Fastmail vs AgentMail

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
   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

   AgentMail~partialclaimed6/10

   AgentMail documents IMAP/SMTP compatibility, letting any standard mail client (Outlook, Thunderbird, Apple Mail) connect to an AgentMail inbox, which supports the open-protocol reachability part of the story. However, there is no mention of JMAP support or of a standards-based export/data-portability mechanism for migrating mail elsewhere. Missing for 10: JMAP protocol support, documented mailbox/data export or migration tooling, and independent confirmation that IMAP/SMTP access works reliably in practice.

   • [claimed-docs] “Connect Outlook, Thunderbird, Apple Mail, or any IMAP/SMTP-compatible client to your AgentMail inbox”

   proof ↗⚑ flag

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

   weight 1 · round drawn
   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

   AgentMail—none0/10

   AgentMail is documented as a hosted email API/service (custom domains, hosted MCP server, webhooks) with no mention anywhere of a self-hosted deployment option; a competitor's marketing even highlights itself as the 'self-hosted drop-in replacement' for AgentMail, implying AgentMail itself is cloud-only.

   • [claimed-docs] “using your own custom domains is essential for production applications. It gives you control over your sending reputation, which is the sing…”
   • [claimed-docs] “AgentMail runs a hosted MCP server at https://mcp.agentmail.to/mcp that exposes inbox, message, thread, draft, and attachment tools to any c…”
   • [community] “agentmail charges $20/mo for 10 inboxes. autopilot gives you unlimited inboxes for the cost of a postgres row, positioning itself as a self-…”

   proof ↗⚑ flag

Agent access

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

   weight 2 · round to AgentMail
   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

   AgentMail✓fullprobed9/10

   AgentMail hosts a live llms.txt file (verified HTTP 200) with a clear agent-oriented summary of its docs, and its entire documentation set is written in agent-consumable .md format (e.g., quickstart.md, messages.md) alongside an OpenAPI spec, MCP server, and CLI docs, making it easy for an agent to be pointed at and consume its docs. Missing for 10: no independent/community confirmation of an agent successfully navigating llms.txt end-to-end.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.agentmail.to/llms.txt # AgentMail | Documentation > AgentMail is an email API built for AI agents.…”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.agentmail.to/openapi.json — contains "openapi" key”
   • [claimed-docs] “The agent registers itself using the human email you provide and gets back an API key, inbox ID, and organization ID.”
   • [probe] “official MCP server documented at https://docs.agentmail.to/integrations/mcp”

   proof ↗⚑ flag

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

   weight 2 · round to AgentMail
   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

   AgentMail✓fullprobed7/10

   AgentMail is fundamentally API/SDK-driven ('Create, manage, and operate email inboxes entirely via API'), with a documented OpenAPI spec, official CLI, and webhook/websocket event delivery that support scripted, non-interactive automation pipelines. No explicit CI/CD example or pipeline walkthrough is given, so full CI-specific validation is inferred rather than directly documented. Missing for 10: an explicit CI/CD pipeline example or GitHub Actions integration, and independent confirmation of headless use in production automation.

   • [claimed-docs] “Create, manage, and operate email inboxes entirely via API.”
   • [claimed-docs] “Create inboxes, send messages, manage threads, and more — all without writing code.”
   • [claimed-docs] “Instead of constantly asking the AgentMail API if there's a new email (a process called polling), you can register a URL, and we will send y…”
   • [claimed-docs] “you can register a URL, and we will send you a `POST` request with the details as soon as an event happens.”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.agentmail.to/openapi.json — contains "openapi" key”
   • [probe] “official CLI documented at https://docs.agentmail.to/integrations/cli”

   proof ↗⚑ flag

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

   weight 3 · round to AgentMail
   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

   AgentMail✓fullprobed8/10

   AgentMail is a service/API product (not itself an agent), so the MCP-server axis applies, and docs confirm a hosted official MCP server at https://mcp.agentmail.to/mcp exposing inbox, message, thread, draft, and attachment tools to any compatible client, corroborated by a probe hit. Missing for 10: independent/hands-on confirmation that the MCP server works reliably in practice beyond first-party docs.

   • [claimed-docs] “AgentMail runs a hosted MCP server at https://mcp.agentmail.to/mcp that exposes inbox, message, thread, draft, and attachment tools to any c…”
   • [claimed-docs] “AgentMail runs a hosted MCP server at `https://mcp.agentmail.to/mcp` that exposes inbox, message, thread, draft, and attachment tools to any…”
   • [probe] “official MCP server documented at https://docs.agentmail.to/integrations/mcp”

   proof ↗⚑ flag

4. ai-native userUse an official CLI

   weight 2 · round to AgentMail
   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

   AgentMail✓fullprobed7/10

   AgentMail documents an official CLI (docs.agentmail.to/integrations/cli) that lets users create inboxes, send messages, and manage threads without writing code, corroborated by a probe confirming the page exists. Missing for 10: no independent/community hands-on confirmation of CLI usage or installation details beyond the docs themselves.

   • [claimed-docs] “Create inboxes, send messages, manage threads, and more — all without writing code.”
   • [probe] “official CLI documented at https://docs.agentmail.to/integrations/cli”

   proof ↗⚑ flag

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

   weight 3 · round to AgentMail
   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

   AgentMail✓fullprobed9/10

   AgentMail is explicitly an API-first product: docs describe registering agents via API, creating inboxes, sending/searching messages, webhooks, permissions, etc., and a live OpenAPI spec is confirmed at docs.agentmail.to/openapi.json. This gives strong first-party and probe-verified evidence of a documented, comprehensive public API. Missing for 10: independent third-party hands-on validation of the API itself (community feedback focuses on website/pricing, not API usage).

   • [claimed-docs] “The agent registers itself using the human email you provide and gets back an API key, inbox ID, and organization ID.”
   • [claimed-docs] “Create, manage, and operate email inboxes entirely via API.”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.agentmail.to/openapi.json — contains "openapi" key”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.agentmail.to/llms.txt # AgentMail | Documentation > AgentMail is an email API built for AI agents.…”
   • [claimed-docs] “Instead of constantly asking the AgentMail API if there's a new email (a process called polling), you can register a URL, and we will send y…”

   proof ↗⚑ flag

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

   weight 2 · round to AgentMail
   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

   AgentMail✓fullclaimed8/10

   Docs explicitly describe scoped API keys restricted to a single pod or inbox, per-customer pods with scoped keys for multi-tenancy, and a dedicated Permissions feature to restrict what an API key can do — directly matching the least-privilege credential story. Missing for 10: independent/hands-on verification that scoping actually enforces restrictions in practice, and detail on granularity of permission types beyond pod/inbox scope.

   • [claimed-docs] “create a Pod per customer, give them a scoped API key, and route webhook events to the right place.”
   • [claimed-docs] “Scoped API keys restrict access to a single pod or a single inbox.”
   • [claimed-docs] “`Permissions` let you restrict what an API key can do.”
   • [claimed-docs] “Create one pod per customer/tenant in your system”

   proof ↗⚑ flag

7. ai-native userBuild against official SDKs

   weight 2 · round to AgentMail
   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

   AgentMail✓fullprobed8/10

   AgentMail is fundamentally an API-first product with dedicated docs, OpenAPI spec, quickstart showing API key/SDK registration, and popovers showing SDK examples praised by a community reviewer, confirming real SDK-based building. Missing for 10: explicit list of language-specific SDKs (e.g. Python/TS/Go) and independent third-party developer testimonials beyond the dashboard praise.

   • [claimed-docs] “The agent registers itself using the human email you provide and gets back an API key, inbox ID, and organization ID.”
   • [claimed-docs] “Create, manage, and operate email inboxes entirely via API.”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.agentmail.to/openapi.json — contains "openapi" key”
   • [community] “What I am most impressed by is the popovers in your dashboard, which show SDK examples. This is a brilliant UI idea (executed with great pol…”

   proof ↗⚑ flag

8. ai-native userSubscribe to events via webhooks

   weight 2 · round to AgentMail
   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

   AgentMail✓fullclaimed9/10

   AgentMail's docs explicitly support webhook subscriptions: registering a URL to receive POST requests on email events instead of polling, avoiding the need for constant API checks. This is a first-party documented, core feature directly matching the story. Missing for 10: independent/hands-on confirmation that webhooks work reliably in practice.

   • [claimed-docs] “Instead of constantly asking the AgentMail API if there's a new email (a process called polling), you can register a URL, and we will send y…”
   • [claimed-docs] “you can register a URL, and we will send you a `POST` request with the details as soon as an event happens.”

   proof ↗⚑ flag

Agentic features

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

   weight 2 · round drawn
   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

   AgentMail~partialclaimed5/10

   AgentMail provides the building blocks for background automation—webhooks and persistent WebSocket connections that push email events in real time instead of requiring polling—so an agent can react autonomously to inbound mail without a human in the loop. However, AgentMail itself is just email infrastructure; there's no evidence of a built-in scheduler, workflow engine, or persistent agent runtime that executes autonomous logic—that has to be built by the user on top of the webhook/websocket feed. Missing for 10: evidence of a native scheduling/automation engine, documented autonomous background job execution, or independent confirmation that these mechanisms reliably drive unattended agent workflows.

   • [claimed-docs] “Instead of constantly asking the AgentMail API if there's a new email (a process called polling), you can register a URL, and we will send y…”
   • [claimed-docs] “you can register a URL, and we will send you a `POST` request with the details as soon as an event happens.”
   • [claimed-docs] “WebSockets provide a persistent, bidirectional connection to AgentMail for receiving email events in real-time.”
   • [claimed-docs] “WebSockets don't require a public URL or external tools like ngrok.”

   proof ↗⚑ flag

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

   weight 2 · round to AgentMail
   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

   AgentMail~partialprobed6/10

   AgentMail exposes a hosted MCP server with inbox/message/thread/draft tools that lets any MCP-compatible AI agent operate the product via natural language, and also ships a CLI for no-code operations. However, there's no first-party chat/NL interface of its own, nor independent evidence of successful natural-language operation in practice. Missing for 10: hands-on demonstration of natural-language command execution, a dedicated conversational UI beyond MCP tool-calling.

   • [claimed-docs] “AgentMail runs a hosted MCP server at https://mcp.agentmail.to/mcp that exposes inbox, message, thread, draft, and attachment tools to any c…”
   • [claimed-docs] “AgentMail runs a hosted MCP server at `https://mcp.agentmail.to/mcp` that exposes inbox, message, thread, draft, and attachment tools to any…”
   • [claimed-docs] “Create inboxes, send messages, manage threads, and more — all without writing code.”
   • [probe] “official MCP server documented at https://docs.agentmail.to/integrations/mcp”
   • [probe] “official CLI documented at https://docs.agentmail.to/integrations/cli”

   proof ↗⚑ flag

Api quality

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

   weight 2 · round to AgentMail
   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

   AgentMail~partialprobed5/10

   AgentMail exposes a machine-readable OpenAPI spec (agentmail-probe-2) and its docs site includes language-switchable code snippets (Python/curl) plus SDK example popovers praised by users (agentmail-comm-2, agentmail-comm-7), suggesting an interactive reference. However, there is no evidence of a true 'try it now' runnable/executable API console, and independent reports note the docs site itself is slow and glitchy (agentmail-comm-1, agentmail-comm-3), undermining a smooth interactive experience. Missing for 10: confirmation of an actual runnable/sandboxed request execution feature, and resolution of the reported performance/UX issues on the docs site.

   • [probe] “PROBE openapi: HTTP 200 at https://docs.agentmail.to/openapi.json — contains "openapi" key”
   • [community] “The website is really bad. Moving from Python to curl tab on the site shows noticeable lag - I have seen 2-3 whole websites load faster in t…”
   • [community] “What I am most impressed by is the popovers in your dashboard, which show SDK examples. This is a brilliant UI idea (executed with great pol…”
   • [community] “"Application error: a client-side exception has occurred while loading www.agentmail.to"... Failed to create WebGL context... Cookie rejecte…”
   • [community] “I have written about how slow the website is... the amount of lag is something I have genuinely never witnessed in any website... I can't vi…”

   proof ↗⚑ flag

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

   weight 2 · round to AgentMail
   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

   AgentMail✓fullprobed9/10

   A probe confirms the OpenAPI spec is live and machine-readable at https://docs.agentmail.to/openapi.json (HTTP 200, contains "openapi" key), backed by documented API-first design. Missing for 10: no independent third-party corroboration of spec completeness or SDK auto-generation from it.

   • [probe] “PROBE openapi: HTTP 200 at https://docs.agentmail.to/openapi.json — contains "openapi" key”
   • [claimed-docs] “Create, manage, and operate email inboxes entirely via API.”

   proof ↗⚑ flag

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

   weight 1 · round drawn
   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

   AgentMail—none0/10

   No evidence of a dedicated sandbox/test environment separate from production; the docs describe creating inboxes on-demand, but nothing indicates an isolated test mode that avoids touching real production data or sending real emails.

   ⚑ flag

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

   weight 2 · round drawn
   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

   AgentMail—none0/10

   Evidence shows an OpenAPI spec and general API docs, but there is no mention anywhere of API versioning scheme or a documented deprecation policy for endpoints.

   ⚑ 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 AgentMail
   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

   AgentMail✓fullprobed8/10

   AgentMail documents a hosted MCP server exposing inbox, message, thread, draft, and attachment tools, plus a full API/CLI for creating inboxes, reading/searching threads, drafting (with human-in-the-loop review), and sending messages with attachments — enabling any MCP-compatible agent (Claude, ChatGPT, custom) to triage and send email end to end. missing for 10: independent hands-on verification of an external agent completing a full read-triage-send workflow via the MCP connection (only vendor docs and probes confirm the endpoint, no third-party usage report).

   • [claimed-docs] “AgentMail runs a hosted MCP server at https://mcp.agentmail.to/mcp that exposes inbox, message, thread, draft, and attachment tools to any c…”
   • [claimed-docs] “AgentMail runs a hosted MCP server at `https://mcp.agentmail.to/mcp` that exposes inbox, message, thread, draft, and attachment tools to any…”
   • [probe] “official MCP server documented at https://docs.agentmail.to/integrations/mcp”
   • [claimed-docs] “Human-in-the-Loop Review: An agent can create a `Draft` for a sensitive or important `Message`, which a human can then review and approve be…”
   • [claimed-docs] “To start a new conversation, you can send a Message from one of your inboxes.”
   • [claimed-docs] “Full-text search finds Threads by keyword across the sender, recipients, subject, and message body, ranked by relevance.”
   • [claimed-docs] “Your agents can both send `Attachments` in outgoing `Messages` and process `Attachments` from incoming `Messages`.”
   • [claimed-docs] “You can cc or bcc a real person on any message your agent sends, creating a "human-in-the-loop" workflow for oversight, escalations, or qual…”

   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 drawn
   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

   AgentMail—none0/10

   AgentMail is developer infrastructure (an email API/MCP server) for building agent-driven email workflows, not an end-user assistant that answers grounded questions across inbox and calendar. Evidence shows full-text search across threads and MCP tool exposure (docs-5, docs-12), but there is no calendar integration anywhere in the evidence, and no shipped assistant/chat interface that synthesizes 'who said what' or 'what's outstanding' answers for a user.

   • [claimed-docs] “Full-text search finds Threads by keyword across the sender, recipients, subject, and message body, ranked by relevance.”
   • [claimed-docs] “AgentMail runs a hosted MCP server at https://mcp.agentmail.to/mcp that exposes inbox, message, thread, draft, and attachment tools to any c…”
   • [claimed-docs] “Create, manage, and operate email inboxes entirely via API.”

   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 drawn
   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

   AgentMail—none0/10

   AgentMail provides Draft objects and human-in-the-loop review (an agent can create a Draft for a human to approve before sending), but there is no evidence that AgentMail itself learns or applies the user's personal voice/tone when generating drafts — it is an email infrastructure/API for agents, not a personalization/writing-style engine.

   • [claimed-docs] “Human-in-the-Loop Review: An agent can create a `Draft` for a sensitive or important `Message`, which a human can then review and approve be…”
   • [claimed-docs] “You can cc or bcc a real person on any message your agent sends, creating a "human-in-the-loop" workflow for oversight, escalations, or qual…”

   proof ↗⚑ 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 drawn
   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

   AgentMail—none0/10

   AgentMail provides developer primitives (Labels, Lists, full-text search, webhooks) that a developer could use to build inbox triage, but there is no evidence of AgentMail itself performing AI-driven auto-labeling, categorization, or surfacing-what-needs-attention out of the box — Labels are described as manually tracked conversation states, not an automated triage engine, and no docs describe a built-in AI classifier or steerable/auditable triage policy.

   • [claimed-docs] “Use `Labels` to track the state of a conversation.”
   • [claimed-docs] “`Lists` allow you to filter emails by allowing or blocking specific email addresses or domains.”
   • [claimed-docs] “Full-text search finds Threads by keyword across the sender, recipients, subject, and message body, ranked by relevance.”
   • [claimed-docs] “Instead of constantly asking the AgentMail API if there's a new email (a process called polling), you can register a URL, and we will send y…”

   proof ↗⚑ flag

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

   weight 2 · round to Fastmail
   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

   AgentMail~partialclaimed4/10

   Docs confirm the platform is fully API-driven and explicitly supports creating 'tens, hundreds, or even thousands' of inboxes on demand, implying agents can script bulk creation, but there's no documented dedicated bulk/batch endpoint for messages, threads, or other items (e.g., bulk send, bulk label, bulk delete). Missing for 10: dedicated batch/bulk API endpoints for messages/threads, documented rate-limit or batching guidance, hands-on evidence of bulk operations at scale.

   • [claimed-docs] “You can create tens, hundreds, or even thousands of Inboxes for your agents on demand.”
   • [claimed-docs] “Create, manage, and operate email inboxes entirely via API.”
   • [claimed-docs] “Create inboxes, send messages, manage threads, and more — all without writing code.”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   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

   AgentMail~partialclaimed5/10

   AgentMail exposes event-driven infrastructure (webhooks and websockets) so external code can react to inbox events, and Lists provide simple automatic allow/block rules on senders/domains, but there's no built-in rule engine for defining conditional 'if X then do Y' automations inside the product itself — the actual rule logic must be implemented by the developer/agent consuming the webhook. missing for 10: a native rules/automation engine (e.g. conditional triggers on subject/content beyond allow-block lists), and independent confirmation that webhook-driven automation works reliably in production.

   • [claimed-docs] “Instead of constantly asking the AgentMail API if there's a new email (a process called polling), you can register a URL, and we will send y…”
   • [claimed-docs] “you can register a URL, and we will send you a `POST` request with the details as soon as an event happens.”
   • [claimed-docs] “WebSockets provide a persistent, bidirectional connection to AgentMail for receiving email events in real-time.”
   • [claimed-docs] “`Lists` allow you to filter emails by allowing or blocking specific email addresses or domains.”
   • [claimed-docs] “Use `Labels` to track the state of a conversation.”

   proof ↗⚑ flag

Sending

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

   weight 1 · round drawn
   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

   AgentMail—none0/10

   No evidence anywhere in the pack mentions read receipts, open tracking, or delivery/open status for sent messages; AgentMail's docs cover inboxes, threads, webhooks, drafts, labels, etc., but nothing about tracking whether a recipient opened an email.

   ⚑ flag

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

   weight 2 · round to Fastmail
   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

   AgentMail—none0/10

   No evidence anywhere in the pack of scheduled sending or an undo-send grace window; AgentMail's documented features cover inboxes, messages, drafts, threads, webhooks, and human-in-the-loop review, but nothing about delayed/scheduled send or send-cancellation.

   ⚑ flag

Templates

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

   weight 2 · round to Fastmail
   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

   AgentMail—none0/10

   AgentMail is an API/infrastructure product for agent-driven email (inboxes, messages, drafts, attachments, webhooks) with no evidence of a saved snippets/templates library or variable-substitution feature for composing replies; nothing in the docs mentions reusable templates or canned responses.

   ⚑ flag

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

   weight 2 · round to AgentMail
   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

   AgentMail✓fullprobed8/10

   AgentMail is explicitly API-first ('Create, manage, and operate email inboxes entirely via API'), with a documented OpenAPI spec, CLI, and MCP server all built atop the same API surface (inboxes, messages, threads, drafts, webhooks, attachments, permissions, pods) — no UI-exclusive features are mentioned anywhere in the docs. missing for 10: an explicit statement or independent test confirming 1:1 parity between the dashboard UI and API (e.g., that every dashboard action maps to a documented endpoint).

   • [claimed-docs] “Create, manage, and operate email inboxes entirely via API.”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.agentmail.to/openapi.json — contains "openapi" key”
   • [claimed-docs] “Create inboxes, send messages, manage threads, and more — all without writing code.”
   • [probe] “official CLI documented at https://docs.agentmail.to/integrations/cli”
   • [claimed-docs] “create a Pod per customer, give them a scoped API key, and route webhook events to the right place.”
   • [claimed-docs] “Scoped API keys restrict access to a single pod or a single inbox.”
   • [claimed-docs] “`Permissions` let you restrict what an API key can do.”

   proof ↗⚑ flag

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

   weight 3 · round to AgentMail
   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

   AgentMail~partialprobed5/10

   AgentMail supports connecting standard IMAP/SMTP clients (Outlook, Thunderbird, Apple Mail), which gives users open-protocol access to their mailbox data rather than lock-in to a proprietary format, and the OpenAPI spec/CLI allow programmatic retrieval of messages. However there is no explicit documented 'export all data' or account-portability/data-takeout feature, and no evidence of exporting threads/attachments in bulk open formats. Missing for 10: explicit bulk export/backup tooling, documented data-portability guarantees, and confirmation of full account deletion with data takeout.

   • [claimed-docs] “Connect Outlook, Thunderbird, Apple Mail, or any IMAP/SMTP-compatible client to your AgentMail inbox”
   • [probe] “PROBE openapi: HTTP 200 at https://docs.agentmail.to/openapi.json — contains "openapi" key”
   • [claimed-docs] “Create inboxes, send messages, manage threads, and more — all without writing code.”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   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

   AgentMail—none0/10

   No evidence of AgentMail's source code being open or under an open-source license; it is a hosted API/SaaS product with documented API, SDKs, CLI, and MCP server but no mention of source availability or licensing.

   ⚑ flag

4. ai-native userSelf-host the core product

   weight 3 · round drawn
   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

   AgentMail—none0/10

   AgentMail is presented entirely as a hosted API/SaaS product (docs describe hosted MCP server, hosted API, dashboards) with no documentation of a self-hosted deployment option; a community comment even notes a competitor markets itself as 'a self-hosted drop-in replacement' for AgentMail, implying AgentMail itself lacks this capability.

   • [claimed-docs] “Create, manage, and operate email inboxes entirely via API.”
   • [claimed-docs] “AgentMail runs a hosted MCP server at https://mcp.agentmail.to/mcp that exposes inbox, message, thread, draft, and attachment tools to any c…”
   • [community] “agentmail charges $20/mo for 10 inboxes. autopilot gives you unlimited inboxes for the cost of a postgres row, positioning itself as a self-…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   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

   AgentMail—none0/10

   No evidence in the pack mentions data residency, regional storage options, or compliance controls for choosing where data is stored; the docs cover inboxes, messaging, webhooks, MCP, and multi-tenancy but nothing about region selection.

   ⚑ flag

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

   weight 3 · round drawn
   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

   AgentMail—none0/10

   No evidence in the pack addresses data-training opt-out, AI model training policies, or privacy controls regarding use of email data for training; the docs focus on API/product functionality, not data-privacy commitments.

   ⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round drawn
   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

   AgentMail—none0/10

   The evidence pack covers AgentMail's inbox/messaging, permissions, and multi-tenancy features but contains no mention of data retention policies, deletion controls, or privacy/compliance settings for stored emails or attachments.

   ⚑ flag

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

   weight 2 · round drawn
   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

   AgentMail—none0/10

   No evidence in the pack mentions telemetry, usage tracking, analytics opt-out, or any privacy/data-collection controls for AgentMail; the docs and community items focus on email/API features, pricing, and site performance instead.

   ⚑ flag

Search

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

   weight 2 · round to AgentMail
   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

   AgentMail~partialclaimed5/10

   Docs confirm full-text search across sender, recipients, subject, and body with relevance ranking, covering the core 'ranked results' and 'across full mail history' aspects. However, there's no evidence of specific search operators (e.g., date ranges, boolean logic) or advanced filters, and no independent benchmarking of speed/precision. missing for 10: documented search operators/filters syntax, evidence of performance at scale, independent verification of search speed/precision.

   • [claimed-docs] “Full-text search finds Threads by keyword across the sender, recipients, subject, and message body, ranked by relevance.”

   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
   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

   AgentMail—none0/10

   AgentMail's docs focus entirely on API/SDK/CLI/webhook/MCP functionality for building agent email workflows; there is no mention anywhere of keyboard shortcuts, a command palette, or any interactive UI navigation features for power users. Community evidence actually describes the dashboard/website as laggy and slow to load (WebGL errors, noticeable lag vs. other sites), directly undercutting the 'fast enough to never wait' requirement even if such an interface existed.

   • [community] “"Application error: a client-side exception has occurred while loading www.agentmail.to"... Failed to create WebGL context... Cookie rejecte…”
   • [community] “The website is really bad. Moving from Python to curl tab on the site shows noticeable lag - I have seen 2-3 whole websites load faster in t…”
   • [community] “I have written about how slow the website is... the amount of lag is something I have genuinely never witnessed in any website... I can't vi…”
   • [claimed-docs] “Create inboxes, send messages, manage threads, and more — all without writing code.”

   proof ↗⚑ flag

Shared inbox

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

   weight 3 · round drawn
   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

   AgentMail—none0/10

   AgentMail's docs describe agent-centric inboxes, cc/bcc human-in-the-loop oversight, drafts for approval, and per-tenant Pods, but nothing indicates a shared inbox/team-channel experience where multiple human team members view the same conversation state together. No evidence of shared inbox dashboards, team member roles, or collaborative conversation views for a team-lead's team.

   • [claimed-docs] “You can cc or bcc a real person on any message your agent sends, creating a "human-in-the-loop" workflow for oversight, escalations, or qual…”
   • [claimed-docs] “create a Pod per customer, give them a scoped API key, and route webhook events to the right place.”
   • [claimed-docs] “Human-in-the-Loop Review: An agent can create a `Draft` for a sensitive or important `Message`, which a human can then review and approve be…”
   • [claimed-docs] “Use `Labels` to track the state of a conversation.”
   • [claimed-docs] “Create one pod per customer/tenant in your system”

   proof ↗⚑ flag

Inbox structure

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

   weight 1 · round to Fastmail
   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

   AgentMail—none0/10

   AgentMail's docs describe programmatic labeling, threading, and search, but there is no evidence of any UI or bulk API operation for selecting many conversations at once and archiving/labeling/marking done in a single action; the product is positioned as an agent-facing API rather than a human triage inbox with bulk controls.

   • [claimed-docs] “Use `Labels` to track the state of a conversation.”
   • [claimed-docs] “Full-text search finds Threads by keyword across the sender, recipients, subject, and message body, ranked by relevance.”

   proof ↗⚑ flag