← Glossary

Glossary · HITL

Human-in-the-Loop (HITL)

Human-in-the-loop (HITL) AI is a design in which a person reviews, approves, or can override an AI system's consequential actions. A risk gate routes low-risk actions to automatic execution and high-risk ones to a human.


HITL is the most important control for putting agents into workflows where a wrong action is costly or irreversible. The threshold is set by impact, reversibility, and the agent's calibrated confidence.

It differs from 'human-on-the-loop,' where a person supervises but the system acts by default; regulated, high-impact decisions usually call for in-the-loop.

Related terms

Learn more