Objective 4.1 · Domain 4 · 16% of the exam
Define evaluation metrics (accuracy, latency, cost, safety, security)
Before you can measure whether something works you have to define what working means, which is what this objective covers: accuracy, latency, cost, safety and security, and the fact that a metric nobody can compute is not a metric. Expect items where several proposed metrics are reasonable and the credited one is the only one both observable in production and tied to the business outcome in the stem.
6 questions · answers and explanations shown as you go · free, no sign-up
The rest of domain 4: Evaluation, Testing & Optimization
This domain is 16% of a scored form, about 10 of the 63 questions, spread across 6 objectives. Drill the whole domain or pick another objective below.
- 4.2Design evaluation datasets and test frameworks using mixed methodologies(5)
- 4.3Conduct A/B testing and iterative improvements(5)
- 4.4Diagnose system issues (prompt failure, hallucinations, model mismatch)(5)
- 4.5Optimize token usage, latency, and cost-performance trade-offs(5)
- 4.6Monitor system performance using logging and observability tools(6)
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 →