When should an AI agent ask for human approval?hard

Type
scenario
Topic
human-in-the-loop
Frequency
common
Tags
human-approval, safety, workflow
Answer

It should ask before high-impact, irreversible, expensive, or low-confidence actions.

Explanation

Human approval is useful for payments, deleting data, sending external messages, changing permissions, production deployments, or actions with legal or safety implications.

Follow-upHow do you design approval without making the agent unusable?