Where should AI agents need human approval?
AI agent builders need to decide which actions an agent may take without a human check. High-risk actions include deploying code, refunding customers, sending emails, deleting data, and running .
The main choices are to require approval, use fixed policies, or rely on the model’s own judgment. As agents become more capable, this becomes a larger design problem.
Key points
- need clear limits on what they can do alone.
- Code , refunds, emails, data deletion, and work are high-risk actions.
- Teams can require approval, set policies, or trust the model’s judgment.
- Stronger agents make the more important.