Real-world problems need specialists working together. The same is true for AI agents: it’s better to have a set of niche experts than a single mind that’s mediocre at everything.
But that raises a new question: how do those agents communicate effectively?

In this session, we introduce the Agent-to-Agent (A2A) protocol, an open protocol designed to let autonomous agents discover each other, exchange tasks, stream progress, and collaborate across frameworks and languages.

We’ll explain why A2A exists, what problems it solves compared to framework-specific agent integrations, and then go inside the protocol, covering concepts like agent cards, tasks, sessions, and event-driven execution.