Skip to content

Agent2Agent protocol definition

The Agent2Agent (A2A) protocol is an open standard that lets AI agents built by different vendors or frameworks discover each other through agent cards, delegate work as tasks, and exchange messages and artifacts, without sharing their internal memory, tools, or reasoning.


A diagram explaining Agent2Agent protocol in terms of related concepts.

How does the Agent2Agent protocol compare to MCP?

What are agent cards, tasks, and artifacts in A2A?

How does one agent delegate a task to another over A2A?

Is the A2A protocol the same as a multi-agent framework?

Who created the Agent2Agent protocol, and who governs it now?

Why do multi-agent systems still need a shared source of context?

Discover More with Sanity

Now that you've learned about Agent2Agent protocol, why not start exploring what Sanity has to offer? Dive into our platform and see how it can support your content needs.

Last updated: