AI in Java: We've Built a Server-Side Enterprise Google A2A for Jakarta EE Devs.
summary
An enterprise Jakarta EE A2A server implements Google Agent2Agent using Jakarta EE10+, JDK25, and runs on Eclipse GlassFish/Omnifish with minimal dependencies; it exposes agent cards, supports langchain4j CDI agents, and deploys as a normal Jakarta app. Communication uses JSON-RPC payloads, optional SSE streaming, and a task lifecycle that returns artifacts (demo content-writer agent starts, submits a task, streams a completed artifact). Extended agent cards require authentication, runtimes support JSON-RPC or REST (pick one), and client/server builders and executors are provided so the example actually works end-to-end.
AI-written summary · about
chapters (6)
- 0:00Introduction and speaker intro
- 4:10What is A2A protocol
- 10:06How A2A agents work
- 21:18A2A in Jakarta EE
- 35:30Demo of A2A server and client
- 52:38Summary and Q&A
related talks
43mA2A in 50 Minutes: Building Interoperable AI Agents
31mA2A in 30 Minutes: Building Communicating AI Agents
27mA2A in 25 Minutes: Building AI agents that communicate
46mAI Tools for Jakarta EE
24mBuilding Agentic Applications with Spring AI
53mUnleash the Power of AI Agents with Java Building Intelligent Application
58mJakarta EE Meets AI
20mAI Solutions with Spring AI 2.0 and Java