Special guest session with Kiana Jafari (Executive Director, Stanford Center for AI Safety).

Kiana's research focuses on Human-Agent Teaming and Human-Centered AI, spanning AI evaluation, adversarial testing, and responsible AI governance. She will share insights on the current AI safety research landscape and what it takes to contribute meaningfully to the field, with space for fellows to ask questions directly.

Format: 30-minute Q&A (not recorded), followed by PRISM office hours and peer networking.