Lutris Labs.ai
AI consulting
AI Training
Hands-on training for development and data teams. Your own codebase, your own tickets, and the tools your developers will actually use: Claude Code, Cursor, Codex, and GitHub Copilot. Taught by someone who ships with them every day.
Three trainings, each one run inside your own codebase, on your own tickets. Pick the one that matches where your team is now.
Your developers spend the day in Claude Code, Cursor, Codex, and GitHub Copilot, working real tickets in their own repository. We cover prompting that survives a large codebase, when to hand an agent a whole task and when to keep it on a short leash, and the review discipline that makes AI-written code safe to merge. No toy projects.
A demo agent takes an afternoon. One you can leave running against real customers takes tool design, guardrails, evals, and monitoring. We build one end to end: what a tool should and should not be allowed to do, how to write evals that catch a regression before your users do, and what to log so you can explain any answer the agent gave last Tuesday.
Retrieval is what breaks most “chat with your documents” projects, long before the model does. We build a RAG pipeline on your own documents: chunking, embeddings, reranking, and the evaluation that tells you whether an answer is grounded or invented. Then GraphRAG, for questions that depend on how documents relate to each other.
A working session, not a lecture. Your team is in the editor from the first hour.
Claude Code, Cursor, Codex, and GitHub Copilot: what each one is good at, the models underneath, and where they fall over.
Exercises in your own codebase, on real tickets from your backlog.
Reviewing, testing, and securing AI-written code.
Working agreements your team keeps after the training ends.
One focused session with your development team, in your own environment.
Small enough that every developer codes along and gets direct feedback.
Depends on group size and scope. One call is enough for a concrete quote.
My name is Guus Bobeldijk. Years of doing exactly this work: as a data-analytics consultant at PwC across banking, telecom, and public organisations, and hands-on as a data scientist and AI engineer. I built and launched AI products solo (RAG, GraphRAG, the lot), so I know first-hand what ships and what only demos well. And because I teach at Nyenrode Business University and train teams in AI for a living, I can sit with your engineers and your director in the same hour and make each understand the other.
Trusted by
Book a short introductory call. We'll discuss your team, your stack, and whether this training fits.
No obligation, practical, and no sales presentation.