Domain 5 · 14% of the exam · 9 of 63 questions
Governance, Safety & Risk Management
Risk, in the engineering sense. Guardrails that hold under adversarial input, as opposed to polite instructions asking a model to behave. The failure modes a given architecture creates. Where a human belongs in the loop. And the compliance constraints, from data residency to retention to erasure to audit, that decide what the architecture is allowed to be.
every one of the 28 pool items in this domain · explanations as you go · free
The 5 objectives in this domain
A real score report grades each of these separately, so a weakness here is addressable at this level rather than by re-reading the whole domain. Each one has its own drill.
- 5.1Implement guardrails and safety controls6 questions
- 5.2Identify risks, limitations, and failure modes of LLM systems6 questions
- 5.3Apply human-in-the-loop validation strategies5 questions
- 5.4Ensure compliance with regulations (e.g., GDPR, HIPAA, FedRAMP)6 questions
- 5.5Address ethical AI considerations (bias, fairness, transparency)5 questions
The other 6 domains
Drilling one domain tells you about one domain. A full-length timed mock in blueprint proportions is what produces a score you can read.
Sit a timed mock →