# Persistent Return Paths for Asynchronous AI Agents

> AgentAddress is the persistence layer between an agent action and the response that may arrive minutes or days later.

## Use AgentAddress when
- The work crosses a human or system boundary.
- The response time exceeds the agent run.
- A later runtime must resume with the same event history.

## 1. Provision

POST https://agentaddress.dev/api/v1/addresses
Content-Type: application/json

{"task_id":"async_task_42","expires_in_seconds":86400}

Save the complete response. In particular, persist `credentials.read_token` and `endpoints.events_url` before the current run exits. The read token is returned only once.

## 2. Hand off

Choose the generated HTTPS inbox or email identity based on how the external responder can communicate.

POST {endpoints.inbox_url}
Content-Type: application/json
Idempotency-Key: result-42

{"type":"task.resumed","data":{"status":"complete"}}

## 3. Return later

GET {endpoints.events_url}?after=0&wait=25
Authorization: Bearer {credentials.read_token}

Process events in `sequence` order. Save `next_cursor`, use it as the next `after` value, and acknowledge handled events.

## Machine contracts

- [OpenAPI 3.1](https://agentaddress.dev/openapi.json)
- [Agent-readable index](https://agentaddress.dev/llms.txt)
- [Complete guide](https://agentaddress.dev/llms-full.txt)
- [Capability discovery](https://agentaddress.dev/.well-known/agentaddress.json)