Back to the AI glossary Workflows
Human in the loop
People check and control AI decisions at critical points.
Explanation
Human-in-the-loop means that a human is involved in important or uncertain decisions. The AI works autonomously, but human approval is obtained at defined points.
How it works
The AI agent carries out routine tasks independently. Cases that exceed predefined thresholds (e.g. cost > $500 or confidence < 80%) are escalated to a human.
Example
A customer service agent answers standard questions automatically, but forwards complaints or special cases to a human agent.
Why it matters
HITL is the key to trustworthy AI in business use – automation with a safety net.