Skip to content
AI Security

Interview question · LLM Application Security

Design the security of a Copilot-style coding assistant API used by thousands of companies.

The service receives customers' source code all day. The scored answer protects that code across tenants, keeps secrets out of prompts and logs, and treats suggestions as untrusted output.

hardNewPreparation tags: Microsoft, Google, AmazonUpdated Nov 2026

The service receives customers' source code all day. The scored answer protects that code across tenants, keeps secrets out of prompts and logs, and treats suggestions as untrusted output.

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 6 follow-ups like an interviewer would

A company exposes an API that lets customers send prompts to its internal assistant, which has tool access to customer account data.

  1. What if API callers can choose which tools the model uses?
  2. What if one customer's request includes data that ends up in another's context?
  3. How should tool calls be authorised?
  4. What if callers use the API to generate abuse at scale?
  5. What if a customer's API key leaks?
  6. What would the API design include?

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 trackDesign an internal LLM gateway that every team's AI features must go through. What does it enforce?Next in this trackHow do you stop employees leaking company data into public AI tools?Next in this trackWhat extra controls apply when an AI assistant handles payment card or health data?
DISCUSSION · 0

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