A2A in 25 Minutes: Building AI agents that communicate
summary
Presents the A2A (Agent-to-Agent) protocol v1.0 — an HTTP + SSE + JSON‑RPC based spec under Linux Foundation stewardship, designed to be extensible for payments and multimodal payloads. Describes a concrete Java prototype built with Quarkus and LangChain4j, including an agent executor with agent-card discovery, an asynchronous task lifecycle (submitted, working, input_required, completed, failed, cancelled, unspecified), and MCP tool integration using Iron Ram as the MCP server. Demonstrates a coordination demo of three agents (Nikoli, IronRam, BruceBanner); code and a blog post are available, and the demo works with a local LangChain4j snapshot.
AI-written summary · about
chapters (6)
related talks
43mA2A in 50 Minutes: Building Interoperable AI Agents
39mA2A in 45 Minutes: Building Interoperable AI Agents
31mA2A in 30 Minutes: Building Communicating AI Agents
10mKeynote: The Agent2Agent (A2A) Protocol
02h 59mStandards and AI Agents: an Overview of MCP, A2A, ADK and More
26mOverview of AI Agent Protocols
34mWhat can A2A do for you and what can you do for it
16mAgent2Agent Protocol and the Future of Agent Collaboration