Glossary/Protocols & Infrastructure

What is A2A (Agent-to-Agent)?

A protocol for AI agents to discover and communicate with each other, exchanging messages through published capability descriptions called AgentCards.

As organizations deploy multiple AI agents, those agents need a standard way to find and use each other — a customer-service agent delegating a billing question to a billing specialist, or an external agent querying a vendor's knowledge agent.

A2A handles this with two pieces: an AgentCard, a public JSON description of what an agent can do and where to reach it, and a message protocol (message/send) for the actual exchange. Where MCP connects an assistant to tools, A2A connects agents to agents.

In BeforeQuery

How BeforeQuery uses this

Each knowledge base publishes a public A2A AgentCard and accepts message/send calls (client-key authenticated), so external agents can query your knowledge programmatically. The @beforequery/agents SDK includes both A2A and MCP clients, and A2A calls appear in traces.

From definition to deployment

Connect a knowledge source and see cited AI answers on your own content in minutes — free, no credit card required.

Get Started Free