CJ Avilla

Agents running generated code, multi-tenant platforms, and untrusted workloads all need strong isolation, but each traditional compute option forces a tradeoff. VMs isolate well but start slowly.

Agents can now work for hours, but most of us still approve every step or skip the prompts and hope. This session asks where we are on the curve for trusting agents, and what has to be true before we hand them much more work. It draws on decades of trust research, from how societies learned to trust strangers to how pilots learned to trust the autopilot.