JUG Noord

📍 Location: Kempkensberg 12, Groningen

🚨 Important: Signing up and valid identification are mandatory for entry. If the name on your Meetup profile does not match your ID, please contact Martijn (organizer) with your full name.

🇬🇧 How to build your own fun and absurd pair programmer by Alexander Chatzizacharias (JDriven)
This session explores building a playful, sarcastic AI assistant using LLMs, Spring Boot, and vector databases. Attendees will learn about Retrieval-Augmented Generation, multi-vector search, and Model Context Protocol integrations, gaining practical insights for creating engaging agentic workflows and unconventional, personality-rich digital assistants.

🇬🇧 Eval-Driven Development: The Fine Line Between Agentic Success and Failure - demonstrated on JVM AI frameworks (Spring-AI, LangChain4j, Koog) by Urs Peter (Xebia)
Agentic systems unlock capabilities that traditional “deterministic” applications simply can’t deliver. But there’s a catch: their probabilistic nature introduces real and often unexpected risks—hallucinations, context drift, prompt degradation, and multi-step workflows that evolve in surprising ways. And you definitely don’t want to discover those in production.

The good news: there is a remedy. We can borrow the most reliable practice from deterministic software—test-driven development—and adapt it to the agentic world. The result is Eval-Driven Development (EDD): a systematic, engineering-first approach to bringing reliability into inherently probabilistic systems.

In this talk, we explore Eval-Driven Agentic Development and how it can transform your agents from unpredictable to reliable. We’ll dive into the techniques, tools, and patterns needed to make evaluation a first-class citizen of your development process—demonstrating all of these in a real-world application built with state-of-the-art JVM AI frameworks, like Spring-AI, Langchain4j, Koog, etc.

Along the way, you will learn how to:

• Test agents at multiple layers—schema validation, tool correctness, decision flows, and end-to-end goal completion
• Gather metrics that serve as the backbone of meaningful evaluations
• Turn complex agent traces into actionable insight rather than noise
• Use LLMs to generate test cases, assertions, synthetic data, and act as “judges” in your eval pipeline
• Detect regressions when prompts, models, or data change
• Build a continuous evaluation loop with real-world data—so your agents improve over time instead of quietly degrading

Evaluation-Driven Development is the only path forward for reliable, smart next-generation applications. Let's learn how to walk it - together!

About the speakers
Alexander Chatzizacharias, a 35-year-old Software Engineer at JDriven, holds dual Dutch and Greek nationality. He earned his master’s degree in Game Studies from the University of Amsterdam, where he discovered his passion for gamification and software engineering. Alexander aims to bridge the gap between game development and software engineering, believing that both industries have much to learn from each other. He is dedicated to integrating technologies and methodologies from both fields. Additionally, he enjoys experimenting with new technologies and cutting-edge sdk's.

Urs Peter is a seasoned software engineer, solution architect, conference speaker, and trainer with over 20 years of experience in building resilient, scalable, and mission-critical systems, mostly involving Kotlin, Scala, and Java.

Besides his job as a consultant, he is also a passionate trainer and author of a wide range of courses, including language courses for Kotlin and Scala, generative AI courses for the JVM platform, as well as architectural training sessions such as Microservices and Event-Driven Architectures.

As a people person by nature, he loves to share knowledge and inspire and get inspired by peers at meetups and conferences. Urs is a JetBrains certified Kotlin trainer.