Agentic AI Without Intent Is Just Guesswork

Everyone is talking about agentic AI in the NOC. Fewer are asking whether the foundation is ready.Nick Lippis sits down with Damien Garros, founder of OpsMill, to unpack what’s missing from most AI-in-operations conversations: structured intent data.Observability tells you what is happening. But intent defines what should be happening. Without that context, AI systems are left reacting to signals without understanding design, policy, or business impact.Damien explains why enterprises need a version-controlled, extensible source of truth before letting agents interact with production infrastructure. He walks through how intent management, branching workflows, automated validation, and human-in-the-loop governance create a safer path toward autonomous operations.If agentic AI is going to live up to the hype, it won’t be because it replaces operators. It will be because it operates on a foundation of structured, trusted intent.This episode explores what that architecture looks like and what it will take to get there.New episodes of the Built for Trust Podcast come out every Thursday. Subscribe to get notified. See you next week!