Missive 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 AgentMail
   Missive—none0/10

   The evidence pack contains no mention of IMAP, JMAP, or SMTP access for user mailboxes, nor any standards-based export functionality; all connectivity evidence is about REST API, webhooks, and MCP integrations for AI/automation, not about open mail protocol interoperability or data portability for switchers.

   ⚑ 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
   Missive—none0/10

   Missive is a cloud-hosted SaaS collaboration/email platform with no documented self-hosting option; community evidence confirms mail data routes through Missive's own servers (missive-comm-1), and no docs mention on-premise or self-hosted deployment.

   • [community] “User asked if Gmail/Yahoo emails pass through Missive's servers. After being told TLS is used but data does route through Missive's servers,…”

   proof ↗⚑ 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
   Missive—none0/10

   Direct probes show no llms.txt, no docs.md, and no OpenAPI spec exposed at expected locations (all 404), and no evidence of agent-oriented documentation formats being offered elsewhere; while Missive has an MCP server (a different axis), there's no proof an agent can be pointed at llms.txt or similar agent-readable docs.

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

   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
   Missive~partialprobed3/10

   Missive exposes a REST API, webhooks, and a documented MCP server that let external systems and AI agents trigger actions without using the UI, which could be scripted from CI/automation pipelines. However there is no evidence of an official CLI, headless mode, Docker/container deployment, or CI-specific documentation/examples for running Missive itself in automated pipelines. Missing for 10: dedicated CLI or headless execution mode, CI/CD integration guides, and independent confirmation of automation-in-CI use cases.

   • [claimed-docs] “Missive developer tools: REST API, UI integrations, webhooks, and custom channels for full customization.”
   • [claimed-docs] “Use the Rest API to enrich Missive conversations with content from anywhere: commits from GitHub, transactions from Stripe,”
   • [claimed-docs] “Automate your workflows”
   • [claimed-docs] “API & MCP access”
   • [probe] “official MCP server documented at https://missiveapp.com/docs/ai/mcp/server”

   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 Missive
   Missive✓fullprobed9/10

   Missive explicitly documents an official MCP server that lets external AI apps (Claude, ChatGPT, Cursor) connect and act on conversations, contacts, calendar, and drafts with configurable permissions, and a dedicated docs page for the MCP server is confirmed to exist via probe. Missing for 10: independent/hands-on third-party confirmation that external agents successfully connect and operate via this server.

   • [claimed-docs] “External AI apps like Claude, ChatGPT, or Cursor can now connect to Missive through the Model Context Protocol and act on your conversations…”
   • [claimed-docs] “External AI apps like Claude, ChatGPT, or Cursor can now connect to Missive through the Model Context Protocol and act on your conversations…”
   • [probe] “official MCP server documented at https://missiveapp.com/docs/ai/mcp/server”
   • [claimed-docs] “API & MCP access”

   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
   Missive—none0/10

   Missive is an email/collaboration app offering REST API, webhooks, and MCP integrations, but no evidence anywhere in the pack mentions an official CLI tool for interacting with Missive. Probes for docs/openapi manifests return 404s, and no CLI-related changelog or docs entries exist.

   • [claimed-docs] “Missive developer tools: REST API, UI integrations, webhooks, and custom channels for full customization.”
   • [claimed-docs] “Missive developer tools: REST API, UI integrations, webh”
   • [probe] “PROBE llms.txt: HTTP 404 at https://missiveapp.com/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://missiveapp.com/docs.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://missiveapp.com/openapi.json, https://missiveapp.com/swagger.json, https://missiveapp.com/api…”

   proof ↗⚑ 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
   Missive✓fullprobed8/10

   Missive documents a REST API, webhooks, UI integrations, and custom channels for developers (missive-docs-31/39/15), plus an official MCP server exposing conversations, contacts, calendar, and drafts to AI apps like Claude/ChatGPT/Cursor (missive-docs-1/20, missive-probe-4). This gives AI-native users a documented, programmatic way to drive the product beyond the UI. Missing for 10: a discoverable OpenAPI/swagger spec or llms.txt (all probed and 404'd) and independent third-party corroboration of API robustness.

   • [claimed-docs] “Missive developer tools: REST API, UI integrations, webhooks, and custom channels for full customization.”
   • [claimed-docs] “Missive developer tools: REST API, UI integrations, webh”
   • [claimed-docs] “Use the Rest API to enrich Missive conversations with content from anywhere: commits from GitHub, transactions from Stripe,”
   • [claimed-docs] “External AI apps like Claude, ChatGPT, or Cursor can now connect to Missive through the Model Context Protocol and act on your conversations…”
   • [claimed-docs] “External AI apps like Claude, ChatGPT, or Cursor can now connect to Missive through the Model Context Protocol and act on your conversations…”
   • [probe] “official MCP server documented at https://missiveapp.com/docs/ai/mcp/server”
   • [claimed-docs] “API & MCP access”

   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
   Missive~partialclaimed5/10

   Missive's MCP integration explicitly notes external AI apps connect "with the permissions you choose" (missive-docs-20) and custom MCP setup lets you "choose an authentication method" (missive-docs-17), implying some scoped access control for agents. However, there's no documentation of granular API-key scopes, role-based permission tiers, or a dedicated credential-issuance UI for least-privilege agent access. Missing for 10: explicit scoped API key/token generation flow, documented permission levels/roles for agents, and independent confirmation that scoping is enforced in practice.

   • [claimed-docs] “External AI apps like Claude, ChatGPT, or Cursor can now connect to Missive through the Model Context Protocol and act on your conversations…”
   • [claimed-docs] “Add "Custom MCP" and enter a name and your server URL. Choose an authentication method and click Add”
   • [claimed-docs] “API & MCP access”
   • [claimed-docs] “Give your Missive AI Assistant access to internal APIs, databases, or custom tooling”

   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
   Missive—none0/10

   Missive documents a REST API, webhooks, custom channels, and MCP integrations for developers, but no evidence anywhere mentions official client SDKs (e.g. language libraries) for building against Missive; probes even show 404s for OpenAPI/spec files that would typically back SDK generation.

   • [claimed-docs] “Missive developer tools: REST API, UI integrations, webhooks, and custom channels for full customization.”
   • [claimed-docs] “Missive developer tools: REST API, UI integrations, webh”
   • [probe] “PROBE openapi: all candidate paths 404 (https://missiveapp.com/openapi.json, https://missiveapp.com/swagger.json, https://missiveapp.com/api…”
   • [probe] “PROBE llms.txt: HTTP 404 at https://missiveapp.com/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://missiveapp.com/docs.md”

   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
   Missive~partialclaimed4/10

   Missive's developer tools page explicitly lists webhooks alongside REST API and custom channels, confirming the capability exists, but there is no detail on event types, subscription setup, payload format, or independent corroboration of webhook usage. Missing for 10: documented list of subscribable event types, webhook setup/config instructions, security/signing details, and third-party confirmation of reliability.

   • [claimed-docs] “Missive developer tools: REST API, UI integrations, webhooks, and custom channels for full customization.”
   • [claimed-docs] “Missive developer tools: REST API, UI integrations, webh”

   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 to Missive
   Missive~partialclaimed7/10

   Missive documents rule-based workflow automation (up to 1000 rules) and long-running AI assistant sessions that operate in the background with a session tab showing progress ('no longer need babysitting'), plus agent-driven triage of conversations against a CRM before a human looks at them — evidence of autonomous background automation. However, there's no independent/hands-on confirmation of reliability or scope of autonomy, and details on triggers/scheduling for rules are thin. Missing for 10: independent corroboration of autonomous execution reliability, deeper documentation on rule triggers/scheduling and failure handling.

   • [claimed-docs] “Automate your workflows”
   • [claimed-docs] “Automate your workflows Up to 1000 rules”
   • [claimed-docs] “Up to 1000 rules”
   • [claimed-docs] “The session tab now shows what the assistant is up to, and a conversation links back to the sessions attached to it.”
   • [claimed-docs] “Long assistant sessions no longer need babysitting. The session tab now shows what the assistant is up to”
   • [claimed-docs] “Let an agent triage new conversations against your CRM before you look at them”
   • [claimed-docs] “External AI apps like Claude, ChatGPT, or Cursor can now connect to Missive through the Model Context Protocol and act on your conversations…”

   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 Missive
   Missive✓fullclaimed7/10

   Missive's AI Assistant/Copilot and MCP integration let users issue natural-language requests (e.g., 'Ask Claude to summarize your inbox and draft replies,' 'compose, reply, and translate messages with AI') and let external AI apps act on conversations, contacts, calendar, and drafts through natural language via Claude/ChatGPT/Cursor. The command bar also supports quick text-based commands for actions like snoozing. Missing for 10: independent/hands-on user validation of natural-language accuracy and no detailed listing of all supported natural-language actions beyond marketing copy.

   • [claimed-docs] “External AI apps like Claude, ChatGPT, or Cursor can now connect to Missive through the Model Context Protocol and act on your conversations…”
   • [claimed-docs] “External AI apps like Claude, ChatGPT, or Cursor can now connect to Missive through the Model Context Protocol and act on your conversations…”
   • [claimed-docs] “Ask Claude to summarize your inbox and draft replies without leaving the chat”
   • [claimed-docs] “Let an agent triage new conversations against your CRM before you look at them”
   • [claimed-docs] “Long assistant sessions no longer need babysitting. The session tab now shows what the assistant is up to”
   • [claimed-docs] “Quickly compose, reply, and translate messages with AI directly in Missive.”
   • [claimed-docs] “Ask how a feature works, how to set up a rule, or where a setting lives. The answer comes straight from the Missive documentation instead of…”
   • [claimed-docs] “Master the command bar: keyboard shortcuts and quick commands. You can use the following patterns to initiate a search: search searc sear se…”

   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
   Missive—none0/10

   Missive documents a REST API and developer tools, but there is no evidence of an interactive API reference or runnable examples; explicit probes for openapi/swagger specs all returned 404s, indicating no interactive API explorer exists.

   • [claimed-docs] “Use the Rest API to enrich Missive conversations with content from anywhere: commits from GitHub, transactions from Stripe,”
   • [claimed-docs] “Missive developer tools: REST API, UI integrations, webhooks, and custom channels for full customization.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://missiveapp.com/openapi.json, https://missiveapp.com/swagger.json, https://missiveapp.com/api…”

   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
   Missive—none0/10

   Probes for OpenAPI/Swagger spec files at standard locations all returned 404, and no evidence pack item mentions a downloadable machine-readable API spec despite Missive having a REST API and developer docs.

   • [probe] “PROBE openapi: all candidate paths 404 (https://missiveapp.com/openapi.json, https://missiveapp.com/swagger.json, https://missiveapp.com/api…”
   • [claimed-docs] “Missive developer tools: REST API, UI integrations, webhooks, and custom channels for full customization.”
   • [claimed-docs] “Missive developer tools: REST API, UI integrations, webh”

   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
   Missive—none0/10

   No evidence of any sandbox, staging, or test environment offered by Missive; all MCP/API access documented operates directly against live conversations, contacts, calendars, and drafts (missive-probe-rt-2), with no mention of a non-production mode for testing.

   ⚑ 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
   Missive—none0/10

   There is a REST API and MCP integrations documented, but no evidence of API versioning scheme or any documented deprecation policy; probes for openapi/spec files all 404. missing for 10: versioning scheme documentation, explicit deprecation/backward-compatibility policy, changelog of breaking API changes.

   • [claimed-docs] “Use the Rest API to enrich Missive conversations with content from anywhere: commits from GitHub, transactions from Stripe,”
   • [claimed-docs] “Missive developer tools: REST API, UI integrations, webhooks, and custom channels for full customization.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://missiveapp.com/openapi.json, https://missiveapp.com/swagger.json, https://missiveapp.com/api…”

   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
   Missive~partialprobed6/10

   Missive documents an official MCP server (missive-probe-4) that lets external AI apps like Claude, ChatGPT, or Cursor connect and act on conversations, contacts, calendar, and drafts with configurable permissions (missive-docs-1, missive-docs-20), including summarizing inboxes, drafting replies, and triaging conversations against a CRM (missive-docs-21, missive-docs-22). However, explicit end-to-end 'send' capability via the agent is not directly documented, and there is no independent/hands-on corroboration of the full read-triage-draft-send loop working in practice. Missing for 10: explicit documentation of agent-initiated sending (not just drafting), and third-party/hands-on verification of the full workflow.

   • [claimed-docs] “External AI apps like Claude, ChatGPT, or Cursor can now connect to Missive through the Model Context Protocol and act on your conversations…”
   • [claimed-docs] “External AI apps like Claude, ChatGPT, or Cursor can now connect to Missive through the Model Context Protocol and act on your conversations…”
   • [claimed-docs] “Ask Claude to summarize your inbox and draft replies without leaving the chat”
   • [claimed-docs] “Let an agent triage new conversations against your CRM before you look at them”
   • [claimed-docs] “With custom MCP, you can connect any MCP-compatible server to Missive's AI Copilot and let AI interact with your internal systems, proprieta…”
   • [claimed-docs] “Connect any MCP-compatible server to Missive's AI Copilot and let AI interact with your internal systems, proprietary data, or homegrown too…”
   • [probe] “official MCP server documented at https://missiveapp.com/docs/ai/mcp/server”

   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 to Missive
   Missive~partialclaimed6/10

   Missive's AI Assistant/MCP integration lets external AI apps (Claude, ChatGPT, Cursor) act on conversations, contacts, calendar, and drafts, and docs explicitly mention asking Claude to summarize the inbox and draft replies — directly supporting cross-inbox Q&A grounded in Missive data. However, evidence doesn't demonstrate calendar-specific querying depth or explicit 'what's outstanding' style aggregate reasoning across the whole inbox, and there's no independent/hands-on validation of answer groundedness or accuracy. Missing for 10: concrete examples of calendar-integrated Q&A, evidence of multi-conversation aggregate answers, and independent corroboration of answer quality/groundedness.

   • [claimed-docs] “External AI apps like Claude, ChatGPT, or Cursor can now connect to Missive through the Model Context Protocol and act on your conversations…”
   • [claimed-docs] “External AI apps like Claude, ChatGPT, or Cursor can now connect to Missive through the Model Context Protocol and act on your conversations…”
   • [claimed-docs] “Ask Claude to summarize your inbox and draft replies without leaving the chat”
   • [claimed-docs] “Give your Missive AI Assistant access to internal APIs, databases, or custom tooling”
   • [claimed-docs] “With custom MCP, you can connect any MCP-compatible server to Missive's AI Copilot and let AI interact with your internal systems, proprieta…”

   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 to Missive
   Missive~partialclaimed4/10

   Missive documents AI compose/reply features ("Quickly compose, reply, and translate messages with AI directly in Missive" and "Ask Claude to summarize your inbox and draft replies") confirming AI drafting exists, but there is no evidence describing tone/voice personalization or that drafts are tuned to the user's own writing style versus generic boilerplate. Missing for 10: evidence of voice/tone learning or personalization, hands-on examples showing draft quality matches user's style, independent corroboration of draft usefulness.

   • [claimed-docs] “Quickly compose, reply, and translate messages with AI directly in Missive.”
   • [claimed-docs] “Ask Claude to summarize your inbox and draft replies without leaving the chat”
   • [claimed-docs] “Give your Missive AI Assistant access to internal APIs, databases, or custom tooling”

   proof ↗⚑ 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 to Missive
   Missive~partialclaimed6/10

   Missive's AI Assistant/MCP integration explicitly supports agent-driven triage ('Let an agent triage new conversations against your CRM before you look at them'), inbox summarization, and rule-based automation (up to 1000 rules), and provides audit trails via action logs and a session tab showing assistant activity, plus permission-scoped access for steering behavior. However, there's no explicit mention of automatic labeling/categorization as a distinct AI feature (only manual rules), and no independent/hands-on evidence confirming triage quality works as advertised. Missing for 10: explicit auto-labeling/categorization feature description, hands-on validation of triage accuracy, and clearer UI for reviewing/adjusting AI triage decisions beyond session logs.

   • [claimed-docs] “Let an agent triage new conversations against your CRM before you look at them”
   • [claimed-docs] “Ask Claude to summarize your inbox and draft replies without leaving the chat”
   • [claimed-docs] “The session tab now shows what the assistant is up to, and a conversation links back to the sessions attached to it.”
   • [claimed-docs] “Long assistant sessions no longer need babysitting. The session tab now shows what the assistant is up to”
   • [claimed-docs] “Every action within Missive is logged, so you know who did what, and when.”
   • [claimed-docs] “External AI apps like Claude, ChatGPT, or Cursor can now connect to Missive through the Model Context Protocol and act on your conversations…”
   • [claimed-docs] “Automate your workflows”
   • [claimed-docs] “Up to 1000 rules”

   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 AgentMail
   Missive~partialclaimed3/10

   Missive documents rule-based automation ('Up to 1000 rules') and API/MCP access that could act across many items, plus a bulk auto-archive list feature, but there is no direct evidence of a bulk-select/bulk-action UI or bulk API endpoint for acting on many conversations/contacts at once. Missing for 10: explicit bulk-action UI documentation, bulk API/webhook examples, and independent confirmation of scale-limits for automation across many items.

   • [claimed-docs] “Automate your workflows Up to 1000 rules”
   • [claimed-docs] “Up to 1000 rules”
   • [claimed-docs] “Picking Everyone in a shared account's Auto-archive list covers anyone who joins your organization later, instead of adding each person by h…”
   • [claimed-docs] “Use the Rest API to enrich Missive conversations with content from anywhere: commits from GitHub, transactions from Stripe,”
   • [claimed-docs] “Give your Missive AI Assistant access to internal APIs, databases, or custom tooling”

   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
   Missive~partialclaimed5/10

   Missive confirms a native Rules feature ("Automate your workflows", "Up to 1000 rules", and documentation referencing 'how to set up a rule') that lets users define automation triggered by events, plus webhooks/API for event-driven actions. However, the evidence pack lacks concrete documentation of what trigger events or actions rules support, no hands-on examples of rule configuration, and no independent corroboration of automation depth or reliability. missing for 10: detailed rule trigger/action catalog, hands-on walkthrough of rule creation, independent user validation of automation reliability.

   • [claimed-docs] “Ask how a feature works, how to set up a rule, or where a setting lives. The answer comes straight from the Missive documentation instead of…”
   • [claimed-docs] “Automate your workflows”
   • [claimed-docs] “Automate your workflows Up to 1000 rules”
   • [claimed-docs] “Up to 1000 rules”
   • [claimed-docs] “Missive developer tools: REST API, UI integrations, webhooks, and custom channels for full customization.”

   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
   Missive—none0/10

   No evidence in the pack mentions read receipts, email open tracking, or notifications about recipient opens/views; the pack covers collaboration, MCP/AI integrations, and admin features but nothing about tracking email opens.

   ⚑ 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 drawn
   Missive—none0/10

   No evidence in the pack mentions scheduled sending or an undo-send grace window; the pack covers MCP integrations, collaboration features, snoozing, and canned responses but nothing about send scheduling or send-delay/undo functionality.

   ⚑ 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 Missive
   Missive✓fullclaimed8/10

   Missive's canned responses/templates feature explicitly supports saving reusable replies, inserting them via keystrokes/command bar, sharing across teams, and customizing with a variables templating engine (recipient name, etc.), directly matching the story; MCP/API docs also confirm drafts resolve template variables like {{ user.name }}. missing for 10: explicit first-party documentation confirming attachments can be bundled/saved within a canned response/template, and independent hands-on corroboration of the templating workflow.

   • [claimed-docs] “Canned responses (or templates) are pre-written replies to common questions. Instead of typing the same answer repeatedly, you write it once…”
   • [claimed-docs] “You can easily customize your responses or templates with dynamic content like your recipient's name by using our variables templating engin…”
   • [claimed-docs] “Drafts created outside the composer, by the assistant, by a rule, or through the API and MCP server, now resolve {{ user.name }} and {{ user…”
   • [claimed-docs] “Drafts created outside the composer, by the assistant, by a rule, or through the API and MCP server, now resolve {{ user.name }} and {{ user…”

   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
   Missive~partialprobed4/10

   Missive documents a REST API, webhooks, and an MCP server that can act on conversations, contacts, calendar, and drafts (missive-docs-15, missive-docs-31, missive-docs-45, missive-probe-4), suggesting broad but not explicitly complete UI/API parity — there is no vendor claim of 1:1 feature parity, and the OpenAPI spec could not be located via standard probes (missive-probe-3), making it hard to verify full API surface coverage against UI capabilities like snoozing, canned responses, or command-bar search (missive-docs-supp-1/3/4) which are not mentioned as API-exposed. Missing for 10: an explicit vendor statement of full UI/API parity, a discoverable OpenAPI/schema reference, and evidence that UI-only features (snoozing, canned responses, command bar actions) are also API-accessible.

   • [claimed-docs] “Use the Rest API to enrich Missive conversations with content from anywhere: commits from GitHub, transactions from Stripe,”
   • [claimed-docs] “Missive developer tools: REST API, UI integrations, webhooks, and custom channels for full customization.”
   • [claimed-docs] “Drafts created outside the composer, by the assistant, by a rule, or through the API and MCP server, now resolve {{ user.name }} and {{ user…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://missiveapp.com/openapi.json, https://missiveapp.com/swagger.json, https://missiveapp.com/api…”
   • [probe] “official MCP server documented at https://missiveapp.com/docs/ai/mcp/server”
   • [claimed-docs] “Snoozing temporarily hides a conversation until a specific time, then brings it back to your Inbox. Use it to defer emails you can't deal wi…”
   • [claimed-docs] “Canned responses (or templates) are pre-written replies to common questions. Instead of typing the same answer repeatedly, you write it once…”

   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
   Missive—none0/10

   The evidence pack shows a REST API, webhooks, and MCP integrations for connecting external tools, but nothing documents a bulk data-export feature or open-format (mbox/CSV/JSON) export enabling a user to fully extract their mail, contacts, and conversation history and leave the platform. Probes for docs/API artifacts (llms.txt, openapi) also 404, further indicating no dedicated export-and-leave capability is documented.

   • [claimed-docs] “Use the Rest API to enrich Missive conversations with content from anywhere: commits from GitHub, transactions from Stripe,”
   • [claimed-docs] “Missive developer tools: REST API, UI integrations, webhooks, and custom channels for full customization.”
   • [probe] “PROBE llms.txt: HTTP 404 at https://missiveapp.com/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://missiveapp.com/docs.md”
   • [probe] “PROBE openapi: all candidate paths 404 (https://missiveapp.com/openapi.json, https://missiveapp.com/swagger.json, https://missiveapp.com/api…”

   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
   Missive—none0/10

   Missive is a closed-source commercial email/collaboration SaaS; no evidence anywhere in the pack of an open-source license or public source repository, and probes for typical openness indicators (llms.txt, docs.md, openapi) all 404. No indication source code is available under any license.

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

   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
   Missive—none0/10

   Missive is a cloud-hosted SaaS collaboration/email product; evidence shows data routes through Missive's own servers (missive-comm-1) and no docs mention any self-hosting/on-prem deployment option anywhere in the extensive feature/pricing/docs pack.

   • [community] “User asked if Gmail/Yahoo emails pass through Missive's servers. After being told TLS is used but data does route through Missive's servers,…”

   proof ↗⚑ 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
   Missive—none0/10

   No evidence in the pack mentions data residency, region selection, or geographic storage location controls; features like IP restrictions and SSO relate to access control, not data storage location. Missing for 10: any mention of regional data hosting options, residency guarantees, or storage location configuration.

   ⚑ 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
   Missive—none0/10

   No evidence in the pack addresses any AI-training opt-out, data-usage policy for AI model training, or privacy controls specific to preventing training on user data. The pack covers MCP integrations, AI assistant features, and collaboration tools, but nothing about training data exclusion or a documented privacy commitment on this axis.

   ⚑ 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
   Missive—none0/10

   No evidence describes any data retention or deletion controls (e.g., configurable retention periods, right-to-delete, data purge options) for Missive or its AI/MCP features; the only related community note concerns data routing through servers via TLS, not retention/deletion policy.

   • [community] “User asked if Gmail/Yahoo emails pass through Missive's servers. After being told TLS is used but data does route through Missive's servers,…”

   proof ↗⚑ 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
   Missive—none0/10

   No evidence pack item addresses telemetry/usage-tracking opt-out settings, privacy controls, or data-collection disclosures for Missive; the closest related content (comm-1) merely notes emails route through Missive's servers, which is unrelated to telemetry opt-out. This is an applicable axis for a SaaS product but no supporting evidence exists.

   ⚑ 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
   Missive~partialclaimed3/10

   Evidence confirms Missive has search filters (Type: Internal/External, Date range) and a command-bar search that can query across messages, contacts, or a specific label, but there is no documentation of search operators (from:, subject:, boolean, etc.), relevance ranking, or explicit assurance of full-history indexing/performance at scale. Missing for 10: documented search operator syntax, ranked-results behavior, evidence of speed/precision across large mail archives, and independent corroboration of search quality.

   • [claimed-docs] “The Type (Internal / External) and Date range filters in search no longer stay greyed out until you enter a search term.”
   • [claimed-docs] “The Type (Internal / External) and Date range filters in search no longer stay greyed out until you enter a search”
   • [claimed-docs] “Master the command bar: keyboard shortcuts and quick commands. You can use the following patterns to initiate a search: search searc sear se…”

   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 Missive
   Missive~partialcommunity6/10

   Missive documents a command bar (⌘/Ctrl+K) supporting search, snooze, and other quick commands, plus configurable swipe/keyboard shortcuts, which is direct evidence of keyboard-driven command palette functionality. However, there's no comprehensive shortcut list, no dedicated performance benchmarks, and community comments call the UI 'unintuitive' with 'design flaws' though also 'snappy' — mixed signal on speed/polish. Missing for 10: a full documented shortcut reference covering all major actions, explicit performance/latency claims, and independent hands-on confirmation of speed and keyboard completeness.

   • [claimed-docs] “You can also snooze by swiping a conversation (configurable in Settings > Preferences > Swipes), or by opening the command bar with ⌘/Ctrl +…”
   • [claimed-docs] “Master the command bar: keyboard shortcuts and quick commands. You can use the following patterns to initiate a search: search searc sear se…”
   • [community] “"We choose Missive for now because Missive feels like a proper snappy desktop app and is vastly cheaper ($15 vs $50 per user). Front feels l…”
   • [community] “"I fear that we will eventually switch to Front because Missive is unintuitive or (please someone build that) Gmail with collaboration featu…”

   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 to Missive
   Missive✓fullcommunity9/10

   Missive's core product docs directly describe shared/team inboxes with multiple people working the same inbox without conflict, conversation assignment while maintaining visibility, distribution-list-to-shared-inbox mapping, per-action audit logging, and dedicated team spaces/channels — exactly the shared-conversation-state model the story describes (missive-docs-6, missive-docs-9, missive-docs-19, missive-docs-28, missive-docs-32, missive-docs-35, missive-docs-30/48). Independent community commentary corroborates it is used specifically for team email collaboration (missive-comm-3), and no evidence contradicts the shared-inbox mechanics themselves (complaints found are about general UX/bugs, not this capability). Missing for 10: a hands-on third-party account specifically confirming real-time shared conversation-state syncing across users (vs. general collaboration praise).

   • [claimed-docs] “Assign conversations to a team or specific person, while maintaining visibility. And jump in, if needed.”
   • [claimed-docs] “Every action within Missive is logged, so you know who did what, and when.”
   • [claimed-docs] “Give each team a tailored space so they can seamlessly focus on their work.”
   • [claimed-docs] “Have multiple people work out of the same inbox, without stepping on each other’s toes.”
   • [claimed-docs] “From distribution lists to shared inboxes”
   • [claimed-docs] “Have multiple people work out of the same inbox, without stepping on each other's toes.”
   • [claimed-docs] “See what’s going on, know who’s doing what, and collaborate behind the scenes — without changing your workflow.”
   • [community] “"I love Streak for singleplayer but prefer Missive or Front for collaboration."”

   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 drawn
   Missive—none0/10

   The evidence pack covers command bar search, snoozing, canned responses, MCP/AI assistant integration, and team collaboration features, but nothing documents multi-select bulk actions (archive/label/mark done across many conversations at once). Missing for 10: any docs or changelog entry describing bulk selection UI, keyboard multi-select, or batch archive/label/mark-done operations.

   • [claimed-docs] “You can also snooze by swiping a conversation (configurable in Settings > Preferences > Swipes), or by opening the command bar with ⌘/Ctrl +…”
   • [claimed-docs] “Master the command bar: keyboard shortcuts and quick commands. You can use the following patterns to initiate a search: search searc sear se…”

   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