Skip to content
AI Security

Interview question · Agent, Tool & MCP Security

A long-running agent works on a task for hours. When must it stop and re-confirm with the user, and how do you bound it in the meantime?

Compare each proposed action with the task’s existing grant, current policy and remaining budget. Continue within that scope; stop when authority expires or the action changes materially, and preserve the state of work already dispatched.

mediumNewUpdated Nov 2026

Compare each proposed action with the task’s existing grant, current policy and remaining budget. Continue within that scope; stop when authority expires or the action changes materially, and preserve the state of work already dispatched.

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.

10 answers per topic instead of 5, plus saved progress and bookmarks · costs nothingor unlock all 529 remaining answers · $25

Every worked answer in all 17 topics, every lesson in every course, the full concept curriculum, the complete practice-test bank, and the downloadable security field guides.

6 months · One payment · No auto-renewal

What if · the follow-ups in this answer

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

Alder’s assistant may compare suppliers and prepare a purchase proposal. Later, a user approves one bounded order. The task can spawn workers and may be stopped while work is queued.

  1. What if another approved catalogue query is needed before the grant expires?
  2. What if a worker reaches the cap while another purchase is unresolved?
  3. What if the user cancels after dispatch?
  4. How would you verify that the task envelope survives resume?

Each rung has a nudge, a model answer, the principle that carries over and the weak answer to avoid. Premium opens every answer and ladder.

UP NEXT ON YOUR JOURNEY
Next in this trackCan the same model that proposes an agent's action also approve it, or act as its guardrail? What should decide instead?Next in this trackWhat evidence supports a claim that a compromised agent cannot retrieve production secrets?Next in this trackAn agent keeps shared memory across users. How do you stop one user, or a slow campaign, from poisoning it?
DISCUSSION · 0

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