NLKUG - Dutch Kotlin User Group

📍 Location:
Maqqie, Coolsingel 135, 3012 AG Rotterdam, 5th floor (Same building like bookshop ‘Donner’)

🕒 Timeline:

• 17:15 – 18:00 Arrival / doors open. 18:00 doors close
• 17:15 – 18:10 Food and drinks 🍕
• 18:10 – 18:15 Opening 🎙️
• 18:15 – 19:05 Best practices for building Kotlin applications with AI - Luc Klaassen 💻
• 19:05 – 19:20 Break
• 19:20 – 20:05 Eval-Driven Development: The Fine Line Between Agentic Success and Failure - demonstrated on JVM AI frameworks (Spring-AI, LangChain4j, Koog) - Urs Peter 💻
• 20:05 Chats & Drinks 👥

***

Talk 1: Best practices for building Kotlin applications with AI

Abstract:
Everyone and their mother is talking about AI-augmented software development, but what does it actually look like in practice? Three months ago, I was a skeptic. Then I built an electronic patient dossier from scratch in Kotlin with AI as my co-pilot, and went from skeptic to evangelist. In this talk, I’ll walk you through my evolving workflow, the tools I tried (and dropped), and the mindset shift that made it click. You’ll leave with a practical approach you can apply to your own Kotlin projects, whether you’re doubtful, curious, or ready to dive in.

Bio:
Luc Klaassen is Head of Engineering at Maqqie, a Dutch HR tech platform that’s using technology to innovate the labour market by facilitating new, compliant ways of working. He’s been building software since 2013 and has spent the last few years figuring out how to make engineering teams thrive. When he’s not wrangling codebases, he’s probably arguing with an AI about how to write them.

***

Talk 2: Eval-Driven Development: The Fine Line Between Agentic Success and Failure - demonstrated on JVM AI frameworks (Spring-AI, LangChain4j, Koog)

Abstract:
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.

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

Bio:
Urs is a seasoned software engineer, solution architect, conference speaker, and trainer with over 20 years of experience building resilient, scalable, and mission-critical systems, primarily in 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 trainings on Microservices and Event-Driven Architectures.

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

***

RSVP Now!
Don't forget to RSVP to secure your seat—spots are limited! We can't wait to see you there and discuss the future of Kotlin and software architecture.

📍 Location: Xebia Netherlands - Amsterdam - Wibautstraat

Join us on an evening filled with tasty food, refreshing drinks, and insightful Kotlin discussions.
Make sure to press the RSVP button!

---

🕒 Timeline:
• 17:45 - Doors open, food and drinks 🍕
• 18:30 - Opening 💻
• 18:40 - Making @Transactional Play Nice with Kotlin Rich Errors and Either - Tjalling Ran
• 19:30 - Quick break 🚽
• 19:40 - How to supercharge your knowledge base with Retrieval Augmented Generation (RAG) - Jamie Craane 💻
• 20:25 - Closing 💻
• 20:30 - Chats & Drinks 👥

---

Title: Making @Transactional Play Nice with Kotlin Rich Errors and Either

@Transactional rolls back on exceptions — but what if your error is a value? Functional error handling patterns like Arrow’s Either.Left or Kotlin’s upcoming Rich Errors let you model errors as return values instead of throwing exceptions, making failure explicit and strongly typed in your function signatures. The downside: your @Transactional would commit even on an error. This talk shows how to solve that with Spring AOP, so you can adopt functional error handling in an existing Spring Boot codebase without breaking your @Transactional behavior.

Bio:
Tjalling Ran is a back-end developer at Maqqie, where he works on public APIs, backoffice tooling, and CLA compliance, bridging technical implementation and technical and non-technical stakeholders alike. He has a passion for writing expressive and unambiguous code by leveraging the type system and naming things well. His day-to-day stack is Kotlin with Spring, OpenAPI, and JPA. Earlier in his career he worked on code generators with Xtend, a language that felt refreshingly modern compared to Java at the time, which made Kotlin a natural fit.

Title: How to supercharge your knowledge base with Retrieval Augmented Generation (RAG)

Abstract
Your notes, documents, and images contain a wealth of knowledge — but finding the right piece at the right moment can be surprisingly hard. What if you could search your personal knowledge base the same way you talk to an AI assistant?

In this talk, we’ll explore how Retrieval-Augmented Generation (RAG) can supercharge your personal knowledge base. You’ll learn how vector embeddings are created, how they are stored, and how they power an end-to-end RAG retrieval workflow. Along the way, we’ll demystify what embeddings actually are and why they work so well for semantic search.

But we won’t stop at text. We’ll also integrate image embeddings into the workflow, enabling you to query your own photos and screenshots using natural language.

Finally, we’ll tackle an often overlooked challenge: protecting sensitive information. You’ll see practical techniques for preventing confidential data from being sent to external embedding providers.

By the end of the session, you’ll understand how to build a powerful, privacy-aware RAG system that turns your personal data into an AI-searchable knowledge engine.

Bio:
With over 20 years of IT experience, Jamie Craane designs and develops software for a wide range of organizations, from large enterprises to startups and SaaS services. Working for Moxie-IT, Jamie focuses on the entire value chain: from architecture and technology to software development, deployment and management, and improving the performance of development teams. Adding value and providing insight for everyone involved are central to his approach.

Fast, secure, and automated delivery are essential to his approach. Jamie combines innovation with proven technologies and closely follows developments in Artificial Intelligence. He doesn’t shy away from challenges and enjoys sharing his knowledge with teams and the community.

---

RSVP Now!
Don't forget to RSVP to secure your seat—spots are limited! We can't wait to see you there and discuss the future of Kotlin and software architecture.