In this session, you’ll dive into the real-world challenges of taking reinforcement learning from elegant theory to practical, user-facing AI products. We’ll examine where reward functions succeed, how design decisions shape model and product behavior, and how to build AI products.

Hosted by Aditya Challapally, with insights from Stanford professor Emma Brunskill and Boris Cherny (Member of Technical Staff at Anthropic, Creator of Claude Code), this conversation looks beyond algorithms to explore how to build AI products used by millions — revealing the mindsets, design choices, and feedback cultures that turn abstract models into enduring, human-centered systems.