What is agentic AI?
Agentic AI describes systems that pursue a goal across multiple steps — planning, calling tools, observing results and adjusting — instead of producing a single response to a single prompt.
The word covers a wide range, from a loop that calls one function until it succeeds to systems that decompose work and delegate between several models. What the examples share is that the model influences control flow: it decides what happens next.
That is precisely what makes governance hard. When a model decides the sequence, you cannot enumerate the paths in advance, so safety cannot come from predicting behaviour. It has to come from bounding capability — limiting what any step is able to reach, regardless of what the model chose.
Related terms
- AI agent — A system that uses a language model to decide which actions to take, then takes them — as opposed to only producing text.
- Tool calling — The mechanism by which a language model requests that a specific function be run with specific arguments.
- Guardrails — Constraints that bound what an AI system can do, distinct from instructions that ask it to behave.
See it working rather than described.
The product demo runs one agent across three systems and stops at the approval gate.