Lutske de Leeuw is a Software Engineer at Craftsmen and co-organizer of JUG Noord and ApeldoornJUG. A Java developer at heart and full-stack by trade. She loves to share knowledge through storytelling, often featuring animals like cats or llamas to make complex topics more relatable. She regularly speaks across Europe about AI and software craftsmanship. Lutske studied Computer Science and completed a Deep Learning specialization, and she enjoys experimenting with AI to bridge the gap between innovation and everyday development. Passionate about Devoxx4Kids and other knowledge-sharing initiatives, she believes learning should always be fun and accessible for everyone.
Is your shiny new AI feature already tangled in a plate of spaghetti code, with helper classes sticking out like rogue meatballs and surprise side effects splattering everywhere? In this session, we follow a short story of a small chatbot named Leo that grows into a full‑blown platform, showing how careless choices turn neat experiments into costly traps. We then flip the script and refactor the same product into a scalable, enterprise-ready architecture using Clean Architecture. Drawing clear lines between domain, application, and infrastructure so that models can change without breaking everything else. By the end, you will see that good structure is not a luxury, but the only way to keep your AI moving fast without regrets.
What we cover
- The hidden cost of “just ship it” when models, data pipelines, and prompts keep changing
- Where Clean Architecture fits in a modern AI stack: domain, ports, adapters, and model gateways
- Demo: Route simple queries to a local LLM and advanced ones to the cloud, in minutes, not days.
- Pitfalls we hit in real projects and the patterns that saved us
What you will learn
- How to spot early signs of architectural decay in AI projects
- A step‑by‑step guide to isolating AI concerns from business rules
- Practical tips for introducing structure into an existing “AI spaghetti” codebase
Searching for speaker images...