Superhuman Mail vs Fastmail

Multi account

1. switcherConnect several accounts across providers — Gmail, Microsoft 365, IMAP — and work them from one place

   weight 3 · round drawn
   Superhuman Mail~partialclaimed6/10

   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.

   • [claimed-docs] “you can instantly switch between Outlook and Gmail accounts without switching apps.”
   • [claimed-docs] “You can add all your Gmail and Outlook account calendars, and easily toggle them on and off.”
   • [claimed-docs] “you can instantly switch between Outlook and Gmail accounts without switching apps”
   • [claimed-docs] “Connect all your Gmail and Outlook accounts, including work, personal, and side projects. Manage every inbox and calendar from one AI assist…”
   • [claimed-docs] “it's available for [Gmail](https://blog.superhuman.com/gmail-alternatives/) and [Outlook](https://blog.superhuman.com/outlook-alternatives/)…”
   • [claimed-docs] “It helps you move faster, save time, respond sooner, and eliminate email anxiety. And it's available for Gmail and Outlook.”

   proof ↗⚑ flag

   Fastmail~partialcommunity6/10

   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.

   • [community] “As an alternative to forwarding, you can also configure Fastmail to fetch mail from (and send via) Gmail like a mail client.”
   • [community] “Fastmail has an easy migration tool as well if you don't want to go the IMAP route. Now, migrating filters and rules over on the other hand.…”
   • [claimed-docs] “Import your mail”
   • [claimed-docs] “Logging in to multiple accounts”
   • [claimed-docs] “Move from Gmail”

   proof ↗⚑ flag

Portability

1. switcherMy mail stays reachable over open protocols and standard formats — IMAP/JMAP/SMTP access and standards-based export — so no client can lock me in

   weight 2 · round to Fastmail
   Superhuman Mail—none0/10

   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.

   ⚑ flag

   Fastmail✓fullcommunity8/10

   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.

   • [claimed-docs] “Fetch `/.well-known/jmap` for the session object - capabilities, accounts, and all API URLs.”
   • [claimed-docs] “JMAP is an open standard any organisation can implement, not more proprietary lock-in from big tech companies.”
   • [claimed-docs] “Open source and standards | Fastmail”
   • [claimed-docs] “API tokens”
   • [claimed-docs] “Import your mail”
   • [community] “As an alternative to forwarding, you can also configure Fastmail to fetch mail from (and send via) Gmail like a mail client.”
   • [community] “I just use SMTP for this (with FastMail). FastMail is not really intended for [transactional emails at scale] as the limits and the like don…”
   • [community] “Fastmail has an easy migration tool as well if you don't want to go the IMAP route. Now, migrating filters and rules over on the other hand.…”

   proof ↗⚑ flag

2. switcherSelf-host the email app and keep the mail pipeline under my own control

   weight 1 · round drawn
   Superhuman Mail—none0/10

   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.

   ⚑ flag

   Fastmail—none0/10

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

   ⚑ flag

Agent access

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

   weight 2 · round drawn
   Superhuman Mail—none0/10

   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.

   • [probe] “PROBE llms.txt: HTTP 404 at https://superhuman.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://superhuman.com/openapi.json, https://superhuman.com/swagger.json, https://superhuman.com/api…”

   proof ↗⚑ flag

   Fastmail—none0/10

   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.

   • [probe] “PROBE llms.txt: HTTP 404 at https://www.fastmail.help/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.fastmail.help/openapi.json, https://www.fastmail.help/swagger.json, https://www.fastmail…”

   proof ↗⚑ flag

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

   weight 2 · round to Fastmail
   Superhuman Mail—none0/10

   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.

   • [probe] “PROBE llms.txt: HTTP 404 at https://superhuman.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://superhuman.com/openapi.json, https://superhuman.com/swagger.json, https://superhuman.com/api…”
   • [claimed-docs] “Use chat or our visual builder to create agents that run proactively based on triggers you set and the work you connect.”

   proof ↗⚑ flag

   Fastmail~partialcommunity5/10

   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.

   • [claimed-docs] “Fetch `/.well-known/jmap` for the session object - capabilities, accounts, and all API URLs.”
   • [claimed-docs] “Standard OAuth 2.0 or Bearer tokens. No custom auth protocol to implement. Works with what you already have.”
   • [claimed-docs] “API tokens”
   • [claimed-docs] “API Documentation”
   • [community] “I just use SMTP for this (with FastMail). FastMail is not really intended for [transactional emails at scale] as the limits and the like don…”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   Superhuman Mail—none0/10

   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.

   • [claimed-docs] “Superhuman Mail MCP connects your inbox and calendar into Claude, ChatGPT, and other AI assistants—so you can summarize threads, draft and s…”
   • [claimed-docs] “You can now drive Superhuman Mail from Claude, ChatGPT, and your favorite AI tools. You can create powerful workflows that run across your i…”
   • [claimed-docs] “Connect all your Gmail and Outlook accounts, including work, personal, and side projects. Manage every inbox and calendar from one AI assist…”
   • [probe] “official MCP server documented at https://superhuman.com/mail/features/email-mcp”

   proof ↗⚑ flag

   Fastmail—none0/10

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

   ⚑ flag

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

   weight 3 · round to Superhuman Mail
   Superhuman Mail✓fullprobed8/10

   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.

   • [claimed-docs] “Superhuman Mail MCP connects your inbox and calendar into Claude, ChatGPT, and other AI assistants—so you can summarize threads, draft and s…”
   • [claimed-docs] “Connect Claude or ChatGPT directly to your inbox to read, draft, and send emails with a single prompt — no copy-pasting required.”
   • [claimed-docs] “You can now drive Superhuman Mail from Claude, ChatGPT, and your favorite AI tools. You can create powerful workflows that run across your i…”
   • [claimed-docs] “Every send action requires your explicit approval, so you stay in control.”
   • [claimed-docs] “Connect all your Gmail and Outlook accounts, including work, personal, and side projects. Manage every inbox and calendar from one AI assist…”
   • [probe] “official MCP server documented at https://superhuman.com/mail/features/email-mcp”

   proof ↗⚑ flag

   Fastmail—none0/10

   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.

   • [claimed-docs] “Fetch `/.well-known/jmap` for the session object - capabilities, accounts, and all API URLs.”
   • [claimed-docs] “API tokens”
   • [probe] “PROBE llms.txt: HTTP 404 at https://www.fastmail.help/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.fastmail.help/openapi.json, https://www.fastmail.help/swagger.json, https://www.fastmail…”

   proof ↗⚑ flag

5. ai-native userUse an official CLI

   weight 2 · round drawn
   Superhuman Mail—none0/10

   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.

   • [probe] “PROBE llms.txt: HTTP 404 at https://superhuman.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://superhuman.com/openapi.json, https://superhuman.com/swagger.json, https://superhuman.com/api…”
   • [claimed-docs] “Cmd+K brings up Superhuman Command, where you can instantly do any action — and also learn the shortcut for next time.”
   • [claimed-docs] “In Superhuman, one shortcut rules them all: Cmd+K. Cmd+K brings up Superhuman Command, where you can instantly do any action”

   proof ↗⚑ flag

   Fastmail—none0/10

   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.

   ⚑ flag

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

   weight 3 · round to Fastmail
   Superhuman Mail~partialprobed6/10

   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.

   • [claimed-docs] “Superhuman Mail MCP connects your inbox and calendar into Claude, ChatGPT, and other AI assistants—so you can summarize threads, draft and s…”
   • [claimed-docs] “You can now drive Superhuman Mail from Claude, ChatGPT, and your favorite AI tools. You can create powerful workflows that run across your i…”
   • [claimed-docs] “Every send action requires your explicit approval, so you stay in control.”
   • [claimed-docs] “Every draft matches your voice and tone, using your unique style for each person. You can review the drafts in Superhuman Mail, or edit and …”
   • [probe] “PROBE llms.txt: HTTP 404 at https://superhuman.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://superhuman.com/openapi.json, https://superhuman.com/swagger.json, https://superhuman.com/api…”
   • [probe] “official MCP server documented at https://superhuman.com/mail/features/email-mcp”

   proof ↗⚑ flag

   Fastmail✓fullclaimed8/10

   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.

   • [claimed-docs] “Fetch `/.well-known/jmap` for the session object - capabilities, accounts, and all API URLs.”
   • [claimed-docs] “Standard OAuth 2.0 or Bearer tokens. No custom auth protocol to implement. Works with what you already have.”
   • [claimed-docs] “Get instant push via EventSource — one connection, all mailboxes. Or use WebPush for mobile-compatible push, no permanent connection require…”
   • [claimed-docs] “Sync changes more easily, more efficiently, and much, much faster. A single HTTP roundtrip is often all that's required.”
   • [claimed-docs] “API tokens”
   • [claimed-docs] “POST a `methodCalls` array. Query, fetch, and send, all in one HTTP request.”
   • [claimed-docs] “API Documentation”
   • [claimed-docs] “Standard OAuth 2.0 or Bearer tokens. No custom auth protocol to implement.”

   proof ↗⚑ flag

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

   weight 2 · round to Fastmail
   Superhuman Mail—none0/10

   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.

   • [claimed-docs] “Every send action requires your explicit approval, so you stay in control.”
   • [claimed-docs] “Admins govern who can build agents and control connector permissions across the entire org from one place.”
   • [probe] “PROBE llms.txt: HTTP 404 at https://superhuman.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://superhuman.com/openapi.json, https://superhuman.com/swagger.json, https://superhuman.com/api…”

   proof ↗⚑ flag

   Fastmail~partialcommunity6/10

   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.

   • [claimed-docs] “API tokens”
   • [claimed-docs] “API tokens – Fastmail”
   • [claimed-docs] “Standard OAuth 2.0 or Bearer tokens. No custom auth protocol to implement. Works with what you already have.”
   • [claimed-docs] “Standard OAuth 2.0 or Bearer tokens. No custom auth protocol to implement.”
   • [community] “I just use SMTP for this (with FastMail). FastMail is not really intended for [transactional emails at scale] as the limits and the like don…”

   proof ↗⚑ flag

8. ai-native userBuild against official SDKs

   weight 2 · round drawn
   Superhuman Mail—none0/10

   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.

   • [probe] “PROBE llms.txt: HTTP 404 at https://superhuman.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://superhuman.com/openapi.json, https://superhuman.com/swagger.json, https://superhuman.com/api…”
   • [claimed-docs] “Superhuman Mail MCP connects your inbox and calendar into Claude, ChatGPT, and other AI assistants—so you can summarize threads, draft and s…”
   • [claimed-docs] “You can now drive Superhuman Mail from Claude, ChatGPT, and your favorite AI tools. You can create powerful workflows that run across your i…”

   proof ↗⚑ flag

   Fastmail—none0/10

   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.

   • [claimed-docs] “API Documentation”
   • [claimed-docs] “API tokens”
   • [probe] “PROBE llms.txt: HTTP 404 at https://www.fastmail.help/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.fastmail.help/openapi.json, https://www.fastmail.help/swagger.json, https://www.fastmail…”

   proof ↗⚑ flag

9. ai-native userSubscribe to events via webhooks

   weight 2 · round to Fastmail
   Superhuman Mail—none0/10

   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.

   • [probe] “PROBE llms.txt: HTTP 404 at https://superhuman.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://superhuman.com/openapi.json, https://superhuman.com/swagger.json, https://superhuman.com/api…”
   • [claimed-docs] “Superhuman Mail MCP connects your inbox and calendar into Claude, ChatGPT, and other AI assistants—so you can summarize threads, draft and s…”

   proof ↗⚑ flag

   Fastmail~partialclaimed5/10

   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.

   • [claimed-docs] “Get instant push via EventSource — one connection, all mailboxes. Or use WebPush for mobile-compatible push, no permanent connection require…”
   • [claimed-docs] “Get instant push via EventSource — one connection, all mailboxes.”
   • [claimed-docs] “POST a `methodCalls` array. Query, fetch, and send, all in one HTTP request.”
   • [claimed-docs] “API Documentation”

   proof ↗⚑ flag

Agentic features

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

   weight 2 · round to Superhuman Mail
   Superhuman Mail✓fullclaimed9/10

   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).

   • [claimed-docs] “You can now get rapid answers without having to remember senders, guess keywords, or comb through messages.”
   • [claimed-docs] “Just ask: _"where is the q2 offsite"_, _"when is my flight"_, _"where am I staying"_, and we'll immediately generate succinct answers.”
   • [claimed-docs] “Just ask: "where is the q2 offsite", "when is my flight", "where am I staying", and we'll immediately generate succinct answers.”
   • [claimed-docs] “Auto Drafts now gather context from your inbox, your calendar, and the web. They can use information from other emails, insert availability,…”
   • [claimed-docs] “Each draft can use your inbox, calendar, and the web to write replies that are ready to send.”
   • [claimed-docs] “Every message that needs a reply comes with a draft written in your voice. Each draft can use your inbox, calendar, and the web to write rep…”
   • [claimed-docs] “Superhuman AI will automatically separate marketing, cold pitches, and social network updates, so you can respond faster to what matters mos…”
   • [claimed-docs] “With Auto Labels, Superhuman Mail automatically classifies incoming messages — so you can focus on what matters most.”
   • [claimed-docs] “Get an email assistant that automatically labels incoming emails, archives low-priority messages, drafts replies, and reminds you to follow …”

   proof ↗⚑ flag

   Fastmail—none0/10

   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.

   ⚑ flag

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

   weight 2 · round to Superhuman Mail
   Superhuman Mail~partialclaimed6/10

   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.

   • [claimed-docs] “Use chat or our visual builder to create agents that run proactively based on triggers you set and the work you connect.”
   • [claimed-docs] “Admins govern who can build agents and control connector permissions across the entire org from one place.”
   • [claimed-docs] “Superhuman AI can automatically archive marketing, cold pitches, and social network updates. Turn on Auto Archive, and eliminate inbox clutt…”
   • [claimed-docs] “Auto Drafts now gather context from your inbox, your calendar, and the web. They can use information from other emails, insert availability,…”
   • [claimed-docs] “Every send action requires your explicit approval, so you stay in control.”

   proof ↗⚑ flag

   Fastmail~partialclaimed5/10

   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.

   • [claimed-docs] “Filters & Rules”
   • [claimed-docs] “Filters & Rules – Fastmail”
   • [claimed-docs] “Get instant push via EventSource — one connection, all mailboxes. Or use WebPush for mobile-compatible push, no permanent connection require…”
   • [claimed-docs] “Get instant push via EventSource — one connection, all mailboxes.”
   • [claimed-docs] “API tokens”
   • [claimed-docs] “API tokens – Fastmail”
   • [claimed-docs] “POST a `methodCalls` array. Query, fetch, and send, all in one HTTP request.”

   proof ↗⚑ flag

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

   weight 3 · round to Superhuman Mail
   Superhuman Mail✓fullclaimed8/10

   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. Missing 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).

   • [claimed-docs] “Every email that needs a reply comes with a draft—you can just edit and send.”
   • [claimed-docs] “If your email needs a response, you’re automatically reminded to follow up—with a draft already written and ready to send.”
   • [claimed-docs] “Handle every follow-up with one prompt. Superhuman Mail can check which emails have been read, draft all the nudges, and send when each reci…”
   • [claimed-docs] “Get an email assistant that automatically labels incoming emails, archives low-priority messages, drafts replies, and reminds you to follow …”
   • [claimed-docs] “Auto Drafts now gather context from your inbox, your calendar, and the web. They can use information from other emails, insert availability,…”
   • [claimed-docs] “Use chat or our visual builder to create agents that run proactively based on triggers you set and the work you connect.”
   • [claimed-docs] “Admins govern who can build agents and control connector permissions across the entire org from one place.”
   • [claimed-docs] “Every draft matches your voice and tone, using your unique style for each person. You can review the drafts in Superhuman Mail, or edit and …”

   proof ↗⚑ flag

   Fastmail—none0/10

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

   ⚑ flag

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

   weight 2 · round to Superhuman Mail
   Superhuman Mail✓fullprobed8/10

   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.

   • [claimed-docs] “Superhuman Mail MCP connects your inbox and calendar into Claude, ChatGPT, and other AI assistants—so you can summarize threads, draft and s…”
   • [claimed-docs] “Connect Claude or ChatGPT directly to your inbox to read, draft, and send emails with a single prompt — no copy-pasting required.”
   • [claimed-docs] “Just ask: _"where is the q2 offsite"_, _"when is my flight"_, _"where am I staying"_, and we'll immediately generate succinct answers.”
   • [claimed-docs] “Add plain-language instructions like "write in lowercase" or "use this booking link" to personalize your writing and scheduling features.”
   • [claimed-docs] “You can even make your own Auto Labels with short AI prompts like "job applications" or "requests to review work".”
   • [claimed-docs] “You can now drive Superhuman Mail from Claude, ChatGPT, and your favorite AI tools. You can create powerful workflows that run across your i…”
   • [claimed-docs] “Every send action requires your explicit approval, so you stay in control.”
   • [probe] “official MCP server documented at https://superhuman.com/mail/features/email-mcp”

   proof ↗⚑ flag

   Fastmail—none0/10

   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.

   • [probe] “PROBE llms.txt: HTTP 404 at https://www.fastmail.help/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.fastmail.help/openapi.json, https://www.fastmail.help/swagger.json, https://www.fastmail…”
   • [claimed-docs] “Keyboard shortcuts”

   proof ↗⚑ flag

Api quality

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

   weight 2 · round drawn
   Superhuman Mail—none0/10

   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.

   • [probe] “PROBE llms.txt: HTTP 404 at https://superhuman.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://superhuman.com/openapi.json, https://superhuman.com/swagger.json, https://superhuman.com/api…”
   • [probe] “official MCP server documented at https://superhuman.com/mail/features/email-mcp”

   proof ↗⚑ flag

   Fastmail—none0/10

   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.

   • [claimed-docs] “API Documentation”
   • [probe] “PROBE llms.txt: HTTP 404 at https://www.fastmail.help/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.fastmail.help/openapi.json, https://www.fastmail.help/swagger.json, https://www.fastmail…”

   proof ↗⚑ flag

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

   weight 2 · round to Fastmail
   Superhuman Mail—none0/10

   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.

   • [probe] “PROBE llms.txt: HTTP 404 at https://superhuman.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://superhuman.com/openapi.json, https://superhuman.com/swagger.json, https://superhuman.com/api…”

   proof ↗⚑ flag

   Fastmail~partialprobed4/10

   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.

   • [claimed-docs] “Fetch `/.well-known/jmap` for the session object - capabilities, accounts, and all API URLs.”
   • [claimed-docs] “API Documentation”
   • [probe] “PROBE llms.txt: HTTP 404 at https://www.fastmail.help/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.fastmail.help/openapi.json, https://www.fastmail.help/swagger.json, https://www.fastmail…”

   proof ↗⚑ flag

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

   weight 1 · round drawn
   Superhuman Mail—none0/10

   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.

   ⚑ flag

   Fastmail—none0/10

   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.

   ⚑ flag

4. ai-native userRely on versioned APIs with a documented deprecation policy

   weight 2 · round drawn
   Superhuman Mail—none0/10

   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.

   • [probe] “PROBE openapi: all candidate paths 404 (https://superhuman.com/openapi.json, https://superhuman.com/swagger.json, https://superhuman.com/api…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://superhuman.com/llms.txt”

   proof ↗⚑ flag

   Fastmail—none0/10

   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.

   • [claimed-docs] “Fetch `/.well-known/jmap` for the session object - capabilities, accounts, and all API URLs.”
   • [claimed-docs] “API Documentation”
   • [probe] “PROBE llms.txt: HTTP 404 at https://www.fastmail.help/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.fastmail.help/openapi.json, https://www.fastmail.help/swagger.json, https://www.fastmail…”

   proof ↗⚑ flag

Agent workflows

1. ai-native userAn external agent — Claude, ChatGPT, or my own — can read, triage, draft, and send my email end to end through a documented connection

   weight 2 · round to Superhuman Mail
   Superhuman Mail✓fullprobed8/10

   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.

   • [claimed-docs] “Superhuman Mail MCP connects your inbox and calendar into Claude, ChatGPT, and other AI assistants—so you can summarize threads, draft and s…”
   • [claimed-docs] “Connect Claude or ChatGPT directly to your inbox to read, draft, and send emails with a single prompt — no copy-pasting required.”
   • [claimed-docs] “Connect all your Gmail and Outlook accounts, including work, personal, and side projects. Manage every inbox and calendar from one AI assist…”
   • [claimed-docs] “You can now drive Superhuman Mail from Claude, ChatGPT, and your favorite AI tools. You can create powerful workflows that run across your i…”
   • [claimed-docs] “Every send action requires your explicit approval, so you stay in control.”
   • [claimed-docs] “Every draft matches your voice and tone, using your unique style for each person. You can review the drafts in Superhuman Mail, or edit and …”
   • [probe] “official MCP server documented at https://superhuman.com/mail/features/email-mcp”

   proof ↗⚑ flag

   Fastmail~partialprobed5/10

   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.

   • [claimed-docs] “Fetch `/.well-known/jmap` for the session object - capabilities, accounts, and all API URLs.”
   • [claimed-docs] “Standard OAuth 2.0 or Bearer tokens. No custom auth protocol to implement. Works with what you already have.”
   • [claimed-docs] “API tokens”
   • [claimed-docs] “POST a `methodCalls` array. Query, fetch, and send, all in one HTTP request.”
   • [claimed-docs] “Standard OAuth 2.0 or Bearer tokens. No custom auth protocol to implement.”
   • [probe] “PROBE llms.txt: HTTP 404 at https://www.fastmail.help/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.fastmail.help/openapi.json, https://www.fastmail.help/swagger.json, https://www.fastmail…”

   proof ↗⚑ flag

Ai assistant

1. ai-native userAsk an assistant questions across my whole inbox and calendar — who said what, what's outstanding — and get grounded answers

   weight 2 · round to Superhuman Mail
   Superhuman Mail✓fullclaimed8/10

   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.

   • [claimed-docs] “You can now get rapid answers without having to remember senders, guess keywords, or comb through messages.”
   • [claimed-docs] “Just ask: _"where is the q2 offsite"_, _"when is my flight"_, _"where am I staying"_, and we'll immediately generate succinct answers.”
   • [claimed-docs] “Just ask: "where is the q2 offsite", "when is my flight", "where am I staying", and we'll immediately generate succinct answers.”
   • [claimed-docs] “Superhuman Mail MCP connects your inbox and calendar into Claude, ChatGPT, and other AI assistants—so you can summarize threads, draft and s…”
   • [claimed-docs] “You can now drive Superhuman Mail from Claude, ChatGPT, and your favorite AI tools. You can create powerful workflows that run across your i…”
   • [claimed-docs] “Connect all your Gmail and Outlook accounts, including work, personal, and side projects. Manage every inbox and calendar from one AI assist…”

   proof ↗⚑ flag

   Fastmail—none0/10

   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.

   • [claimed-docs] “Fetch `/.well-known/jmap` for the session object - capabilities, accounts, and all API URLs.”
   • [claimed-docs] “API tokens”
   • [claimed-docs] “API Documentation”

   proof ↗⚑ flag

Ai drafting

1. ai-native userAI drafts replies in my own voice and tone — ready to review and send, not generic boilerplate

   weight 3 · round to Superhuman Mail
   Superhuman Mail✓fullclaimed9/10

   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.

   • [claimed-docs] “Just jot down some phrases, and we'll turn them into a full email. Best of all, the email sounds like you. Superhuman AI matches the voice a…”
   • [claimed-docs] “Every message that needs a reply comes with a draft written in your voice.”
   • [claimed-docs] “Every draft matches your voice and tone, using your unique style for each person.”
   • [claimed-docs] “Every draft matches your voice and tone, using your unique style for each person. You can review the drafts in Superhuman Mail, or edit and …”
   • [claimed-docs] “Auto Drafts now gather context from your inbox, your calendar, and the web. They can use information from other emails, insert availability,…”
   • [claimed-docs] “Each draft can use your inbox, calendar, and the web to write replies that are ready to send.”
   • [claimed-docs] “Every message that needs a reply comes with a draft written in your voice. Each draft can use your inbox, calendar, and the web to write rep…”
   • [claimed-docs] “Every send action requires your explicit approval, so you stay in control.”
   • [claimed-docs] “with Auto Drafts 2.0, every message that needs a reply comes with a draft. You can just edit and send.”

   proof ↗⚑ flag

   Fastmail—none0/10

   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.

   ⚑ flag

Ai triage

1. ai-native userAI triages my inbox for me — auto-labeling, categorizing, and surfacing what needs attention — with behavior I can steer and audit

   weight 3 · round to Superhuman Mail
   Superhuman Mail✓fullclaimed8/10

   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.

   • [claimed-docs] “Superhuman AI can automatically archive marketing, cold pitches, and social network updates. Turn on Auto Archive, and eliminate inbox clutt…”
   • [claimed-docs] “Superhuman AI will automatically separate marketing, cold pitches, and social network updates, so you can respond faster to what matters mos…”
   • [claimed-docs] “You can even make your own Auto Labels with short AI prompts like "job applications" or "requests to review work".”
   • [claimed-docs] “Turn on Auto Archive, and eliminate inbox clutter for good.”
   • [claimed-docs] “Auto Labels, Superhuman AI will automatically separate marketing, cold pitches, and social network updates, so you can respond faster to wha…”
   • [claimed-docs] “you can make your own Auto Labels with short AI prompts, and then split your inbox into tabs using these custom Auto Labels.”
   • [claimed-docs] “Get an email assistant that automatically labels incoming emails, archives low-priority messages, drafts replies, and reminds you to follow …”
   • [claimed-docs] “Emails are labeled the moment they arrive, so you can see what's important and what's not.”
   • [claimed-docs] “Custom Auto Labels let you categorize emails with your own AI prompts. (Available for our Business and Enterprise customers.)”
   • [claimed-docs] “Every send action requires your explicit approval, so you stay in control.”
   • [claimed-docs] “Admins govern who can build agents and control connector permissions across the entire org from one place.”

   proof ↗⚑ flag

   Fastmail—none0/10

   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.

   • [claimed-docs] “Filters & Rules”
   • [claimed-docs] “Filters & Rules – Fastmail”
   • [claimed-docs] “Searching your mail”

   proof ↗⚑ flag

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

   weight 2 · round to Superhuman Mail
   Superhuman Mail~partialclaimed6/10

   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.

   • [claimed-docs] “Handle every follow-up with one prompt. Superhuman Mail can check which emails have been read, draft all the nudges, and send when each reci…”
   • [claimed-docs] “Superhuman Mail can check which emails have been read, draft all the nudges, and send when each recipient is most likely to open it.”
   • [claimed-docs] “Turn on Auto Archive, and eliminate inbox clutter for good.”
   • [claimed-docs] “Superhuman AI can automatically archive marketing, cold pitches, and social network updates. Turn on Auto Archive, and eliminate inbox clutt…”
   • [claimed-docs] “You can even make your own Auto Labels with short AI prompts like "job applications" or "requests to review work".”
   • [claimed-docs] “You can now drive Superhuman Mail from Claude, ChatGPT, and your favorite AI tools. You can create powerful workflows that run across your i…”
   • [claimed-docs] “Use chat or our visual builder to create agents that run proactively based on triggers you set and the work you connect.”
   • [claimed-docs] “Superhuman Mail MCP connects your inbox and calendar into Claude, ChatGPT, and other AI assistants—so you can summarize threads, draft and s…”

   proof ↗⚑ flag

   Fastmail~partialclaimed5/10

   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.

   • [claimed-docs] “POST a `methodCalls` array. Query, fetch, and send, all in one HTTP request.”
   • [claimed-docs] “Filters & Rules”
   • [claimed-docs] “Sync changes more easily, more efficiently, and much, much faster. A single HTTP roundtrip is often all that's required.”

   proof ↗⚑ flag

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

   weight 3 · round to Superhuman Mail
   Superhuman Mail✓fullclaimed7/10

   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.

   • [claimed-docs] “Use chat or our visual builder to create agents that run proactively based on triggers you set and the work you connect.”
   • [claimed-docs] “Admins govern who can build agents and control connector permissions across the entire org from one place.”
   • [claimed-docs] “You can even make your own Auto Labels with short AI prompts like "job applications" or "requests to review work".”
   • [claimed-docs] “you can make your own Auto Labels with short AI prompts, and then split your inbox into tabs using these custom Auto Labels.”
   • [claimed-docs] “Custom Auto Labels let you categorize emails with your own AI prompts. (Available for our Business and Enterprise customers.)”
   • [claimed-docs] “Superhuman AI can automatically archive marketing, cold pitches, and social network updates. Turn on Auto Archive, and eliminate inbox clutt…”
   • [claimed-docs] “Turn on Auto Archive, and eliminate inbox clutter for good.”
   • [claimed-docs] “Get an email assistant that automatically labels incoming emails, archives low-priority messages, drafts replies, and reminds you to follow …”

   proof ↗⚑ flag

   Fastmail~partialcommunity5/10

   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.

   • [claimed-docs] “Filters & Rules”
   • [claimed-docs] “Filters & Rules – Fastmail”
   • [claimed-docs] “Get instant push via EventSource — one connection, all mailboxes. Or use WebPush for mobile-compatible push, no permanent connection require…”
   • [community] “Fastmail has an easy migration tool as well if you don't want to go the IMAP route. Now, migrating filters and rules over on the other hand.…”

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round to Superhuman Mail
   Superhuman Mail~partialclaimed5/10

   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.

   • [claimed-docs] “Use chat or our visual builder to create agents that run proactively based on triggers you set and the work you connect.”
   • [claimed-docs] “Admins govern who can build agents and control connector permissions across the entire org from one place.”
   • [claimed-docs] “You can now drive Superhuman Mail from Claude, ChatGPT, and your favorite AI tools. You can create powerful workflows that run across your i…”

   proof ↗⚑ flag

   Fastmail—none0/10

   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.

   • [claimed-docs] “Filters & Rules”
   • [claimed-docs] “Scheduled Send”
   • [claimed-docs] “Snooze messages to just when you need them. Whether it’s tickets to that stadium gig in September, or a bill due next Thursday, sometimes yo…”

   proof ↗⚑ flag

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

   weight 1 · round drawn
   Superhuman Mail—none0/10

   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.

   ⚑ flag

   Fastmail—none0/10

   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.

   • [claimed-docs] “Filters & Rules”
   • [claimed-docs] “Filters & Rules – Fastmail”

   proof ↗⚑ flag

Calendar

1. power-userSee my calendar, respond to invites, and create events without leaving the email client

   weight 2 · round to Fastmail
   Superhuman Mail~partialclaimed6/10

   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.

   • [claimed-docs] “Simply add teammates, click "Find Time", and instantly see when everyone is free.”
   • [claimed-docs] “You can add all your Gmail and Outlook account calendars, and easily toggle them on and off.”
   • [claimed-docs] “When any email mentions a date, Superhuman Mail will show your day in the right side panel — so you always have context.”
   • [claimed-docs] “Working across time zones? Add a secondary time zone, so scheduling between San Francisco and New York (or London and Tokyo) is effortless.”
   • [claimed-docs] “Add a secondary time zone, so scheduling between San Francisco and New York (or London and Tokyo) is effortless.”

   proof ↗⚑ flag

   Fastmail✓fullclaimed7/10

   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.

   • [claimed-docs] “Calendar events and invitations”
   • [claimed-docs] “Calendar events and invitations – Fastmail”
   • [claimed-docs] “JMAP is the open protocol that replaces IMAP (and CardDAV and CalDAV). It's faster, simpler, more powerful, and built for how email works to…”

   proof ↗⚑ flag

2. power-userShare my availability or insert bookable meeting times directly into an email

   weight 1 · round to Superhuman Mail
   Superhuman Mail✓fullclaimed7/10

   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.

   • [claimed-docs] “Auto Drafts now gather context from your inbox, your calendar, and the web. They can use information from other emails, insert availability,…”
   • [claimed-docs] “Simply add teammates, click "Find Time", and instantly see when everyone is free.”
   • [claimed-docs] “Add plain-language instructions like "write in lowercase" or "use this booking link" to personalize your writing and scheduling features.”
   • [claimed-docs] “Add plain-language instructions like "write in lowercase" or "use this booking link" to personalize your writing and schedul”
   • [claimed-docs] “Add plain-language instructions like "write in lowercase" or "use this booking link" to personalize your writing”

   proof ↗⚑ flag

   Fastmail—none0/10

   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.

   • [claimed-docs] “Calendar events and invitations”
   • [claimed-docs] “Calendar events and invitations – Fastmail”

   proof ↗⚑ flag

Sending

1. power-userSee whether and when recipients opened my email

   weight 1 · round to Superhuman Mail
   Superhuman Mail~partialcommunity6/10

   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.

   • [claimed-docs] “Handle every follow-up with one prompt. Superhuman Mail can check which emails have been read, draft all the nudges, and send when each reci…”
   • [claimed-docs] “Superhuman Mail can check which emails have been read, draft all the nudges, and send when each recipient is most likely to open it.”
   • [claimed-docs] “Team Read Statuses: Read statuses are now shared across your team, so anybody can follow up with full context.”
   • [claimed-docs] “Read statuses are now shared across your team, so anybody can follow up with full context.”
   • [community] “"Superhuman doesn't even let its own customers turn images off. So merely by using Superhuman, you are vulnerable to the exact same spying t…”

   proof ↗⚑ flag

   Fastmail—none0/10

   No evidence in the pack mentions read receipts, delivery/open tracking, or any similar feature in Fastmail's composing/sending tools or documentation.

   ⚑ flag

2. power-userSchedule an email to send later and undo a send within a grace window

   weight 2 · round to Fastmail
   Superhuman Mail—none0/10

   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.

   ⚑ flag

   Fastmail✓fullclaimed8/10

   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.

   • [claimed-docs] “Scheduled Send”
   • [claimed-docs] “Undo send”
   • [claimed-docs] “Scheduled Send – Fastmail”
   • [claimed-docs] “Undo send – Fastmail”

   proof ↗⚑ flag

Templates

1. power-userInsert saved snippets or templates — with variables and attachments — instead of retyping the same reply

   weight 2 · round to Superhuman Mail
   Superhuman Mail~partialclaimed5/10

   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.

   • [claimed-docs] “Insert commonly-used phrases, paragraphs, or whole emails with a simple keyboard shortcut.”
   • [claimed-docs] “You can also share Snippets with your team, so your team can move faster, with consistent, up-to-date, and high-performing messaging.”
   • [claimed-docs] “Snippets can now be shared across your team, so you can all work faster with current and consistent messaging.”
   • [claimed-docs] “With Snippets, you can automate typing and push past this limit. Insert commonly-used phrases, paragraphs, or whole emails with a simple key…”

   proof ↗⚑ flag

   Fastmail~partialclaimed4/10

   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.

   • [claimed-docs] “Templates”
   • [claimed-docs] “Templates – Fastmail”

   proof ↗⚑ flag

Offline

1. power-userRead, search, and write email offline, with changes syncing when I reconnect

   weight 2 · round to Fastmail
   Superhuman Mail~partialclaimed5/10

   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.

   • [claimed-docs] “Superhuman gives you a new way to work with Gmail. It works perfectly offline.”
   • [claimed-docs] “Superhuman gives you a new way to work with Gmail. It works perfectly offline. It works even when online, and your internet connection is te…”
   • [claimed-docs] “It works perfectly offline. It works even when online, and your internet connection is terrible.”

   proof ↗⚑ flag

   Fastmail~partialclaimed6/10

   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.

   • [claimed-docs] “Offline support”
   • [claimed-docs] “Offline support – Fastmail”
   • [claimed-docs] “If you're offline when a snoozed message is scheduled to return to your Inbox, you will not see the snoozed message reappear until you're ba…”
   • [claimed-docs] “Sync changes more easily, more efficiently, and much, much faster. A single HTTP roundtrip is often all that's required.”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   Superhuman Mail~partialprobed5/10

   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.

   • [claimed-docs] “Superhuman Mail MCP connects your inbox and calendar into Claude, ChatGPT, and other AI assistants—so you can summarize threads, draft and s…”
   • [claimed-docs] “Connect Claude or ChatGPT directly to your inbox to read, draft, and send emails with a single prompt — no copy-pasting required.”
   • [claimed-docs] “Connect all your Gmail and Outlook accounts, including work, personal, and side projects. Manage every inbox and calendar from one AI assist…”
   • [claimed-docs] “You can now drive Superhuman Mail from Claude, ChatGPT, and your favorite AI tools. You can create powerful workflows that run across your i…”
   • [claimed-docs] “Every send action requires your explicit approval, so you stay in control.”
   • [probe] “PROBE llms.txt: HTTP 404 at https://superhuman.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://superhuman.com/openapi.json, https://superhuman.com/swagger.json, https://superhuman.com/api…”
   • [probe] “official MCP server documented at https://superhuman.com/mail/features/email-mcp”

   proof ↗⚑ flag

   Fastmail~partialclaimed5/10

   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.

   • [claimed-docs] “Fetch `/.well-known/jmap` for the session object - capabilities, accounts, and all API URLs.”
   • [claimed-docs] “Sync changes more easily, more efficiently, and much, much faster. A single HTTP roundtrip is often all that's required.”
   • [claimed-docs] “POST a `methodCalls` array. Query, fetch, and send, all in one HTTP request.”
   • [claimed-docs] “API Documentation”
   • [claimed-docs] “Masked Email”
   • [claimed-docs] “Filters & Rules”
   • [claimed-docs] “Snooze messages to just when you need them. Whether it’s tickets to that stadium gig in September, or a bill due next Thursday, sometimes yo…”

   proof ↗⚑ flag

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

   weight 3 · round to Fastmail
   Superhuman Mail—none0/10

   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.

   ⚑ flag

   Fastmail~partialclaimed4/10

   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.

   • [claimed-docs] “JMAP is an open standard any organisation can implement, not more proprietary lock-in from big tech companies.”
   • [claimed-docs] “Open source and standards | Fastmail”
   • [claimed-docs] “Fetch `/.well-known/jmap` for the session object - capabilities, accounts, and all API URLs.”
   • [claimed-docs] “API Documentation”
   • [claimed-docs] “Import your mail”

   proof ↗⚑ flag

3. ai-native userRead the product's source under an open license

   weight 2 · round drawn
   Superhuman Mail—none0/10

   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.

   ⚑ flag

   Fastmail—none0/10

   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.

   • [claimed-docs] “Open source and standards | Fastmail”
   • [claimed-docs] “JMAP is an open standard any organisation can implement, not more proprietary lock-in from big tech companies.”

   proof ↗⚑ flag

4. ai-native userSelf-host the core product

   weight 3 · round drawn
   Superhuman Mail—none0/10

   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.

   ⚑ flag

   Fastmail—none0/10

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

   ⚑ flag

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

   weight 2 · round drawn
   Superhuman Mail—none0/10

   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.

   ⚑ flag

   Fastmail—none0/10

   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.

   ⚑ flag

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

   weight 3 · round drawn
   Superhuman Mail—none0/10

   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.

   ⚑ flag

   Fastmail—none0/10

   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.

   ⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round drawn
   Superhuman Mail—none0/10

   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.

   ⚑ flag

   Fastmail—none0/10

   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.

   ⚑ flag

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

   weight 2 · round drawn
   Superhuman Mail—none0/10

   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.

   ⚑ flag

   Fastmail—none0/10

   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.

   ⚑ flag

Protection

1. switcherUse aliases or masked addresses so sign-ups and strangers never learn my real address

   weight 1 · round to Fastmail
   Superhuman Mail—none0/10

   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.

   ⚑ flag

   Fastmail✓fullcommunity8/10

   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.

   • [claimed-docs] “Masked Email”
   • [claimed-docs] “Masked Email – Fastmail”
   • [claimed-docs] “How to set up aliases”
   • [claimed-docs] “How to set up aliases – Fastmail”
   • [community] “Fastmail is fantastic, I've been a very happy customer for at least a couple years now. Masked emails have been so nice for throwaway/sketch…”

   proof ↗⚑ flag

2. switcherThe client protects me from senders' tracking — blocking read pixels by default — and is transparent about what it does with my mail data

   weight 2 · round drawn
   Superhuman Mail—none0/10

   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.

   • [community] “"Superhuman doesn't even let its own customers turn images off. So merely by using Superhuman, you are vulnerable to the exact same spying t…”

   proof ↗⚑ flag

   Fastmail—none0/10

   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.

   ⚑ flag

Migration

1. switcherImport my complete mail history and contacts from my old provider or client

   weight 1 · round to Fastmail
   Superhuman Mail—none0/10

   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.

   ⚑ flag

   Fastmail~partialcommunity6/10

   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.

   • [claimed-docs] “Import your mail”
   • [claimed-docs] “Import your mail – Fastmail”
   • [community] “As an alternative to forwarding, you can also configure Fastmail to fetch mail from (and send via) Gmail like a mail client.”
   • [community] “Fastmail has an easy migration tool as well if you don't want to go the IMAP route. Now, migrating filters and rules over on the other hand.…”
   • [claimed-docs] “Move from Gmail”

   proof ↗⚑ flag

Search

1. power-userSearch is fast and precise — operators, filters, and ranked results across my full mail history

   weight 2 · round to Fastmail
   Superhuman Mail!disputedcontradicted4/10

   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.

   • [claimed-docs] “You can now get rapid answers without having to remember senders, guess keywords, or comb through messages.”
   • [claimed-docs] “Just ask: _"where is the q2 offsite"_, _"when is my flight"_, _"where am I staying"_, and we'll immediately generate succinct answers.”
   • [claimed-docs] “Just ask: "where is the q2 offsite", "when is my flight", "where am I staying", and we'll immediately generate succinct answers.”
   • [community] “"I am an ex-user. A search through my email archive would regularly take ten seconds while gmail would do it instantly... my experience was …”
   • [community] “"My experience is that search and UI transitions are blazing fast. It crashes (rarely, but more than I like) and requires a restart. But I l…”

   proof ↗⚑ flag

   Fastmail~partialclaimed3/10

   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.

   • [claimed-docs] “Searching your mail”
   • [claimed-docs] “Searching your mail – Fastmail”
   • [claimed-docs] “Sync changes more easily, more efficiently, and much, much faster. A single HTTP roundtrip is often all that's required.”
   • [claimed-docs] “POST a `methodCalls` array. Query, fetch, and send, all in one HTTP request.”

   proof ↗⚑ flag

Shortcuts

1. power-userDo everything from the keyboard — comprehensive shortcuts and a command palette — in an interface fast enough to never make me wait

   weight 3 · round to Fastmail
   Superhuman Mail!disputedcontradicted6/10

   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.

   • [claimed-docs] “Cmd+K brings up Superhuman Command, where you can instantly do any action — and also learn the shortcut for next time.”
   • [claimed-docs] “In Superhuman, one shortcut rules them all: Cmd+K. Cmd+K brings up Superhuman Command, where you can instantly do any action”
   • [claimed-docs] “You can reply to important messages faster with blazingly fast shortcuts and features like Instant Intro.”
   • [community] “"I am an ex-user. A search through my email archive would regularly take ten seconds while gmail would do it instantly... my experience was …”
   • [community] “"My experience is that search and UI transitions are blazing fast. It crashes (rarely, but more than I like) and requires a restart. But I l…”
   • [community] “"They essentially just teach you how to do things that gmail already lets you do, but put a cuter UI around it, and they force teach you con…”

   proof ↗⚑ flag

   Fastmail~partialcommunity5/10

   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.

   • [claimed-docs] “Keyboard shortcuts”
   • [claimed-docs] “Keyboard shortcuts – Fastmail”
   • [claimed-docs] “Sync changes more easily, more efficiently, and much, much faster. A single HTTP roundtrip is often all that's required.”
   • [community] “I switched from protonmail to fastmail recently. Fastmail was a ton faster and didn't randomly forget my sessions. Night and day to use. It …”
   • [community] “I recently moved my email to FastMail and I really like it. I even prefer its web interface over Gmail's.”

   proof ↗⚑ flag

Channels

1. team-leadThe same inbox also handles adjacent customer channels — SMS, WhatsApp, social, or live chat — beside email

   weight 1 · round drawn
   Superhuman Mail—none0/10

   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.

   ⚑ flag

   Fastmail—none0/10

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

   ⚑ flag

Routing

1. team-leadAssign conversations to teammates and route incoming mail with rules so ownership is explicit

   weight 2 · round to Superhuman Mail
   Superhuman Mail~partialclaimed4/10

   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.

   • [claimed-docs] “Team Read Statuses: Read statuses are now shared across your team, so anybody can follow up with full context.”
   • [claimed-docs] “Team Reply Indicators: See when your team is replying, so you can avoid double work and embarrassing collisions.”
   • [claimed-docs] “let you @mention teammates, share live email views, and coordinate responses without external recipients seeing internal discussions”
   • [claimed-docs] “Snippets can now be shared across your team, so you can all work faster with current and consistent messaging.”
   • [claimed-docs] “Read statuses are now shared across your team, so anybody can follow up with full context.”
   • [claimed-docs] “See when your team is replying, so you can avoid double work and embarrassing collisions.”

   proof ↗⚑ flag

   Fastmail~partialclaimed3/10

   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.

   • [claimed-docs] “Filters & Rules”
   • [claimed-docs] “Filters & Rules – Fastmail”

   proof ↗⚑ flag

Shared inbox

1. team-leadWe can discuss an email in an internal side-thread — comments and @mentions beside the message — instead of forwarding copies around

   weight 2 · round to Superhuman Mail
   Superhuman Mail✓fullclaimed8/10

   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.

   • [claimed-docs] “let you @mention teammates, share live email views, and coordinate responses without external recipients seeing internal discussions”
   • [claimed-docs] “Team Read Statuses: Read statuses are now shared across your team, so anybody can follow up with full context.”
   • [claimed-docs] “Team Reply Indicators: See when your team is replying, so you can avoid double work and embarrassing collisions.”
   • [claimed-docs] “Read statuses are now shared across your team, so anybody can follow up with full context.”
   • [claimed-docs] “See when your team is replying, so you can avoid double work and embarrassing collisions.”

   proof ↗⚑ flag

   Fastmail—none0/10

   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.

   ⚑ flag

2. team-leadMy team works shared inboxes together — shared accounts or team channels where everyone sees the same conversation state

   weight 3 · round to Superhuman Mail
   Superhuman Mail~partialclaimed6/10

   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.

   • [claimed-docs] “Team Read Statuses: Read statuses are now shared across your team, so anybody can follow up with full context.”
   • [claimed-docs] “Team Reply Indicators: See when your team is replying, so you can avoid double work and embarrassing collisions.”
   • [claimed-docs] “Team Scheduling: See when your team is free, so you can schedule at the speed of thought.”
   • [claimed-docs] “let you @mention teammates, share live email views, and coordinate responses without external recipients seeing internal discussions”
   • [claimed-docs] “Snippets can now be shared across your team, so you can all work faster with current and consistent messaging.”
   • [claimed-docs] “Read statuses are now shared across your team, so anybody can follow up with full context.”
   • [claimed-docs] “See when your team is replying, so you can avoid double work and embarrassing collisions.”
   • [claimed-docs] “See when your team is free, so you can schedule at the speed of thought.”

   proof ↗⚑ flag

   Fastmail—none0/10

   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.

   • [claimed-docs] “Logging in to multiple accounts”
   • [claimed-docs] “Logging in to multiple accounts – Fastmail”

   proof ↗⚑ flag

Followups

1. power-userSnooze conversations and set follow-up reminders that resurface a thread if nobody replies

   weight 2 · round to Superhuman Mail
   Superhuman Mail~partialclaimed6/10

   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.

   • [claimed-docs] “If your email needs a response, you’re automatically reminded to follow up—with a draft already written and ready to send.”
   • [claimed-docs] “If your email needs a response, you're automatically reminded to follow up—with a draft already written and ready to send.”
   • [claimed-docs] “Handle every follow-up with one prompt. Superhuman Mail can check which emails have been read, draft all the nudges, and send when each reci…”
   • [claimed-docs] “Superhuman Mail can check which emails have been read, draft all the nudges, and send when each recipient is most likely to open it.”
   • [claimed-docs] “Get an email assistant that automatically labels incoming emails, archives low-priority messages, drafts replies, and reminds you to follow …”
   • [claimed-docs] “works inside Gmail and Outlook to label, declutter, draft, and remind automatically”

   proof ↗⚑ flag

   Fastmail~partialclaimed5/10

   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.

   • [claimed-docs] “Snooze messages to just when you need them. Whether it’s tickets to that stadium gig in September, or a bill due next Thursday, sometimes yo…”
   • [claimed-docs] “If you're offline when a snoozed message is scheduled to return to your Inbox, you will not see the snoozed message reappear until you're ba…”

   proof ↗⚑ flag

Inbox structure

1. power-userSelect many conversations at once and archive, label, or mark them done in one stroke

   weight 1 · round drawn
   Superhuman Mail~partialclaimed3/10

   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).

   • [claimed-docs] “Turn on Auto Archive, and eliminate inbox clutter for good.”
   • [claimed-docs] “you can focus on a specific topic — and get through emails of the same type, at the same time.”
   • [claimed-docs] “Get an email assistant that automatically labels incoming emails, archives low-priority messages, drafts replies, and reminds you to follow …”
   • [claimed-docs] “In Superhuman, one shortcut rules them all: Cmd+K. Cmd+K brings up Superhuman Command, where you can instantly do any action”
   • [claimed-docs] “splitting your inbox allows you to divide your inbox into different areas of focus — based on the types of email you receive mos”

   proof ↗⚑ flag

   Fastmail~partialclaimed3/10

   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.

   • [claimed-docs] “Keyboard shortcuts”
   • [claimed-docs] “Keyboard shortcuts – Fastmail”
   • [claimed-docs] “Filters & Rules”
   • [claimed-docs] “Filters & Rules – Fastmail”

   proof ↗⚑ flag

2. power-userSplit my inbox into focused streams — important, team, newsletters, calendar invites — so triage happens in priority order, not arrival order

   weight 3 · round to Superhuman Mail
   Superhuman Mail✓fullclaimed8/10

   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.

   • [claimed-docs] “in Superhuman Mail, you can design your own categories: like "VIP", "Notifications", "Calendar", or "Team".”
   • [claimed-docs] “you can design your own categories: like "VIP", "Notifications", "Calendar", or "Team".”
   • [claimed-docs] “splitting your inbox allows you to divide your inbox into different areas of focus — based on the types of email you receive mos”
   • [claimed-docs] “splitting your inbox allows you to divide your inbox into different areas of focus — based on the types of email you receive most”
   • [claimed-docs] “you can make your own Auto Labels with short AI prompts, and then split your inbox into tabs using these custom Auto Labels.”
   • [claimed-docs] “you can make your own Auto Labels with short AI prompts, and then split your inbox into tabs using these custom Auto Labels”
   • [claimed-docs] “you can focus on a specific topic — and get through emails of the same type, at the same time.”
   • [claimed-docs] “Custom Auto Labels let you categorize emails with your own AI prompts. (Available for our Business and Enterprise customers.)”

   proof ↗⚑ flag

   Fastmail~partialclaimed5/10

   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.

   • [claimed-docs] “Filters & Rules”
   • [claimed-docs] “Filters & Rules – Fastmail”
   • [claimed-docs] “Searching your mail”
   • [claimed-docs] “Searching your mail – Fastmail”
   • [claimed-docs] “Calendar events and invitations”
   • [claimed-docs] “Calendar events and invitations – Fastmail”

   proof ↗⚑ flag