Skip to content
AI Security

Interview question · LLM Application Security

How should prompts, traces and logs in an LLM application handle personal data and secrets?

LLM observability quietly becomes the largest copy of customer data in the company. The scored answer minimises what is captured, separates what must be kept, and treats trace stores as production data.

mediumNewPreparation tags: Microsoft, Salesforce, DatabricksUpdated Nov 2026

LLM observability quietly becomes the largest copy of customer data in the company. The scored answer minimises what is captured, separates what must be kept, and treats trace stores as production data.

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

An LLM app stores every prompt and response in its logging system for debugging, and logs are shipped to a third-party observability tool.

  1. What risk does this create?
  2. What if you redact personal data before logging?
  3. What if engineers need full prompts to debug quality issues?
  4. How long should full prompts be kept?
  5. What about the third-party observability tool?
  6. What logging policy would you set?

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 trackShould LLM guardrails fail open or closed, and how do you handle their latency and cost?Next in this trackHow do you evaluate guardrails honestly, without optimising only for pass rate?Next in this trackCan prompt caching or response caching in an LLM application leak data between users?
DISCUSSION · 0

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