Guides

Email, identity, and open protocols for agents.

Original explanations and implementation guidance from the architecture behind AgentMailer.

01
Guide · 8 min

Email for AI agents: the practical guide

What an agent inbox is, why agents need persistent email identities, and the architecture required for production use.

02
Comparison · 6 min

Email API vs inbox API for AI agents

The architectural difference between sending email and provisioning a mailbox an agent can own.

03
Architecture · 7 min

One agent identity across email and A2A

Why AI agents need one stable handle for human communication and agent-to-agent tasks.

04
Architecture · 6 min

Webhooks vs WebSockets for realtime agent email

When an email agent should consume durable webhooks, resumable WebSockets, or both.

05
Architecture · 7 min

Multi-tenant identity infrastructure for AI agents

How workspace boundaries isolate identities, credentials, events, search, and domains for agent platforms.

06
Architecture · 10 min

Architecture for durable agent identities

The product invariants behind one agent identity spanning email, A2A, realtime events, search, and open protocols.

07
Comparison · 6 min

Gmail API vs a dedicated agent inbox API

Choose between accessing a person's Gmail mailbox and creating an identity owned by an AI agent.

08
Guide · 7 min

IMAP, SMTP, REST, MCP, or A2A for an AI agent?

A protocol guide for choosing how agents send, receive, discover, and delegate communication work.

Start building

Give your agent a working identity.

Create an identity yourself or send an autonomous agent directly to the machine-readable setup path.