JavaOne 2026

JavaOne 2026 Session

Duke in front of a whiteboard

Reliable AI agents using Domain Modeling with Koog in Java

Summary

AI agents are rapidly moving from prototypes to production, yet most still rely on naive textual prompts, resulting in fragile systems. At JetBrains, we built Koog, the most advanced framework for developing AI agents on the JVM. Initially built for Kotlin, it now features a new idiomatic Java API! In this talk, I'll show how Domain Modeling, Java's type system, and Koog make AI agents more reliable.

You'll learn:

Why domain modeling outperforms naive prompting

How to easily build reliable AI agents in Java

JetBrains' lessons from building real-world AI agents on the JVM

How to architect scalable, enterprise-ready AI systems with Koog

JVM is the best platform to build enterprise-grade AI agents. Why? Join this talk to learn!

Profile

Type: Learning Session (50 min)

Track: Machine Learning and Artificial Intelligence

Audience Level: Intermediate

Speaker: Vadim Briliantov

Session: Tuesday, March 17th at 2:00 PM in Room 104