Glossary

Approval mode

Also called: human in the loop, human-in-the-loop

Definition

Approval mode is a setting where an agent pauses before a specified action and waits for a human to sign off before carrying it out.

In practice

It is the practical middle ground between watching an agent constantly and not watching it at all. The agent runs unattended by default and stops only at the steps you nominated, which lets you separate what is reversible from what is not. Gate on reversibility rather than importance: an agent doing important reading unattended is fine, an agent doing trivial deleting unattended is not. The usual candidates are sending external email, spending money, deleting, and posting publicly. Requiring approval everywhere defeats the purpose, since an agent that needs a click per step is a slower version of doing it yourself.

Read more

Nearby terms

All 18 terms

Run agents without the homework

Qoren runs OpenClaw, Hermes, and Codex agents in managed environments, with the restarts, secrets, schedules, and spend caps handled for you.

Start free trial