AISG practice · Module 6

Secure AI Architecture, Guardrails & Agentic IAM — 10 questions. Choose the BEST answer.

You can answer as a guest, but you'll need a free account to see your score and save it. Sign up · Sign in
Question 1 Question 1 · M6
Streaming model output token by token to users primarily complicates which control?
Question 2 Question 2 · M6
What is context boundary validation?
Question 3 Question 3 · M6
Which restriction is MOST important for a sandbox where an agent runs code it wrote?
Question 4 Question 4 · M6
Which mechanism lets workloads authenticate without stored long-lived secrets?
Question 5 Question 5 · M6
Which pattern keeps a privileged planning model from being exposed to injected content?
Question 6 Question 6 · M6
A bank must keep KYC data in India, needs auditable citations and has a small ML-ops team. Which deployment fits BEST?
Question 7 Question 7 · M6
Which authentication method is MOST appropriate for administrators of AI platforms?
Question 8 Question 8 · M6
Why should autoscaling for inference have a ceiling?
Question 9 Question 9 · M6
Which test type checks behaviour beyond expected limits, such as exhausting context windows and GPUs?
Question 10 Question 10 · M6
Red-team results: injected emails convinced the model to propose unauthorised refunds 6% of the time, but none executed. What does this show?