19:30 - 20:00
Building an AI that pushes back: lessons from Arete - Jesús García Ramírez (Dataminded)

​LLMs are great at giving answers but surprisingly bad at challenging your thinking. They agree too easily, jump straight to code, and rarely ask the questions a good senior engineer would ask before you commit to a design.

​This talk introduces Arete, an open-source brainstorming agent that stress-tests your decisions before you write a single line of code. Expect a hands-on look at how it works under the hood: sub-agents that keep context clean, the shift from prompt engineering to context engineering, and how a handful of markdown files can turn a generic LLM into something that feels like a real brainstorming partner.

20:00 - 21:00
Build Your Own Agent: Hands-on creating agents— Joris Gillis (TrendMiner)

​The goal of the session is to create agents and skills to use in your daily life. We’ll provide a couple of examples and ideas (or you bring your own). We based on the recently won knowledge about agents, we start building agent skills.

​If you like, feel free to demo your agent at the end of the session.

​Note: bring your own Claude Code & API keys.

21:00 - 22:00
Demo of Agents, Networking, Closing