05 June 2025 —
16:50 to
17:20 on
Future of Engineering Stage
As LLMs reshape software development, Java/Kotlin developers face unique challenges when integrating these powerful AI models into production applications. How do you maintain reliability, control costs, and ensure testability while leveraging the full potential of AI?
This talk demonstrates how to build AI-powered applications using LangChain4j with Kotlin. We'll explore how Kotlin's expressive syntax and coroutines transform complex asynchronous Java code into clean, maintainable code on Kotlin. Through a practical game demo, you'll see LangChain4j's capabilities for RAG, function calling, Model Context Protocol, and request moderation. The heart of this presentation addresses the testing challenge: how do you verify AI integrations without unpredictable responses, high costs, or rate limits? I'll introduce AI-Mocks, a testing library that enables deterministic, fast, and reliable tests for LLM integrations. You'll learn practical patterns for mocking LLMs, handling streaming responses, and simulating failures. Who is this talk for? JVM developers looking to integrate LLMs into production systems, teams struggling with testing AI components, and engineers seeking practical strategies for maintaining reliability in AI applications. Attendees will leave with code examples and approaches they can immediately apply to their projects.
Read More...
By
Konstantin Pavlov [Staff Software Engineer — Twilio Inc.]