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