Glossary · Agentic AI
What is A2A? Definition and meaning
An open protocol, now under the Linux Foundation, with which agents discover each other and delegate tasks.
Definition
A2A: An open protocol, now under the Linux Foundation, with which agents discover each other and delegate tasks.
In short: Agent-to-Agent protocol for agents that talk to each other.
When it is used
Interoperability between agents from different vendors and frameworks.
Where it fits
A2A belongs to Protocols in the Agentic AI topic. These are the other terms in the same group:
- MCP: An open protocol, created by Anthropic, that lets a model use tools, data sources and prompts exposed by servers.
- Function calling: A model returns a structured call to a named function with arguments, and the application runs it and returns the result.
- Structured outputs: Constrains generation to a JSON schema or type so that results are always parseable.
- OAuth for tool access: Uses OAuth flows so an agent acts on a user's behalf with scoped, revocable permissions.
Learn more
The full guide to A2A explains how it works, when to use it and how it compares with the alternatives, with examples. The glossary lists every term on the site from A to Z.
Next term: A2C