Skip to content
AI Security

Interview question · LLM Application Security

Architect the guardrail pipeline for a customer-facing financial assistant, including how you guard streamed responses.

The regulator does not care which classifier you used. The design that scores puts authorisation and commitments in code, uses classifiers where they are good, and decides in advance what happens when a streamed answer goes wrong halfway.

hardNewPreparation tags: JPMorgan Chase, Microsoft, GoogleUpdated Nov 2026

The regulator does not care which classifier you used. The design that scores puts authorisation and commitments in code, uses classifiers where they are good, and decides in advance what happens when a streamed answer goes wrong halfway.

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 bank's assistant answers questions about accounts and can initiate transfers between the customer's own accounts and to saved payees.

  1. What if the model alone decides whether a transfer is allowed?
  2. Where do input and output filters fit?
  3. What if the assistant reads a statement containing injected text?
  4. What should the confirmation step look like?
  5. What regulatory expectations apply?
  6. What pipeline would you design?

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 trackPractical coding: implement a rate limiter for an LLM API that budgets tokens, not requests, then make it work across many gateway nodes.Next in this trackYour CISO wants to buy an AI security platform. How do you evaluate one, module by module, and what will it never do for you?Next in this trackHow do AI providers detect and disrupt attackers using their models, and how would you build that capability for your own AI platform?
DISCUSSION · 0

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