Building Intelligent Java Apps: Agent Patterns, MCP, and the Future of AI Native Design

Foredragsholder

Daniel Oh

LinkedIn Bluesky X

Java Champion, CNCF Ambassador & TAG DevEX Co-Chair, Microsoft MVP, Developer Advocate, Technical Marketing, Keynote Speaker, Published Author

Om sesjonen

As AI rapidly evolves from model experimentation to production-grade applications, Java developers are increasingly faced with a new paradigm: designing intelligent systems that can reason, interact, and adapt. This talk explores the emerging Java AI application development journey through the lens of agent-based architecture, with a focus on how the Model Context Protocol (MCP) and Agent2Agent (A2A) communication patterns are transforming the way we build intelligent, context-aware services. We’ll walk through the foundational shifts in building AI-native Java applications—moving beyond single-shot prompt-response interactions to multiagent coordination, persistent memory, and tool-augmented reasoning. We’ll also address the critical architectural trade-offs: performance versus flexibility, open source versus vendor-managed inference, local versus remote model deployment, and how to maintain security and observability in agent-based systems.

Passer for

Developer, Architect

Samtidig i programmet

1. 15:40 Hvordan logger kan felle en Nav-direktør Room 1
2. 15:40 The lightweight approach to building internal developer platforms Room 3
3. 15:40 When ORM Becomes OMG: Performance Pitfalls in JPA and Friends Room 4
4. 15:40 Personalizing Your Random Numbers Room 5
5. 15:40 Hvorfor du bør ha timeout i Regex’en din… Room 6
6. 15:40 10 Things I Hate About Java Room 7
7. 15:40 The Bold, the Broken, and the Burned: Hard won lessons in the 7 years of developing Quarkus Room 8
8. 15:55 Når regresjonen blir automatisert: hvor skaper testeren mest verdi? Room 6
9. 16:10 Spec, Test, Doc: One Table, Three Lives Room 6