💻 Shaping AI Agent Behavior: Why UX Must Own AI Evaluation Frameworks

As AI agents move from novelty to core product functionality, UX teams are stepping into an unexpected new responsibility: designing and managing evaluation systems that shape how AI behaves.

This session makes the case for why UX is the right discipline to own AI eval -- and shows what that looks like in practice. We'll cover how to build evaluation frameworks grounded in user behavior rather than model metrics, how to identify failure modes that engineering