ModelRefs / Agent-to-Agent Protocol (A2A) — AI Glossary
Agent-to-Agent Protocol (A2A) — AI Glossary
Google's open protocol for structured communication between AI agents, defining capability discovery, task delegation, and result exchange.
Overview
Google's Agent2Agent (A2A) protocol (2025) defines how agents advertise capabilities via Agent Cards, create tasks, exchange messages, and stream results using JSON-RPC over HTTP. Designed for enterprise multi-agent systems where agents from different vendors need to interoperate without shared infrastructure.
Reference details
| Topic | agents |
|---|---|
| Also known as | A2A, agent-to-agent |
| Last reviewed | 2026-06-24 |
Related terms
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Agent-to-Agent Protocol (A2A) — AI Glossary.
Frequently asked questions
What is Agent-to-Agent Protocol (A2A)?
Google's open protocol for structured communication between AI agents, defining capability discovery, task delegation, and result exchange.
Is Agent-to-Agent Protocol (A2A) the same as A2A?
Yes — A2A, agent-to-agent are common aliases for Agent-to-Agent Protocol (A2A).
What concepts are related to Agent-to-Agent Protocol (A2A)?
Closely related concepts include agent protocol, mcp, agent.