Skip to content
AI Security

Interview question · How LLM Systems Work

How does function calling work, and where does an agent actually get its authority?

Trace the proposal to its executor, resource policy and task scope. A valid credential or tool schema does not by itself authorize this particular action.

easyEssentialNewUpdated Nov 2026

Trace the proposal to its executor, resource policy and task scope. A valid credential or tool schema does not by itself authorize this particular action.

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

In an original fictional review, member M7 may manage bookings B7 and B9. The current request concerns only B7, and any change requires confirmation of its exact slot. The scheduling service can queue work.

  1. What if the model proposes changing B9 using a valid delegated credential?
  2. What if B7 is correct but the slot differs from the one the member confirmed?
  3. What if the same scheduling operation is offered through a provider-hosted tool with no local callback?
  4. What if the service accepts the change, the reply times out and the model proposes a second call?
  5. Which records would make this tool call reviewable?

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 are embeddings, and why do they matter for security filters and for data leakage?Next in this trackIf the model is forced to return valid JSON matching a schema, is its output safe to use?Next in this trackHow would you use Google's Secure AI Framework (SAIF) and its risk map to choose controls for a new AI product?
DISCUSSION · 0

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