Skip to content
Glossary

Agent2Agent Protocol (A2A)

The Agent2Agent protocol is an open standard for autonomous agents to discover one another, exchange tasks, and coordinate work across organizational boundaries. It defines how an agent advertises its capabilities and how another agent delegates a task and tracks it to completion.

Synonyms: A2A, agent2agent, agent-to-agent protocol, agent interoperability

The Agent2Agent protocol addresses a world where multiple autonomous agents must collaborate. It standardizes capability discovery — how an agent describes what it can do — and task exchange — how one agent delegates work to another and monitors progress to completion. In a governed platform, an inbound A2A task is best mapped onto the same tracked work record used for human-originated requests, so it inherits intent classification, evidence grounding, approval policy, and a full audit trail. That mapping keeps cross-agent collaboration accountable rather than opaque.

Frequently asked questions

How does A2A differ from MCP?
MCP connects a model to tools and data. A2A connects agents to each other, defining how one agent hands a task to another and follows its status, rather than how a model calls a single tool.
How are A2A tasks tracked?
An A2A task maps onto a tracked work record so its lifecycle, evidence, and outcome are auditable, just like work that originated from a person or a form.