "shortwave", "storyId": "openness-api-parity", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence of a public API for Shortwave; probes for llms.txt, docs-md, and OpenAPI specs all returned 404, and no documentation mentions programmatic access to core features like AI assistant, triggers, or inbox management outside the UI/MCP integration (which is inbound, not an outbound API for replicating UI actions).", "evidenceIds": [ "shortwave-probe-1", "shortwave-probe-2", "shortwave-probe-3" ] }, { "productId": "shortwave", "storyId": "openness-full-export", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence of any data export feature (mailbox, comments, snippets, etc.) in open formats; probes for llms.txt, docs-md, and openapi endpoints all returned 404, and no changelog/blog mentions an export or account-portability capability. Community threads mention deleting the account making it 'low-risk' to switch back to Gmail, but that is because Shortwave uses Gmail as the underlying store, not because Shortwave itself offers a data export mechanism. missing for 10: any documented export/download feature, supported open file formats, or migration/backup tooling.", "evidenceIds": [ "shortwave-probe-1", "shortwave-probe-2", "shortwave-probe-3", "shortwave-comm-8" ] }, { "productId": "shortwave", "storyId": "openness-open-license", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of any open-source license or public source repository for Shortwave; it is a closed commercial SaaS email client with no mention of open licensing anywhere in the evidence pack.", "evidenceIds": [] }, { "productId": "shortwave", "storyId": "openness-self-host", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Shortwave is a hosted SaaS email client with no evidence of any self-hostable version; it relies on Google servers and its own cloud infrastructure (comm-11), and no self-hosting docs, Docker images, or open-source releases exist in the evidence pack.", "evidenceIds": [ "shortwave-comm-11", "shortwave-probe-1", "shortwave-probe-2", "shortwave-probe-3" ] }, { "productId": "shortwave", "storyId": "privacy-data-residency", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence anywhere in the pack mentions data residency, region selection, or storage location controls; Shortwave is shown to run on Google servers with no configurable region options, and community comments only raise general privacy/security concerns without any residency feature being offered.", "evidenceIds": [ "shortwave-comm-11", "shortwave-comm-7" ] }, { "productId": "shortwave", "storyId": "privacy-no-training", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence pack item describes any setting, policy statement, or opt-out mechanism letting users prevent their email/AI data from being used for model training; the only related community evidence (shortwave-comm-7) actually flags that Shortwave's privacy policy permits sharing email content/metadata with third-party vendors, which a user rejected outright rather than confirming a training opt-out exists.", "evidenceIds": [ "shortwave-comm-7", "shortwave-comm-6" ] }, { "productId": "shortwave", "storyId": "privacy-retention-controls", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "The only evidence touching on data deletion is a community anecdote that deleting one's Shortwave account makes it low-risk to switch back to Gmail, implying account-level deletion works, but there is no documented retention policy, granular deletion controls, or data-lifecycle settings; community comments even flag privacy concerns about email content being synced/shared with third-party vendors with no denylist option. missing for 10: documented retention policy, explicit deletion/export controls, first-party privacy/data-handling documentation.", "evidenceIds": [ "shortwave-comm-8", "shortwave-comm-6", "shortwave-comm-7" ] }, { "productId": "shortwave", "storyId": "privacy-telemetry-optout", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence Shortwave offers any telemetry/usage-tracking opt-out control; documentation focuses on AI features and integrations, and community discussion instead raises concerns about email content being shared with third-party vendors with no denylist option, but nothing addresses telemetry/analytics opt-out specifically.", "evidenceIds": [ "shortwave-comm-6", "shortwave-comm-7" ] }, { "productId": "shortwave", "storyId": "read-statuses", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence in the pack mentions read receipts, open tracking, or notifications about recipient email opens; Shortwave's documented features cover AI drafting, snippets, scheduling, undo send, and integrations but nothing about tracking whether/when recipients opened a message.", "evidenceIds": [] }, { "productId": "shortwave", "storyId": "scheduled-send-undo", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Shortwave's docs explicitly describe both scheduled send (set a time, write message, move on) and undo send (revert a sent message back to a draft), directly matching the story. Missing for 10: explicit detail on the undo grace-window duration and independent/hands-on corroboration beyond vendor blog.", "evidenceIds": [ "shortwave-docs-7", "shortwave-docs-8", "shortwave-docs-26" ] }, { "productId": "shortwave", "storyId": "self-host-option", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Shortwave is a cloud-hosted email client that syncs data to its own servers and works only with Gmail/Google servers (per community reports), with no documentation of any self-hosting option, on-prem deployment, or open-source pipeline; probes for docs/API specs also return 404s, indicating no infrastructure exposed for self-hosting.", "evidenceIds": [ "shortwave-comm-11", "shortwave-comm-6", "shortwave-comm-7", "shortwave-probe-1", "shortwave-probe-2", "shortwave-probe-3" ] }, { "productId": "shortwave", "storyId": "share-availability", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "Evidence shows Shortwave's AI can 'check your calendar' and connect to Calendar via integrations, but there is no mention of sharing availability or inserting bookable meeting time slots into an email — a distinct calendar-scheduling feature not evidenced anywhere in the pack.", "evidenceIds": [] }, { "productId": "shortwave", "storyId": "shared-team-inbox", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Shortwave offers team comments and @mention that grant teammates access to specific emails/threads (shortwave-docs-10,11,34,37), enabling some shared visibility and discussion. However, community evidence explicitly questions whether Shortwave's 'Bundles'/Workspaces model can replace true shared/team inboxes as found in dedicated tools (shortwave-comm-4), and there is no direct documentation of a shared-account or team-channel inbox where the whole team sees identical conversation state by default. Missing for 10: explicit shared-inbox/team-channel product feature, documentation of multi-user access to a single mailbox, and confirmation that collaboration extends beyond per-email comments to full inbox-level shared state.", "evidenceIds": [ "shortwave-docs-10", "shortwave-docs-11", "shortwave-docs-34", "shortwave-docs-37", "shortwave-comm-4" ] }, { "productId": "shortwave", "storyId": "snippets-templates", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Shortwave documents 'AI Snippets' that let users define an email template once and reuse it, available for individual and team use — directly matching the core snippet/template story. However, the evidence never confirms support for variables (dynamic fields) within snippets or attaching files as part of a snippet, both explicitly requested in the story. Missing for 10: documentation of variable/placeholder support in snippets, documentation of attachment bundling with snippets, and independent/hands-on confirmation of the feature working as described.", "evidenceIds": [ "shortwave-docs-5", "shortwave-docs-6" ] }, { "productId": "shortwave", "storyId": "snooze-and-reminders", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Community evidence confirms Shortwave has a snooze feature (comm-10 references 'snoozed emails' behavior), implying threads can be snoozed and resurfaced, but no evidence describes a follow-up reminder that resurfaces a thread specifically when nobody replies. Missing for 10: dedicated docs on follow-up/no-reply reminders, evidence of reminder triggers tied to reply detection, and confirmation of default snooze durations or scheduling UI for this specific workflow.", "evidenceIds": [ "shortwave-comm-10" ] }, { "productId": "shortwave", "storyId": "split-inbox-triage", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Shortwave's 'Splits' feature explicitly lets users divide one inbox into multiple focused inboxes by importance/type, each in its own tab, directly matching the triage-by-priority story, and independent community feedback (Front power-user) praised the related 'Bundles' grouping as 'top shelf.' Missing for 10: explicit documentation that the default splits match the exact categories named (team, newsletters, calendar invites) rather than just importance-based tabs, and more independent verification of the feature's real-world triage benefit.", "evidenceIds": [ "shortwave-docs-9", "shortwave-docs-21", "shortwave-docs-33", "shortwave-comm-4" ] }, { "productId": "shortwave", "storyId": "tracker-blocking", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "No evidence anywhere in the pack describes Shortwave blocking sender tracking pixels, nor does it detail transparent data-handling practices for mail content; the only related community evidence (comm-6, comm-7) actually raises unaddressed privacy concerns about syncing sensitive mail and sharing content/metadata with third-party vendors. missing for 10: any mention of read-pixel/tracking-pixel blocking, any transparency documentation on mail data handling, and evidence rebutting the third-party data-sharing concerns.", "evidenceIds": [ "shortwave-comm-6", "shortwave-comm-7" ] }, { "productId": "superhuman", "storyId": "agent-email-end-to-end", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Superhuman documents a first-party MCP server connecting Claude/ChatGPT (and other assistants) to inbox and calendar, enabling reading, summarizing, drafting, and sending emails via prompts, with explicit send-approval controls and an official MCP feature probe confirming the endpoint exists. missing for 10: independent/hands-on third-party verification of the MCP integration working end-to-end, and detail on triage/labeling actions being fully agent-driven rather than app-side AI.", "evidenceIds": [ "superhuman-docs-10", "superhuman-docs-11", "superhuman-docs-24", "superhuman-docs-37", "superhuman-docs-41", "superhuman-docs-64", "superhuman-probe-3" ] }, { "productId": "superhuman", "storyId": "agentic-agent-docs", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "The probe explicitly shows llms.txt returns 404 and no agent-oriented docs (openapi/well-known) are found; while an MCP server exists, there's no evidence of llms.txt or similar agent-discovery docs a user could point an agent at.", "evidenceIds": [ "superhuman-probe-1", "superhuman-probe-2" ] }, { "productId": "superhuman", "storyId": "agentic-ai-insights", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "Superhuman Mail delivers extensive AI-generated insights from user data: Ask AI answers questions by mining inbox content (e.g., flight/hotel/offsite queries), Auto Drafts pull context from inbox, calendar, and web to write ready-to-send replies, Auto Labels classify and surface important emails, and read-status/follow-up nudges surface actionable insights. First-party docs are extensive and consistent across many features (Ask AI, Auto Drafts 2.0, Auto Labels, Email Assistant), though independent hands-on validation specifically of the AI-insight features (vs. general product commentary) is thin. Missing for 10: independent/hands-on corroboration specifically validating the accuracy or usefulness of AI-generated insights (most evidence is vendor-authored).", "evidenceIds": [ "superhuman-docs-4", "superhuman-docs-18", "superhuman-docs-26", "superhuman-docs-38", "superhuman-docs-52", "superhuman-docs-59", "superhuman-docs-14", "superhuman-docs-46", "superhuman-docs-27" ] }, { "productId": "superhuman", "storyId": "agentic-autonomous-automation", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Superhuman documents proactive automations: Auto Archive/Auto Labels/Auto Drafts run automatically in the background, and a newer 'agents' feature lets users build proactive agents via chat or visual builder with admin-governed triggers and connectors. However, sending still requires explicit human approval, limiting true autonomy, and there is no independent/hands-on corroboration of the agent-builder feature working as described. Missing for 10: third-party verification of the visual builder/agent triggers, detail on failure/error handling for autonomous runs, and evidence of unattended send/execute actions.", "evidenceIds": [ "superhuman-docs-61", "superhuman-docs-62", "superhuman-docs-3", "superhuman-docs-38", "superhuman-docs-41" ] }, { "productId": "superhuman", "storyId": "agentic-builtin-assistant", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Superhuman ships a built-in AI assistant that auto-labels, archives, drafts replies, answers questions, and now supports building proactive agents from triggers/connectors with admin governance, all documented extensively as first-party features (docs-2,6,25,27,38,61,62,64). This directly matches delegating tasks to an in-product AI assistant beyond simple automation.\nMissing for 10: independent/hands-on user reports specifically validating the delegation/agent-building experience (community evidence covers general product sentiment, not this AI-assistant delegation feature).", "evidenceIds": [ "superhuman-docs-2", "superhuman-docs-6", "superhuman-docs-25", "superhuman-docs-27", "superhuman-docs-38", "superhuman-docs-61", "superhuman-docs-62", "superhuman-docs-64" ] }, { "productId": "superhuman", "storyId": "agentic-headless", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Superhuman Mail is a GUI email client with an MCP server and agent triggers, but there is no evidence of a CLI, API, or documented mode to run the product headlessly or invoke it from a CI pipeline — probes for llms.txt and OpenAPI specs both returned 404. The story is plausible for an AI-native product with automation features, so it is not out of scope, but no evidence supports the specific headless/CI capability.", "evidenceIds": [ "superhuman-probe-1", "superhuman-probe-2", "superhuman-docs-61" ] }, { "productId": "superhuman", "storyId": "agentic-mcp-client", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "All evidence describes Superhuman Mail acting as an MCP *server* that Claude/ChatGPT connect to (docs-10, docs-37, docs-24, probe-3), not Superhuman itself consuming external MCP servers' tools as a client. There is no evidence that a user can plug third-party MCP servers into Superhuman so it gains their tools.", "evidenceIds": [ "superhuman-docs-10", "superhuman-docs-37", "superhuman-docs-24", "superhuman-probe-3" ] }, { "productId": "superhuman", "storyId": "agentic-mcp-server", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Superhuman documents an official Mail MCP server that connects Claude, ChatGPT, and other AI assistants to the inbox/calendar for summarizing, drafting, sending, and scheduling, with explicit send-approval controls, confirmed by a dedicated probe finding the official MCP page. Missing for 10: independent/hands-on third-party verification of the MCP server working (community evidence pack lacks any first-hand MCP usage reports) and technical details on the MCP server's implementation/spec compliance.", "evidenceIds": [ "superhuman-docs-10", "superhuman-docs-11", "superhuman-docs-37", "superhuman-docs-41", "superhuman-docs-24", "superhuman-probe-3" ] }, { "productId": "superhuman", "storyId": "agentic-nl-commands", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Superhuman supports natural-language operation via Ask AI queries, plain-language personalization instructions, AI-prompt-based Auto Labels, and full MCP integration letting users drive inbox/calendar actions (summarize, draft, send, schedule) via Claude/ChatGPT with a single prompt. missing for 10: independent/hands-on verification of natural-language command accuracy and no first-party demo of complex multi-step NL commands beyond simple prompts.", "evidenceIds": [ "superhuman-docs-10", "superhuman-docs-11", "superhuman-docs-18", "superhuman-docs-9", "superhuman-docs-15", "superhuman-docs-37", "superhuman-docs-41", "superhuman-probe-3" ] }, { "productId": "superhuman", "storyId": "agentic-official-cli", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Superhuman Mail is an email client with an MCP integration and command palette (Cmd+K), but there is no evidence of an official CLI for AI-native workflows; probes for llms.txt/openapi also return 404, and no CLI is mentioned anywhere in docs.", "evidenceIds": [ "superhuman-probe-1", "superhuman-probe-2", "superhuman-docs-8", "superhuman-docs-34" ] }, { "productId": "superhuman", "storyId": "agentic-public-api", "verdict": "partial", "quality": 6, "confidence": "high", "rationale": "Superhuman ships a documented, public MCP server (email-mcp) that lets AI-native users drive inbox/calendar actions—summarize, draft, send, schedule—directly from Claude, ChatGPT and other AI tools, which is a real programmatic surface for agentic use. However, probes confirm there is no traditional REST/OpenAPI-documented public API (llms.txt and openapi.json endpoints all 404), so developers outside the MCP/AI-assistant flow have no documented way to integrate. Missing for 10: a general-purpose REST/GraphQL API with OpenAPI spec, and any independent/hands-on verification of the MCP server's reliability.", "evidenceIds": [ "superhuman-docs-10", "superhuman-docs-37", "superhuman-docs-41", "superhuman-docs-64", "superhuman-probe-1", "superhuman-probe-2", "superhuman-probe-3" ] }, { "productId": "superhuman", "storyId": "agentic-scoped-keys", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows Superhuman Mail connects to Claude/ChatGPT via MCP and includes approval gates ('every send action requires explicit approval') plus admin-level 'connector permissions' governance, but there is no evidence of an actual scoped/least-privilege API credential or key system that an ai-native user can issue to individual agents. Probes for llms.txt and OpenAPI specs both return 404, suggesting no public API surface for credential scoping exists.", "evidenceIds": [ "superhuman-docs-41", "superhuman-docs-62", "superhuman-probe-1", "superhuman-probe-2" ] }, { "productId": "superhuman", "storyId": "agentic-sdks", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows Superhuman ships an MCP server for AI assistants (docs-10, docs-37, probe-3) but there is no mention of official SDKs, client libraries, or public API documentation for developers; explicit probes for llms.txt and OpenAPI/Swagger specs both returned 404 (superhuman-probe-1, superhuman-probe-2), indicating no official SDK exists.", "evidenceIds": [ "superhuman-probe-1", "superhuman-probe-2", "superhuman-docs-10", "superhuman-docs-37" ] }, { "productId": "superhuman", "storyId": "agentic-webhooks", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows Superhuman offers an MCP server for AI assistant integration and an agents/automation feature, but nothing describes webhook subscriptions or event-driven push notifications for external systems; API/OpenAPI probes also returned 404s, indicating no documented webhook API.", "evidenceIds": [ "superhuman-probe-1", "superhuman-probe-2", "superhuman-docs-10" ] }, { "productId": "superhuman", "storyId": "ai-drafts-in-my-voice", "verdict": "full", "quality": 9, "confidence": "high", "rationale": "Superhuman's Auto Drafts feature explicitly writes replies in the user's own voice/tone (matching style from sent emails, even per-recipient), pulling context from inbox/calendar/web, and presents them ready to edit and send rather than generic boilerplate — with explicit human approval before sending. This is well-documented across first-party docs with consistent detail; missing for 10: independent/hands-on user corroboration of draft quality/voice-matching accuracy beyond vendor claims.", "evidenceIds": [ "superhuman-docs-23", "superhuman-docs-35", "superhuman-docs-43", "superhuman-docs-64", "superhuman-docs-38", "superhuman-docs-52", "superhuman-docs-59", "superhuman-docs-41", "superhuman-docs-57" ] }, { "productId": "superhuman", "storyId": "ai-inbox-answers", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Superhuman's Ask AI feature directly supports natural-language Q&A grounded in the inbox and calendar (e.g., 'where is the q2 offsite', 'when is my flight', 'where am I staying'), and the MCP integration extends this to Claude/ChatGPT for cross-inbox/calendar queries, drafting, and scheduling grounded in real data. Missing for 10: independent/hands-on evidence validating accuracy of 'grounded answers' across a full inbox+calendar corpus, and detail on how well it surfaces 'what's outstanding' beyond follow-up reminders.", "evidenceIds": [ "superhuman-docs-4", "superhuman-docs-18", "superhuman-docs-26", "superhuman-docs-10", "superhuman-docs-37", "superhuman-docs-24" ] }, { "productId": "superhuman", "storyId": "ai-triage-labels", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Superhuman documents auto-labeling ('Auto Labels'), custom AI-prompt categories, auto-archiving of low-priority mail, inbox splitting into topic tabs, and immediate labeling on arrival — directly matching triage/categorization needs. Steerability is evidenced via custom prompt-based Auto Labels, plain-language instructions, and admin governance controls, plus auditability via draft review before sending and explicit send approval. missing for 10: independent/hands-on validation of triage accuracy or audit trail is absent, and community evidence is largely about UI/performance rather than AI triage quality.", "evidenceIds": [ "superhuman-docs-3", "superhuman-docs-14", "superhuman-docs-15", "superhuman-docs-16", "superhuman-docs-21", "superhuman-docs-22", "superhuman-docs-27", "superhuman-docs-58", "superhuman-docs-33", "superhuman-docs-41", "superhuman-docs-62" ] }, { "productId": "superhuman", "storyId": "api-interactive-docs", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "There is no evidence of an interactive API reference or runnable examples; probes explicitly confirm no OpenAPI/swagger spec and no llms.txt is available, and the MCP server page offers no interactive docs/playground.", "evidenceIds": [ "superhuman-probe-1", "superhuman-probe-2", "superhuman-probe-3" ] }, { "productId": "superhuman", "storyId": "api-machine-spec", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Direct probes for OpenAPI/Swagger specs and llms.txt all returned 404s, and no documentation mentions a downloadable machine-readable API spec; only an MCP server is offered, which is a separate mechanism, not an API spec.", "evidenceIds": [ "superhuman-probe-1", "superhuman-probe-2" ] }, { "productId": "superhuman", "storyId": "api-sandbox", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence anywhere in the pack mentions a sandbox, test/staging environment, or any way to develop or validate AI workflows against non-production data — the docs only describe production-facing features (MCP, auto-drafts, auto-labels) with no mention of test environments. missing for 10: any sandbox/staging environment, test data isolation, or dev-mode API/MCP endpoint separate from live inbox data.", "evidenceIds": [] }, { "productId": "superhuman", "storyId": "api-versioning-policy", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of any versioned public API or documented deprecation policy; probes for OpenAPI specs returned 404s, and there's no mention of API versioning or deprecation practices anywhere in the docs. The only developer-facing surface found is the MCP server, which is unrelated to API versioning guarantees. missing for 10: any public API documentation, version numbers, changelog/deprecation policy, or evidence of stable programmatic interfaces.", "evidenceIds": [ "superhuman-probe-2", "superhuman-probe-1" ] }, { "productId": "superhuman", "storyId": "assignment-and-routing", "verdict": "partial", "quality": 4, "confidence": "medium", "rationale": "Superhuman offers team-collaboration signals like shared read statuses, reply indicators, and @mention team comments that help avoid duplicate work, plus shared snippets and team scheduling — but there is no evidence of formal conversation assignment or rule-based mail routing that establishes explicit ownership of a thread to a specific teammate. Missing for 10: dedicated 'assign to teammate' functionality, configurable routing/ownership rules for incoming mail, and any independent confirmation these team features work as advertised.", "evidenceIds": [ "superhuman-docs-49", "superhuman-docs-50", "superhuman-docs-55", "superhuman-docs-56", "superhuman-docs-71", "superhuman-docs-72" ] }, { "productId": "superhuman", "storyId": "automation-bulk-operations", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Superhuman supports batch-style operations like Auto Archive, Auto Labels, and 'Handle every follow-up with one prompt' (checking read status, drafting all nudges, sending in bulk) plus MCP-driven workflows that run across the whole inbox/calendar, giving genuine bulk automation for triage, labeling, and follow-ups. However, this is scoped to email/calendar items only and there's no evidence of arbitrary bulk operations across many items in a single explicit action (e.g., bulk delete/move/tag N selected emails via UI or API in one command) or bulk operation limits/performance at scale. missing for 10: evidence of explicit multi-item bulk actions (e.g., select-and-bulk-process UI), scale/performance data on bulk automation, and independent/hands-on confirmation of bulk operations working reliably.", "evidenceIds": [ "superhuman-docs-25", "superhuman-docs-31", "superhuman-docs-16", "superhuman-docs-3", "superhuman-docs-15", "superhuman-docs-37", "superhuman-docs-61", "superhuman-docs-10" ] }, { "productId": "superhuman", "storyId": "automation-rules-engine", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Superhuman documents explicit rule/trigger-based automation: custom Auto Labels driven by user-defined AI prompts, Auto Archive, Auto Drafts, and a stated capability to \"create agents that run proactively based on triggers you set and the work you connect\" with admin governance over agent building. This directly matches the ai-native automation-depth story of defining rules that fire actions on events. missing for 10: independent/hands-on verification of the rule engine's reliability and richer documentation of trigger/condition/action logic beyond marketing copy.", "evidenceIds": [ "superhuman-docs-61", "superhuman-docs-62", "superhuman-docs-15", "superhuman-docs-22", "superhuman-docs-33", "superhuman-docs-3", "superhuman-docs-16", "superhuman-docs-27" ] }, { "productId": "superhuman", "storyId": "automation-scheduled-jobs", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Superhuman documents 'agents that run proactively based on triggers you set' and MCP-driven 'workflows that run across your inbox and calendar,' suggesting some automation/triggering capability, but there's no detail on recurring/scheduled job mechanics (e.g., cron-like scheduling, workflow persistence) and no independent/hands-on corroboration. Missing for 10: explicit recurring-schedule configuration details, independent verification that these agent workflows actually run repeatedly/reliably, and more than a passing marketing mention.", "evidenceIds": [ "superhuman-docs-61", "superhuman-docs-62", "superhuman-docs-37" ] }, { "productId": "superhuman", "storyId": "automation-versioned-workflows", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Superhuman offers automations like Auto Labels, Auto Archive, agent builders, and MCP-driven workflows, but there is no evidence of version history, review/audit trails, or rollback capability for these automations. Missing for 10: version history of automation rules, diff/review UI before changes take effect, rollback/undo mechanism for automation edits.", "evidenceIds": [] }, { "productId": "superhuman", "storyId": "beyond-email-channels", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "All evidence is about email (Gmail/Outlook) plus calendar integration; there is no mention of SMS, WhatsApp, social, or live chat channels being unified into the same inbox. The product is positioned strictly as an email/calendar client with AI and MCP integrations, not an omnichannel customer messaging platform.", "evidenceIds": [] }, { "productId": "superhuman", "storyId": "bulk-triage-actions", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Superhuman documents AI-driven Auto Archive and Auto Labels that batch-classify/archive whole categories of mail automatically, plus a command palette (Cmd+K) said to 'instantly do any action,' and split-inbox tabs to 'get through emails of the same type, at the same time' — all of which gesture at bulk triage outcomes, but none explicitly describe a manual multi-select-then-archive/label/mark-done workflow across many conversations. Missing for 10: explicit documentation or independent confirmation of manual multi-select bulk actions (checkbox/shift-click select many threads, then batch archive/label/mark-done in one keystroke).", "evidenceIds": [ "superhuman-docs-16", "superhuman-docs-17", "superhuman-docs-27", "superhuman-docs-34", "superhuman-docs-45" ] }, { "productId": "superhuman", "storyId": "calendar-inside-client", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Superhuman Calendar lets users view their day in the email side panel, add/toggle multiple calendars, and use 'Find Time' to schedule meetings with teammates across time zones, all without leaving the client. However, none of the evidence explicitly confirms responding to/RSVPing on calendar invites or manually creating new calendar events from within the client. Missing for 10: explicit invite-response (accept/decline) capability, explicit event-creation UI/flow evidence, independent hands-on confirmation of calendar features.", "evidenceIds": [ "superhuman-docs-7", "superhuman-docs-19", "superhuman-docs-32", "superhuman-docs-44", "superhuman-docs-68" ] }, { "productId": "superhuman", "storyId": "full-history-import", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence in the pack describes importing mail history or contacts from another provider/client; Superhuman only connects live Gmail/Outlook accounts, with no mention of migration, historical import, or contact import tools. Missing for 10: any documentation of import/migration functionality, historical mail transfer, or contact import from other providers.", "evidenceIds": [] }, { "productId": "superhuman", "storyId": "instant-search-operators", "verdict": "disputed", "quality": 4, "confidence": "medium", "rationale": "Superhuman markets 'Ask AI' as a way to get answers without keyword search (docs-4, docs-18, docs-26) but the evidence pack contains no documentation of actual search operators, filters, or ranked-results syntax across full mail history. A hands-on ex-user reports search was actually slow ('ten seconds' vs Gmail's instant) contradicting the 'fastest email' marketing, while another user reports search is 'blazing fast' (superhuman-comm-7 vs superhuman-comm-9), creating a genuine dispute rather than settled capability. missing for 10: documented search operator syntax, filter capabilities, ranked-results mechanism, and independent confirmation resolving the speed contradiction.", "evidenceIds": [ "superhuman-docs-4", "superhuman-docs-18", "superhuman-docs-26", "superhuman-comm-7", "superhuman-comm-9" ] }, { "productId": "superhuman", "storyId": "internal-comments-mentions", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Superhuman's Team Comments feature explicitly supports @mentioning teammates, sharing live email views, and coordinating internal discussion without external recipients seeing it — directly matching the story's side-thread/comment use case, backed by Team Read Statuses and Reply Indicators for coordination. Missing for 10: independent/hands-on validation of the comment threading UX and details on comment persistence/notification workflow beyond vendor blog claims.", "evidenceIds": [ "superhuman-docs-55", "superhuman-docs-49", "superhuman-docs-50", "superhuman-docs-71", "superhuman-docs-72" ] }, { "productId": "superhuman", "storyId": "keyboard-first-speed", "verdict": "disputed", "quality": 6, "confidence": "medium", "rationale": "Superhuman documents a comprehensive Cmd+K command palette that surfaces every action and teaches shortcuts (docs-8, docs-34) plus fast reply shortcuts (docs-67), fitting the keyboard-power-user story. However, hands-on community reports are split: some users call it 'blazingly fast' (comm-9), while at least one ex-user reports search taking ten seconds vs instant in Gmail, directly contradicting the 'never wait' claim (comm-7), and another calls the UI just a 'cuter UI' around Gmail features with no real speed edge (comm-12). Missing for 10: a documented exhaustive keyboard-shortcut reference beyond the command palette, and independent benchmark data resolving the conflicting speed reports.", "evidenceIds": [ "superhuman-docs-8", "superhuman-docs-34", "superhuman-docs-67", "superhuman-comm-7", "superhuman-comm-9", "superhuman-comm-12" ] }, { "productId": "superhuman", "storyId": "masked-aliases", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence anywhere in the pack mentions email aliasing, masked/anonymous addresses, or any feature to hide a user's real address from sign-ups or strangers; Superhuman's documented features focus on AI triage, drafting, scheduling, and MCP integrations, not address privacy. Missing for 10: any mention of alias generation, masked email addresses, or privacy-relay/forwarding features.", "evidenceIds": [] }, { "productId": "superhuman", "storyId": "multi-account-unified", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Superhuman clearly supports connecting and instantly switching between multiple Gmail and Outlook/Microsoft 365 accounts from one place (docs-12, docs-19, docs-20, docs-24, docs-40, docs-53), which covers two of the three providers in the story. However, no evidence mentions generic IMAP account support, so the 'switcher from any IMAP provider' part of the story is unaddressed. Missing for 10: explicit IMAP account support/connection, independent/hands-on confirmation of multi-provider account switching beyond vendor docs.", "evidenceIds": [ "superhuman-docs-12", "superhuman-docs-19", "superhuman-docs-20", "superhuman-docs-24", "superhuman-docs-40", "superhuman-docs-53" ] }, { "productId": "superhuman", "storyId": "offline-access", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Superhuman's own docs repeatedly claim the app 'works perfectly offline' and even when the connection is terrible, suggesting core reading/composing functionality persists without a network. However, there is no explicit documentation of offline search behavior or how changes (sent drafts, read/archive actions) reconcile once reconnected, and no independent/hands-on corroboration of offline sync reliability. missing for 10: explicit description of offline search indexing, detail on conflict resolution/sync-on-reconnect mechanics, and third-party verification of offline behavior.", "evidenceIds": [ "superhuman-docs-13", "superhuman-docs-28", "superhuman-docs-42" ] }, { "productId": "superhuman", "storyId": "open-protocol-access", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Superhuman is a proprietary client layered on top of Gmail/Outlook accounts; the evidence pack contains no mention of IMAP/JMAP/SMTP access, standards-based export, or any data-portability guarantee — only MCP integration for AI assistants and account switching between Gmail/Outlook. No documentation addresses protocol-level openness or export, so switchers have no evidence their mail stays reachable outside Superhuman's own app.", "evidenceIds": [] }, { "productId": "superhuman", "storyId": "openness-api-parity", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Superhuman exposes an official MCP server (email-mcp) letting AI assistants read, draft, send emails, summarize threads, and schedule meetings — a real but curated subset of UI actions — while probes show no public REST/OpenAPI spec (404s on openapi.json/llms.txt), meaning many UI capabilities (Auto Labels config, split inbox, Snippets, team features, Command palette, offline mode) have no documented API equivalent. Missing for 10: full OpenAPI/REST documentation, evidence of parity for non-email/calendar UI features (labels, snippets, team collaboration, command palette), and independent confirmation that MCP covers 1:1 UI functionality.", "evidenceIds": [ "superhuman-docs-10", "superhuman-docs-11", "superhuman-docs-24", "superhuman-docs-37", "superhuman-docs-41", "superhuman-probe-1", "superhuman-probe-2", "superhuman-probe-3" ] }, { "productId": "superhuman", "storyId": "openness-full-export", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence of any data export capability, open-format export, or account portability/exit tooling in the evidence pack; the product is an email client layered on Gmail/Outlook but nothing documents exporting Superhuman-specific data (labels, snippets, agent configs) or facilitating leaving the platform. missing for 10: data export feature docs, open format (e.g. mbox/CSV/JSON) support, migration/exit tooling, any independent confirmation of portability.", "evidenceIds": [] }, { "productId": "superhuman", "storyId": "openness-open-license", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Superhuman Mail is closed-source proprietary SaaS; no evidence of any open-licensed source availability. missing for 10: any mention of open-source license, public repository, or source availability.", "evidenceIds": [] }, { "productId": "superhuman", "storyId": "openness-self-host", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Superhuman Mail is a proprietary SaaS email client; no evidence anywhere in the pack indicates a self-hostable version, on-prem deployment, or open-source core. All evidence describes a cloud-hosted product with API/MCP integrations, not self-hosting options.", "evidenceIds": [] }, { "productId": "superhuman", "storyId": "privacy-data-residency", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence anywhere in the pack mentions data residency, region selection, or storage location choices for Superhuman Mail; the axis applies to an email/data platform but no capability is documented.", "evidenceIds": [] }, { "productId": "superhuman", "storyId": "privacy-no-training", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack addresses data usage for AI model training, opt-out settings, or any privacy/data-retention policy statement — the evidence pack is entirely about feature functionality (AI drafting, labeling, MCP, calendar) with no mention of training-data controls. missing for 10: any privacy policy statement on AI training data usage, an opt-out or opt-in toggle for model training, or third-party confirmation of data handling practices.", "evidenceIds": [] }, { "productId": "superhuman", "storyId": "privacy-retention-controls", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "The evidence pack contains no mention of data retention settings, deletion controls, or data lifecycle policies for Superhuman Mail or its AI/MCP features—only feature descriptions, community sentiment, and unrelated probes. This is a fair privacy-posture question for an AI-native email product, but no evidence shows such controls exist.", "evidenceIds": [] }, { "productId": "superhuman", "storyId": "privacy-telemetry-optout", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence pack item addresses telemetry, analytics opt-out, or usage-tracking controls; one community comment even notes Superhuman does not let users disable image-loading tracking, but this doesn't constitute a documented telemetry opt-out and can't establish 'disputed' since no vendor claim of an opt-out exists to contradict.", "evidenceIds": [] }, { "productId": "superhuman", "storyId": "read-statuses", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Superhuman docs confirm read-status tracking ('check which emails have been read', 'Read statuses are now shared across your team') and community evidence (superhuman-comm-1, criticizing image-based tracking as 'spying') independently corroborates that read/open tracking is a real, functioning feature. However, no evidence explicitly confirms a timestamped 'when opened' view for individual recipients—only binary read/unread status and team-level sharing are documented. Missing for 10: explicit per-recipient open-time timestamps, hands-on verification of accuracy/reliability of the read-tracking mechanism.", "evidenceIds": [ "superhuman-docs-25", "superhuman-docs-31", "superhuman-docs-49", "superhuman-docs-71", "superhuman-comm-1" ] }, { "productId": "superhuman", "storyId": "scheduled-send-undo", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "No evidence in the pack mentions scheduled send or an undo-send grace window feature for Superhuman Mail; the docs cover AI drafting, labeling, MCP integration, and other features but nothing about delayed/scheduled sending or send-undo functionality.", "evidenceIds": [] }, { "productId": "superhuman", "storyId": "self-host-option", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Superhuman Mail is a cloud SaaS client layered on top of Gmail/Outlook accounts; there is no evidence of any self-hosted deployment option, open-source server, or ability to run the mail pipeline on infrastructure the user controls. All evidence points to a hosted, proprietary service with no self-host path, so this axis is not delivered.", "evidenceIds": [] }, { "productId": "superhuman", "storyId": "share-availability", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Superhuman's Auto Drafts explicitly 'insert availability' pulled from your calendar (docs-38), the Calendar feature lets you 'Find Time' to instantly see when teammates are free (docs-7), and users can add plain-language instructions like 'use this booking link' to personalize scheduling in drafts (docs-9, docs-54, docs-60). Missing for 10: independent/hands-on verification of this exact workflow and more detail on native booking-link generation vs. relying on a user-supplied link.", "evidenceIds": [ "superhuman-docs-38", "superhuman-docs-7", "superhuman-docs-9", "superhuman-docs-54", "superhuman-docs-60" ] }, { "productId": "superhuman", "storyId": "shared-team-inbox", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Superhuman ships several team-collaboration features that approximate shared inbox awareness — team read statuses, reply indicators to avoid double-replies, team comments for internal coordination without external visibility, and shared snippets/scheduling — giving a team-lead's group real-time visibility into who's handling what (superhuman-docs-49,50,51,55,56,71,72,73). However, this is built on individually-owned mailboxes with cross-visibility signals, not a true shared/group inbox or shared account model where the whole team works one conversation queue with assignment/ownership. Missing for 10: evidence of a genuine shared mailbox/account model, ticket-style assignment of conversations, and independent confirmation of how well these team signals work in practice.", "evidenceIds": [ "superhuman-docs-49", "superhuman-docs-50", "superhuman-docs-51", "superhuman-docs-55", "superhuman-docs-56", "superhuman-docs-71", "superhuman-docs-72", "superhuman-docs-73" ] }, { "productId": "superhuman", "storyId": "snippets-templates", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Superhuman's Snippets feature is well documented — insert commonly-used phrases, paragraphs, or whole emails via keyboard shortcut, and share snippets across a team — directly matching the 'saved templates instead of retyping' part of the story. However, no evidence mentions variable/placeholder support (e.g., auto-filled name/date fields) or attaching files as part of a snippet/template. Missing for 10: variable/placeholder support in snippets, attachment bundling within snippets, independent hands-on confirmation of these specifics.", "evidenceIds": [ "superhuman-docs-47", "superhuman-docs-48", "superhuman-docs-56", "superhuman-docs-70" ] }, { "productId": "superhuman", "storyId": "snooze-and-reminders", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Superhuman documents an automated follow-up reminder system that drafts nudges and resurfaces threads needing a response when no reply has come ('automatically reminded to follow up—with a draft already written', 'check which emails have been read, draft all the nudges, and send when each recipient is most likely to open it'), closely matching the reminder half of the story. However, there is no explicit mention of a 'snooze' feature to temporarily hide a conversation and resurface it later, which is a core part of the story. Missing for 10: explicit snooze/defer-conversation functionality, independent/hands-on confirmation of the follow-up reminder behavior.", "evidenceIds": [ "superhuman-docs-6", "superhuman-docs-36", "superhuman-docs-25", "superhuman-docs-31", "superhuman-docs-27", "superhuman-docs-66" ] }, { "productId": "superhuman", "storyId": "split-inbox-triage", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Superhuman explicitly documents 'split inbox' functionality with custom categories like VIP, Notifications, Calendar, and Team, plus custom Auto Labels that let users organize incoming mail into tabs by type so triage happens by focus area rather than arrival order. This is a first-party documented feature with a dedicated blog post, not just a vague claim. missing for 10: independent/hands-on confirmation of the split-inbox feature specifically (community evidence covers other aspects of Superhuman but not this feature) and detail on how priority ordering interacts with arrival order within each stream.", "evidenceIds": [ "superhuman-docs-5", "superhuman-docs-39", "superhuman-docs-45", "superhuman-docs-69", "superhuman-docs-22", "superhuman-docs-63", "superhuman-docs-17", "superhuman-docs-33" ] }, { "productId": "superhuman", "storyId": "tracker-blocking", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No documentation claims Superhuman blocks tracking pixels by default or explains transparent data handling; in fact, community evidence explicitly states Superhuman does not let users disable images/tracking pixels, meaning senders' read-tracking is not blocked. No privacy-policy or data-handling transparency evidence is present either.", "evidenceIds": [ "superhuman-comm-1" ] }, { "productId": "zero", "storyId": "agent-email-end-to-end", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Zero documents an official MCP server (MCP.md, verified by probe) enabling agents like Claude to read threads, ask questions about mailbox content, compose with AI assistance, and create/send drafts and new emails, plus manage labels — covering triage, drafting, and sending end to end via Better Auth session token auth. missing for 10: no hands-on third-party report of an external agent (Claude/ChatGPT) actually completing a full read-triage-send workflow, and OAuth support is still 'coming soon' rather than shipped.", "evidenceIds": [ "zero-docs-4", "zero-docs-5", "zero-docs-9", "zero-docs-11", "zero-docs-14", "zero-docs-8", "zero-probe-1", "zero-probe-rt-1" ] }, { "productId": "zero", "storyId": "agentic-agent-docs", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "The repo ships an AGENT.md (agent-configuration doc) and a detailed MCP.md describing the MCP server's tool surface, both of which are exactly the kind of machine/agent-oriented documentation an AI agent could be pointed at; this was confirmed by a hands-on probe of the actual repo tree. However there is no evidence of a dedicated llms.txt file or any explicit guidance framing these docs as an 'agent-readable spec' in the llms.txt convention. Missing for 10: an actual llms.txt file, first-party statement that docs are structured for LLM consumption, and independent confirmation an agent successfully parsed these docs.", "evidenceIds": [ "zero-probe-rt-1", "zero-probe-1", "zero-docs-8", "zero-docs-14" ] }, { "productId": "zero", "storyId": "agentic-ai-insights", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Zero documents AI features that generate insights from mailbox data: composing emails with AI assistance, answering questions about mailbox content and specific threads, and summarizing/chatting with inbox content, corroborated by founder description of AI-powered summarization and chat-with-inbox in community coverage. missing for 10: independent hands-on verification of insight quality/accuracy and no broader third-party review confirming these AI features work reliably in practice.", "evidenceIds": [ "zero-docs-5", "zero-docs-9", "zero-docs-14", "zero-comm-1", "zero-probe-rt-1" ] }, { "productId": "zero", "storyId": "agentic-autonomous-automation", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows an MCP server exposing on-demand email tools (search, compose, label, delete) that an AI client can call interactively, but nothing shows Zero itself scheduling or running autonomous background automations/triggers/workflows without a user or agent actively invoking them.", "evidenceIds": [] }, { "productId": "zero", "storyId": "agentic-builtin-assistant", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Zero ships a built-in AI assistant that can compose emails, answer questions about threads/mailbox, and perform web search (Perplexity), confirmed both in docs (MCP.md) and independent community description of it as an 'AI-powered email client' that summarizes, drafts, and lets users chat with their inbox. Missing for 10: broader independent hands-on verification beyond a single HN comment, and clearer distinction between MCP-exposed tools vs. in-app assistant UX.", "evidenceIds": [ "zero-docs-4", "zero-docs-5", "zero-docs-9", "zero-docs-14", "zero-comm-1", "zero-probe-rt-1" ] }, { "productId": "zero", "storyId": "agentic-headless", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is \"none\", never \"na\". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)", "evidenceIds": [] }, { "productId": "zero", "storyId": "agentic-mcp-client", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "All evidence describes Zero exposing its own email/label/compose tools via an official 'ZeroMCP' server for other AI agents to consume — i.e., Zero acting as an MCP server/provider, not as a client that plugs in external MCP servers to use their tools. There is no documentation of Zero itself connecting to third-party MCP servers to extend its own toolset.", "evidenceIds": [ "zero-docs-8", "zero-probe-1", "zero-probe-rt-1", "zero-docs-14" ] }, { "productId": "zero", "storyId": "agentic-mcp-server", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Zero ships a documented, named 'Zero MCP' server (MCP.md) exposing concrete tools (email CRUD, labels, AI compose, mailbox Q&A, web search) with an authentication method (Better Auth session token, OAuth coming soon), confirmed by an independent runtime probe finding the file in the actual repo. Missing for 10: independent hands-on verification that a third-party agent successfully connects and uses the server end-to-end, and OAuth is still unimplemented.", "evidenceIds": [ "zero-docs-8", "zero-docs-11", "zero-docs-14", "zero-probe-1", "zero-probe-rt-1" ] }, { "productId": "zero", "storyId": "agentic-nl-commands", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Zero's founder describes it as an AI-powered email client where users can chat with their inbox, ask questions about threads, and have AI draft replies, and the MCP docs confirm natural-language driven actions (compose, search, ask questions, web search) — this directly matches AI-native NL command operation. Missing for 10: independent hands-on verification of the actual chat UI/NL command interface beyond founder claims and MCP protocol docs.", "evidenceIds": [ "zero-comm-1", "zero-docs-5", "zero-docs-9", "zero-docs-14", "zero-docs-4" ] }, { "productId": "zero", "storyId": "agentic-official-cli", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Zero's evidence shows an MCP server (ZeroMCP) and self-hosting via docker-compose, plus a pnpm-based dev script for Drizzle Studio, but no official CLI tool for AI-native interaction with the product itself is documented anywhere in the pack.", "evidenceIds": [ "zero-docs-8", "zero-docs-16", "zero-probe-1" ] }, { "productId": "zero", "storyId": "agentic-public-api", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Zero ships a documented MCP server (ZeroMCP) exposing a public, structured API for emails, labels, AI compose, mailbox Q&A, and web search, with authentication documented via Better Auth session tokens (OAuth coming soon), corroborated by a runtime probe confirming the real MCP.md and AGENT.md files in the repo. missing for 10: independent third-party usage/testing of the MCP API beyond first-party docs and a single runtime probe, and full OAuth support (currently listed as coming soon).", "evidenceIds": [ "zero-docs-8", "zero-docs-11", "zero-docs-14", "zero-probe-1", "zero-probe-rt-1" ] }, { "productId": "zero", "storyId": "agentic-scoped-keys", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Zero's MCP server documents authentication via a Better Auth session token (or future OAuth), but there is no evidence of scoped or least-privilege credential issuance, permission granularity, or agent-specific token scoping — auth appears to be a single session-level token granting full account access. Missing for 10: any documentation of scopes/permissions models, per-agent credential minting, or restricted-access tokens for agents.", "evidenceIds": [ "zero-docs-8", "zero-probe-rt-1" ] }, { "productId": "zero", "storyId": "agentic-sdks", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Zero doesn't publish a traditional language SDK, but it does document an official 'ZeroMCP' server (MCP.md) with concrete tool endpoints (email CRUD, labels, AI compose, mailbox Q&A) plus AGENT.md agent-configuration docs, giving AI-native developers a documented, official programmatic interface to build against, corroborated by a runtime probe confirming these files exist in the live repo. Missing for 10: an actual client SDK/library (Python/JS package), auth beyond a session token (OAuth marked 'coming soon'), and independent third-party developer usage reports.", "evidenceIds": [ "zero-docs-1", "zero-docs-8", "zero-docs-11", "zero-probe-1", "zero-probe-rt-1", "zero-gh-7" ] }, { "productId": "zero", "storyId": "agentic-webhooks", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence covers Zero's MCP server (tool-calling actions like search, compose, label management) but nowhere mentions webhooks, event subscriptions, or push notifications for external systems to react to inbox events.", "evidenceIds": [] }, { "productId": "zero", "storyId": "ai-drafts-in-my-voice", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Zero's MCP docs and founder description confirm AI drafts replies ('Compose emails with AI assistance', 'drafts replies') as a core feature, but no evidence describes voice/tone personalization or learning the user's writing style. Missing for 10: documentation of voice/tone matching or personalization mechanism, and independent hands-on verification that drafts read as the user's own voice rather than generic AI text.", "evidenceIds": [ "zero-docs-4", "zero-docs-14", "zero-comm-1" ] }, { "productId": "zero", "storyId": "ai-inbox-answers", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Zero's MCP server explicitly supports asking questions about mailbox content and specific email threads, plus AI compose, search, and labels, and community commentary confirms an AI-powered 'chat with your inbox' experience. However, evidence doesn't show cross-inbox/whole-calendar synthesis, calendar integration, or 'who said what / what's outstanding' style grounded multi-thread reasoning — the documented Q&A appears scoped to mailbox/thread level rather than full inbox+calendar grounding. missing for 10: calendar integration/awareness, evidence of synthesizing across the entire inbox (not just single threads), independent hands-on verification of grounded multi-source answers.", "evidenceIds": [ "zero-docs-5", "zero-docs-9", "zero-docs-14", "zero-comm-1", "zero-probe-rt-1" ] }, { "productId": "zero", "storyId": "ai-triage-labels", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Community and docs evidence show Zero markets itself as an AI-powered inbox that auto-categorizes emails, and its MCP server exposes tools to modify/create labels, filter/search by label, and answer questions about threads/mailbox content, giving a steerable interface for AI actions. However, there's no explicit documentation of automatic prioritization/surfacing of 'what needs attention' or an audit log of AI triage decisions beyond the generic MCP action list. Missing for 10: dedicated 'needs attention' surfacing/prioritization feature, explicit audit trail or history of AI-taken triage actions, and independent hands-on verification of auto-labeling accuracy.", "evidenceIds": [ "zero-comm-1", "zero-docs-1", "zero-docs-3", "zero-docs-6", "zero-docs-9", "zero-probe-rt-1" ] }, { "productId": "zero", "storyId": "api-interactive-docs", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Zero is an email client with an MCP server and docs (MCP.md, ROADMAP.md), but there is no evidence of an interactive API reference (e.g., Swagger/OpenAPI explorer, Postman collection, or runnable code sandbox) for AI-native users to explore and execute example calls.", "evidenceIds": [] }, { "productId": "zero", "storyId": "api-machine-spec", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is \"none\", never \"na\". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)", "evidenceIds": [] }, { "productId": "zero", "storyId": "api-sandbox", "verdict": "none", "quality": 0, "confidence": "low", "rationale": "Zero is an AI email client whose evidence covers MCP tools for real mailbox operations (send/delete/label emails) and self-hosting, but nothing describes a sandbox, test/staging mode, or mock data environment isolated from production email accounts.", "evidenceIds": [] }, { "productId": "zero", "storyId": "api-versioning-policy", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Evidence describes Zero's MCP server capabilities and self-hosting, but no documentation anywhere mentions API versioning, version numbers, or a deprecation policy for its MCP/API surface. missing for 10: any mention of API versioning scheme, changelog/deprecation policy, or backward-compatibility guarantees.", "evidenceIds": [] }, { "productId": "zero", "storyId": "assignment-and-routing", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Zero is a personal AI-powered email client with unified inbox, labels, and MCP tooling, but no evidence anywhere in the pack describes team features like assigning conversations to teammates or configuring routing/ownership rules — capabilities relevant for shared team inboxes. This is a fair axis for an email client, but no evidence supports it, so it's 'none' rather than 'na'.", "evidenceIds": [] }, { "productId": "zero", "storyId": "automation-bulk-operations", "verdict": "partial", "quality": 5, "confidence": "medium", "rationale": "Zero's MCP server exposes email actions like 'Bulk delete emails' and 'Bulk archive emails' explicitly labeled as bulk operations, plus label/search operations that could apply across many items. However, evidence does not specify limits, batch size, or confirm bulk semantics beyond these two named actions, nor is there hands-on confirmation of bulk behavior at scale. missing for 10: independent/hands-on verification of bulk operations at scale, documentation of batch limits or performance, evidence of bulk operations beyond delete/archive (e.g., bulk label/move/send).", "evidenceIds": [ "zero-docs-2", "zero-docs-11", "zero-probe-rt-1" ] }, { "productId": "zero", "storyId": "automation-rules-engine", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows Zero as an AI email client with MCP tool actions (search, compose, label, etc.) but no documented rule-based automation engine that triggers actions on events (e.g., 'when email arrives from X, do Y'). All actions appear to be user- or agent-invoked rather than event-triggered automation. Missing for full credit: any documented trigger/condition/action rules engine or scheduled/event-based automation feature.", "evidenceIds": [ "zero-docs-1", "zero-docs-11", "zero-docs-14", "zero-probe-rt-1" ] }, { "productId": "zero", "storyId": "automation-scheduled-jobs", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Zero is an AI email client with MCP tools for email actions (labels, search, compose, AI Q&A) but no evidence of scheduling recurring jobs or workflows/automation triggers.", "evidenceIds": [] }, { "productId": "zero", "storyId": "automation-versioned-workflows", "verdict": "na", "quality": 0, "confidence": "high", "rationale": "Zero is an AI email client, not an automation/workflow-building product with versionable automations; the versioning/rollback story is a category mismatch (wrong axis).", "evidenceIds": [] }, { "productId": "zero", "storyId": "beyond-email-channels", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is \"none\", never \"na\". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)", "evidenceIds": [] }, { "productId": "zero", "storyId": "bulk-triage-actions", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Zero's MCP docs explicitly list 'Bulk delete emails' and 'Bulk archive emails' plus label modification tools, showing some bulk-action capability, but this is exposed via an AI/MCP tool interface rather than confirmed as a native UI multi-select action, and there's no mention of a 'mark done' state or how many items can be selected/acted on interactively. Community commentary even flags gaps in basic power-user UI ergonomics (no real keyboard navigation), suggesting bulk in-UI triage may be immature.\n\nmissing for 10: confirmed UI multi-select archive/label/done action, evidence of a 'done' state, independent hands-on confirmation of bulk UI workflow.", "evidenceIds": [ "zero-docs-1", "zero-docs-2", "zero-docs-13", "zero-comm-2" ] }, { "productId": "zero", "storyId": "calendar-inside-client", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is \"none\", never \"na\". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)", "evidenceIds": [] }, { "productId": "zero", "storyId": "full-history-import", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Zero connects to providers like Gmail/Outlook for unified inbox access, but no evidence describes any import/migration tool for bulk historical mail or contacts from an old provider/client — no mention of mbox/EML import, contact list import, or migration wizard.", "evidenceIds": [] }, { "productId": "zero", "storyId": "instant-search-operators", "verdict": "partial", "quality": 4, "confidence": "low", "rationale": "Evidence shows a basic 'search emails with custom queries' and 'filter by labels' capability via the MCP server, but there is no documentation of advanced operators, ranked relevance, or performance/scale across full mail history; a community comment even flags missing basic navigation features, suggesting search UX is still immature. missing for 10: documented search operators/syntax, evidence of ranking/relevance across full historical mail, performance benchmarks, independent hands-on confirmation of search speed/precision.", "evidenceIds": [ "zero-docs-6", "zero-comm-2", "zero-docs-14" ] }, { "productId": "zero", "storyId": "internal-comments-mentions", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Evidence covers email management, MCP AI features, and self-hosting, but nothing describes internal side-threads with comments/@mentions for team discussion of emails without forwarding.", "evidenceIds": [] }, { "productId": "zero", "storyId": "keyboard-first-speed", "verdict": "disputed", "quality": 2, "confidence": "medium", "rationale": "Zero's own roadmap lists 'customizable keyboard shortcuts' as a planned (not yet shipped) feature, and a hands-on community comment explicitly states the product lacks 'real keyboard navigation' today, directly contradicting any power-user keyboard-first claim; no command palette is mentioned anywhere in the evidence. missing for 10: shipped keyboard shortcut system, command palette, any evidence of interface speed/responsiveness for power users.", "evidenceIds": [ "zero-docs-10", "zero-comm-2" ] }, { "productId": "zero", "storyId": "masked-aliases", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Zero is an AI-powered unified email client with labels, search, and MCP integrations, but nothing in the evidence pack describes email alias generation or masked/burner address creation to hide a user's real address from sign-ups or strangers.", "evidenceIds": [] }, { "productId": "zero", "storyId": "multi-account-unified", "verdict": "disputed", "quality": 4, "confidence": "low", "rationale": "Zero's marketing repeatedly claims a 'Unified Inbox' connecting Gmail, Outlook, 'and more,' but the only hands-on/community description of the actual product (zero-comm-1) says it 'works on top of Gmail' and is in public beta, suggesting multi-provider (Microsoft 365, IMAP) support isn't yet realized in practice — no IMAP mention anywhere in the pack. Missing for 10: explicit IMAP support, confirmed working Microsoft 365/Outlook connection, and independent verification that multiple accounts can be worked from one place simultaneously.", "evidenceIds": [ "zero-gh-1", "zero-gh-13", "zero-comm-1" ] }, { "productId": "zero", "storyId": "offline-access", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence anywhere in the pack mentions offline mode, local caching, or sync-on-reconnect; Zero appears to be a web-based email client requiring live connection to providers/AI services, with no offline-capability documentation.", "evidenceIds": [] }, { "productId": "zero", "storyId": "open-protocol-access", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows Zero connects to providers like Gmail/Outlook and offers self-hosting and an MCP server for AI actions, but nothing in the pack mentions IMAP/JMAP/SMTP protocol access or standards-based mail export for portability — the core of this switcher story is unaddressed.", "evidenceIds": [ "zero-gh-1", "zero-gh-13", "zero-gh-2", "zero-docs-15" ] }, { "productId": "zero", "storyId": "openness-api-parity", "verdict": "partial", "quality": 6, "confidence": "medium", "rationale": "Zero's MCP server exposes many core email actions (search, send, draft, delete, labels, AI compose, thread Q&A) that mirror UI functionality, giving strong API-parity for mail operations. However missing for 10: no evidence of API parity for UI-specific settings like customizable keyboard shortcuts, UI theming/customization, unified inbox provider management, or account/connection setup via API — these remain UI-only per docs, and there's no independent confirmation the MCP surface is fully comprehensive versus a curated subset.", "evidenceIds": [ "zero-docs-4", "zero-docs-5", "zero-docs-6", "zero-docs-9", "zero-docs-11", "zero-docs-13", "zero-docs-14", "zero-probe-rt-1", "zero-docs-10", "zero-gh-3" ] }, { "productId": "zero", "storyId": "openness-full-export", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows Zero is self-hostable, open-source, and doesn't sell user data, plus a Drizzle Studio DB viewer for self-hosters, but there is no documented data-export feature (e.g., mbox/EML export, takeout tool) letting a user extract all their mail data in an open format and leave the service.", "evidenceIds": [ "zero-gh-8", "zero-gh-13", "zero-gh-15", "zero-docs-16" ] }, { "productId": "zero", "storyId": "openness-open-license", "verdict": "full", "quality": 8, "confidence": "medium", "rationale": "Zero's source is publicly hosted on GitHub (Mail-0/Zero) with a full contributing guide, self-hosting instructions, and a verified runtime probe confirming a real, clonable source tree with Docker configs for self-hosting — consistent with an open-source project freely readable by AI-native users. Missing for 10: explicit citation of the license file/name (e.g. MIT/AGPL) to confirm licensing terms.", "evidenceIds": [ "zero-gh-2", "zero-gh-8", "zero-gh-13", "zero-docs-16", "zero-probe-rt-1" ] }, { "productId": "zero", "storyId": "openness-self-host", "verdict": "full", "quality": 8, "confidence": "high", "rationale": "Multiple GitHub and docs citations explicitly advertise 'Self-Hosting Freedom' and describe running your own email app, and a runtime probe confirms a real self-hostable source tree with docker-compose files for self-hosting deployment. Missing for 10: independent hands-on report of a completed self-host deployment beyond the repo/docker-compose evidence, and more detailed self-host setup documentation.", "evidenceIds": [ "zero-gh-2", "zero-gh-6", "zero-gh-8", "zero-gh-11", "zero-gh-13", "zero-docs-15", "zero-probe-rt-1" ] }, { "productId": "zero", "storyId": "privacy-data-residency", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Zero's self-hosting capability (own infra, own database via docker-compose) lets a user effectively choose where their data lives, and it claims not to track/collect/sell data, but there is no explicit region/residency selection feature or documented multi-region hosted offering. missing for 10: explicit region/residency selection UI or hosted multi-region options, documentation on data locality guarantees for the hosted SaaS version, independent confirmation of self-host deployment satisfying residency requirements.", "evidenceIds": [ "zero-gh-2", "zero-gh-6", "zero-gh-8", "zero-gh-11", "zero-docs-15", "zero-gh-13", "zero-gh-15" ] }, { "productId": "zero", "storyId": "privacy-no-training", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Zero states it does not track, collect, or sell user data, and self-hosting is available which would let users fully control data flow, implying no AI training on user data. However, there is no explicit statement or policy about AI-model training exclusion (e.g., no clause addressing whether email content sent to AI features like compose/summarize is used for model training). missing for 10: explicit AI-training opt-out/data-use policy, third-party AI provider data-handling terms, independent verification of the no-training claim.", "evidenceIds": [ "zero-gh-15", "zero-gh-8", "zero-gh-13" ] }, { "productId": "zero", "storyId": "privacy-retention-controls", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Zero claims a no-tracking/no-sell data policy and supports self-hosting (giving users full control over their own data and deletion since they own the infrastructure), plus MCP tools include explicit 'delete emails' actions. However, there's no documented data retention policy, no explicit account/data deletion workflow or export tooling described, and no independent verification of the no-tracking claim. missing for 10: documented retention/export/deletion policy for hosted use, independent audit of data practices, explicit account-deletion or right-to-be-forgotten flow.", "evidenceIds": [ "zero-gh-15", "zero-gh-8", "zero-gh-13", "zero-docs-11", "zero-docs-2" ] }, { "productId": "zero", "storyId": "privacy-telemetry-optout", "verdict": "partial", "quality": 5, "confidence": "low", "rationale": "Zero's GitHub page states it 'does not track, collect, or sell your data in any way,' and self-hosting support (Docker compose files, self-hosting docs) lets AI-native users run their own instance with no vendor telemetry at all. However there is no explicit telemetry settings/opt-out toggle documented, no privacy policy detail, and no independent verification of the no-tracking claim. Missing for 10: explicit telemetry opt-out control/setting, detailed privacy policy, and independent/hands-on confirmation of the no-tracking claim.", "evidenceIds": [ "zero-gh-15", "zero-gh-2", "zero-gh-6", "zero-probe-rt-1" ] }, { "productId": "zero", "storyId": "read-statuses", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence anywhere in the pack mentions read receipts, open tracking, or notifications about when recipients open emails; the MCP/docs only cover sending, drafting, labeling, and searching emails.", "evidenceIds": [] }, { "productId": "zero", "storyId": "scheduled-send-undo", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence anywhere in the pack mentions scheduled send or undo-send functionality; MCP docs list send/draft/delete but nothing about delayed sending or a grace-window recall.", "evidenceIds": [ "zero-docs-11", "zero-docs-12" ] }, { "productId": "zero", "storyId": "self-host-option", "verdict": "full", "quality": 7, "confidence": "medium", "rationale": "Zero is explicitly open-source and self-hostable, with GitHub docs stating 'Self-Hosting Freedom – Run your own email app with ease' and a probe confirming a real, keyless-cloneable source tree with docker-compose files for self-hosting the full mail pipeline (DB, prod services). This gives a switcher genuine control over their own instance rather than relying on a hosted SaaS. Missing for 10: detailed self-hosting setup/migration docs (e.g. IMAP/SMTP backend specifics), independent hands-on reports of a completed self-hosted deployment, and confirmation of full mailbox portability beyond Gmail/Outlook OAuth integration.", "evidenceIds": [ "zero-gh-2", "zero-gh-6", "zero-gh-8", "zero-gh-13", "zero-probe-rt-1", "zero-docs-15" ] }, { "productId": "zero", "storyId": "share-availability", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Zero is an email client with AI/MCP features for composing, searching, and managing emails, but no evidence in the pack mentions calendar integration, availability sharing, or inserting bookable meeting times into emails.", "evidenceIds": [] }, { "productId": "zero", "storyId": "shared-team-inbox", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "Zero is positioned as a personal AI-powered unified inbox for individual users (Gmail/Outlook accounts), with no evidence of shared inboxes, team channels, or shared conversation state across multiple users; features described are individual email management, MCP tooling, and self-hosting, not multi-user collaboration.", "evidenceIds": [ "zero-gh-1", "zero-comm-1" ] }, { "productId": "zero", "storyId": "snippets-templates", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence pack item mentions saved snippets, canned responses, or templates with variables/attachments; the docs describe AI-assisted composing, MCP tools, labels, and self-hosting but nothing about a snippet/template insertion feature.", "evidenceIds": [] }, { "productId": "zero", "storyId": "snooze-and-reminders", "verdict": "none", "quality": 0, "confidence": "high", "rationale": "No evidence anywhere in the pack mentions snooze, follow-up reminders, or resurfacing threads after no reply; the documented features cover labels, search, compose, AI Q&A, and self-hosting only.", "evidenceIds": [] }, { "productId": "zero", "storyId": "split-inbox-triage", "verdict": "none", "quality": 0, "confidence": "medium", "rationale": "Evidence shows Zero supports labels, filtering, unified inbox, and AI Q&A, but there is no mention of dedicated inbox streams/views separating important, team, newsletter, and calendar-invite emails for priority-ordered triage. Labeling/filtering capabilities exist but no evidence of a stream-based triage UI or auto-categorized views as described in the story.", "evidenceIds": [ "zero-docs-1", "zero-docs-6", "zero-docs-13", "zero-comm-1" ] }, { "productId": "zero", "storyId": "tracker-blocking", "verdict": "partial", "quality": 3, "confidence": "low", "rationale": "Only a general privacy claim ('Zero does not track, collect, or sell your data in any way') is evidenced, with no mention of read-pixel/tracking-pixel blocking specifically or a detailed data-handling policy. missing for 10: explicit read-receipt/tracking-pixel blocking feature, documentation of default-on behavior, a privacy policy detailing mail data handling, and independent confirmation of the no-tracking claim.", "evidenceIds": [ "zero-gh-15" ] } ]