Trust in Multi-Agent Architectures

Multi-agent architectures are rapidly reshaping how agentic AI systems work. When data moves between agents, there is an implicit trust established. We’ll explore what that means, what trust actually looks like in multi-agent architectures, and how we can lean on decades of security research and best practices to mitigate potential issues that stem from that implicit trust.

Join us for the next AI Group!

5:30 - 6:00 - Socializing/Networking
6:00 - Speaker begins