Human-in-the-loop
Definition
Human-in-the-loop is a design approach where an AI system pauses to get a person's approval before taking consequential actions, keeping a human in control of decisions that carry risk while still letting the AI do the heavy lifting.
For agentic AI that can operate your computer and connected accounts, human-in-the-loop is a core safety mechanism. The agent proposes or prepares an action — sending an email, deleting a file, posting to a system — and waits for you to approve it.
Claude Cowork uses this model prominently, which is part of why it's a comfortable fit for non-technical teams handling real business data. It lets you capture the speed of automation without giving up oversight.