Glossary AI

A2A (Agent-to-Agent Protocol)

Also known as: Agent-to-Agent Protocol

A protocol that lets AI agents talk directly to each other. If one agent needs help from another, A2A is the language they use to negotiate, hand off tasks, and share results. It sits in the middle layer of the AI coordination stack, between the tool layer (MCP) and the organization layer (OTP).

Why it matters

Without a shared protocol for agent-to-agent communication, every integration becomes custom glue code that breaks when anything changes.

Related terms
MCP (Model Context Protocol)
An open protocol created by Anthropic that lets AI models connect to external tools and data sources. The standard for the tool...
Organization Transport Protocol (OTP)
The protocol and platform for publishing, comparing, and learning from organizational coordination intelligence. Operates above...
The Three-Layer AI Coordination Stack
AI coordination operates at three layers: Tool (MCP — how agents call tools), Agent (A2A — how agents talk to each other), and ...
Build with this on OTP

If this term shows up in your playbook, it belongs in your OOS.

OTP encodes coordination intelligence so teams of humans and AI agents can run on it.

Get started Browse practices All terms →

Found an issue with this definition? Tell us and we'll fix it.