# Agent2Agent (A2A)

An open protocol that lets independently operated agent systems discover one another, exchange messages and track work as a task with its own state and output artefacts.

Source: https://aecon.ai/glossary/agent2agent-protocol
Updated: 2026-09-15

## In practice

A research agent hands a bounded extraction task to a specialist agent run by another company, disconnects, reconnects an hour later and asks for the task's current state.

## The distinction

A2A moves tasks between agents; MCP connects one application to its tools. A2A carries the conversation and task state, and leaves the principal, permission, quality, contract and remedy to the systems around it.

## The task is the centre

A2A puts a `Task` at the middle of the exchange: a server-generated identifier, a current status, artefacts, history and metadata. The caller can submit work, disconnect, reconnect and ask for the state.

That solves a genuine transport problem. A remote agent can request more input, report progress or return a file without exposing its own prompt, memory or tool implementation.

## Completed is not accepted

The protocol's `completed` state means the remote implementation reached its terminal success state. It does not mean the parent agent accepted the file, the customer received what was promised, or a downstream record changed correctly.

That gap is the one to design for. A child task can complete while the parent discovers the schema is wrong, the evidence is stale or the customer needed something else. Acceptance is a separate record, owned by whoever is entitled to make it.

## What sits beside the wire

Five questions stay outside the message: which person or organisation owns the objective; what this actor may do with the data and budget; what makes the returned work correct; whether this is a one-off request or a supplier contract; and who repairs a loss.

A signed message can show integrity. It cannot show that the sender had the right to commission the work.

## Sources & context

- [A2A Protocol Specification](https://a2a-protocol.org/latest/specification/) — A2A Project, 1.0. Defines Agent Cards, messages, tasks, artefacts, streaming, push notifications and task operations, and leaves the authorisation model to the agent and its operator. Checked 2026-09-13.
- [Announcing the Agent2Agent Protocol](https://developers.googleblog.com/a2a-a-new-era-of-agent-interoperability/) — Google Developers Blog, 2025. States the design intent that independent agents collaborate without sharing internal state, memory or tools. A launch announcement, not adoption evidence. Checked 2026-09-13.

## Related reading

- [AI agent](https://aecon.ai/glossary/ai-agent)
- [Delegation](https://aecon.ai/glossary#delegation)
- [Model Context Protocol (MCP)](https://aecon.ai/glossary/model-context-protocol)
- [Agent registry](https://aecon.ai/glossary/agent-registry)