Objective 5.1 · Domain 5 · 14% of the exam
Implement guardrails and safety controls
Guardrails and safety controls in layers: input filtering, system-prompt constraints, output validation and tool-level permissions. The point the exam presses hardest is that a prompt instruction is not a security control. Anything that must hold under adversarial input has to be enforced outside the model, and answers that defend against prompt injection by asking the model not to comply are reliably wrong.
6 questions · answers and explanations shown as you go · free, no sign-up
The rest of domain 5: Governance, Safety & Risk Management
This domain is 14% of a scored form, about 9 of the 63 questions, spread across 5 objectives. Drill the whole domain or pick another objective below.
One objective is a narrow slice. A full-length timed mock is what tells you whether the whole thing holds together.
Sit a timed mock →