Skip to content
AI Security

Interview question · Agent, Tool & MCP Security

Design human approval for agent actions that does not turn into rubber-stamping.

Design the review around a permitted action and an understandable consequence. Evaluate whether people catch relevant changes, while keeping authorization, exact-action binding and alternate delivery paths enforced outside the model.

mediumNewUpdated Nov 2026

Design the review around a permitted action and an understandable consequence. Evaluate whether people catch relevant changes, while keeping authorization, exact-action binding and alternate delivery paths enforced outside the model.

Make your first attempt

What would you say before reading the answer?

  1. 01 State the assumptions your answer depends on.
  2. 02 Explain the mechanism and choose a control.
  3. 03 Name a condition that would change your decision.

The worked answer includes an approach, scoring criteria and follow-up questions. Compare the reasoning with your own.

signing in unlocks more free answers per topic

What if · the follow-ups in this answer

The answer works through 4 follow-ups like an interviewer would

A support assistant prepares replies with attachments. Operators review the sending action, but the team does not know whether the review catches recipient or document mistakes.

  1. What if nearly every proposal is approved?
  2. What if an attachment preview was correct but the stored object changed?
  3. What if reviewers cannot understand why a recipient is flagged?
  4. What evidence would make you keep or change the gate?

Each rung has a nudge, a model answer, the principle that carries over and the weak answer to avoid. Sign in free to open it.

UP NEXT ON YOUR JOURNEY
Next in this trackWhen should an agent act automatically, ask for approval or refuse?Next in this trackHow do you stop injected instructions from persisting through agent memory or long-term state?Next in this trackA prompt injection caused an unauthorized tool call in production. Walk through containment and the fix.
DISCUSSION · 0

No comments yet. Share a correction or a different way to answer it.