Skip to content
AI Security

Interview question · Agent, Tool & MCP Security

Your company runs hundreds of AI agents built by different teams. How do you govern the fleet?

One agent is a design review. Four hundred agents is an operations problem: who owns each, what it can touch, how much it can spend, and how you stop one, a class or all of them in minutes.

expertEssentialNewPreparation tags: Microsoft, Amazon, GoogleUpdated Nov 2026

One agent is a design review. Four hundred agents is an operations problem: who owns each, what it can touch, how much it can spend, and how you stop one, a class or all of them in minutes.

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 5 follow-ups like an interviewer would

An audit finds about 400 agents across the company: some built on an internal platform, many using team API keys from repositories, several acting through a shared service account, and three whose builders have left.

  1. What do you do in the first two weeks?
  2. Why is the shared service account the priority?
  3. What about the three orphaned agents?
  4. How would you stop every agent from taking external actions within minutes?
  5. What is the target operating model?

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 trackWhat can an agent gateway or MCP gateway enforce between agents and their tools, and what can it never see?Next in this trackHow would you protect AI agents at runtime: sandboxes, syscall monitoring, tool-call policy and data provenance?Next in this trackYour agent will call other companies' agents over the A2A protocol. What are the security risks, and what does a signed Agent Card prove?
DISCUSSION · 0

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