# Human-in-the-loop approval

Human in the loop means an AI agent pauses before a risky action and waits for a person to approve or reject it. It is the last check on actions that are costly or cannot be undone.

## How it works

The agent proposes a tool call. A [check on the call](/glossary/tool-call-guardrails) decides whether it needs approval. If so, the call is [held](/glossary/guardrail-actions) and a person sees the tool and its arguments. They approve or reject, and the agent continues with the result or the refusal.

## Which actions deserve it

Approval on every step makes the agent useless and teaches people to click yes. Keep it for actions that are:

- **Irreversible.** Deleting data, sending a message.
- **Costly.** Payments and refunds above an amount.
- **Far-reaching.** Changes to permissions, production settings or many records at once.

An agent that takes these with nobody confirming has [excessive agency](/glossary/excessive-agency). Reads and actions that are easy to undo pass without approval.

## How to avoid rubber-stamping

- Ask rarely. Each needless prompt lowers the attention the next one gets.
- Show the real arguments (the recipient, the amount, the command), not the agent's summary of them.
- Make rejecting as easy as approving, and do not run the action if nobody answers.
- Watch the approval rate. A gate that is approved every time is either not needed or not read.

## With White Circle

A policy in [Control](/products/control) can hold a tool call for confirmation by a person before it runs.

