Writing better skills and rules

Your AI agent isn’t “misbehaving”, it’s doing exactly what you told it to do. Great agents and models still fail if the skills, rules and context are wrong. And as AI agents become more autonomous, skills and rules matter more than prompts. When poorly written, they can also inadvertently make it more expensive. In this session you'll learn how small wording choices can prevent hallucinations, control autonomy, goal drift and make agent behavior predictable.

Key takeaways:
* What “skills” and “rules” actually mean in modern AI agent architectures
* Common mistakes teams make when defining agent behavior
* Patterns for writing clear, robust, and composable skills
* Techniques for enforcing boundaries without over‑constraining the model
* How to test, iterate, and evolve rules as agents grow more autonomous

More efficient agents - Learn from my mistakes

Have you also been working, or playing, with AI agents? Had some reasoning and decision making issues? It behaves like it has dementia, and doesn't understand any context?
I've had the exact same problems, and found a few solutions. I haven't made it perfect (yet!) but I can help you not to make the same mistakes. And looking at the fact that more and more vendors are shifting from the 'attract and hook' to a more economically fair 'pay for what you use' model, I'll also help you make your AI agents more cost-efficient. But that's just the cherry on top.