Every Agent is Rogue by Default [RSVP REQUIRED]

This event requires an RSVP; to attend, submit form here

An agent that reads production secrets it was never scoped to touch. Another that runs overnight and bills $800 in API calls. These aren't hypothetical breach scenarios. They're the natural consequence of deploying AI without an identity layer. This session breaks down how identity becomes the control plane for AI agents: token vaulting, fine-grained authorization, human-in-the-loop approval, and real-time threat detection. We'll walk through a production sales agent end-to-end so you leave with a concrete picture of what "secured by design" actually looks like.