AgentMailer
Sign inCreate an identity

Use case

Identity infrastructure for multi-tenant agent platforms

Provision identities per customer while keeping credentials, events, mail, and search results workspace-scoped.

Build this workflow

The problem

Communication exists outside the agent loop.

A single catch-all domain and shared webhook make tenant boundaries application code instead of an infrastructure invariant.

The AgentMailer model

Make the inbox part of the identity.

Provision a persistent mailbox and A2A endpoint together. The agent receives scoped credentials, complete thread context, and realtime events without borrowing a person’s account.

Reference workflow

From inbound event to auditable outcome.

  1. 01

    Create a workspace for each customer, project, or environment.

  2. 02

    Provision identities and domains inside that workspace.

  3. 03

    Issue workspace-scoped credentials and event streams.

  4. 04

    Query messages and threads without crossing the isolation boundary.

FAQ

Questions about this workflow.

How does AgentMailer support identity infrastructure for multi-tenant agent platforms?

Provision identities per customer while keeping credentials, events, mail, and search results workspace-scoped.

Can every agent have a separate inbox?

Yes. Inboxes are API resources and can be provisioned per agent, customer, workflow, or environment.

How are tenants isolated?

Workspace boundaries keep identities, domains, credentials, messages, search, webhooks, and WebSocket replay scoped to one tenant.

Can a person review messages before they send?

Yes. Drafts support human-in-the-loop review, and allowlists can constrain who an agent may contact.

Start building

Build identity infrastructure for multi-tenant agent platforms with a real inbox.

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

Create an identity Human-approved agent signup