Home / Claude Certified Architect – Professional / Objective 4.1

Domain 4: Evaluation, Testing & Optimization · 16% of the exam · Full exam outline

4.1 Define evaluation metrics (accuracy, latency, cost, safety, security)

Practice questions

Question 1easy

A document-translation service has a p95 latency target written into its requirements. Which grading method fits the check that the service stays under that target?

Included in Sample: sample every domain.See plans

Choose an answer to check it. Afterward, select any option to review its explanation.

A judge is for behaviors that need interpretation, such as tone or reasoning quality. Whether a measured time is under a target needs no interpretation, and a judge adds cost and inconsistency for nothing.

Latency p95 is a number compared with a threshold, so a deterministic function settles it in milliseconds at almost no cost. The grading ladder starts with code whenever the behavior allows it.

Human review is the slowest and most expensive rung, kept for high-stakes or novel behavior that code and a judge can't grade. A numeric latency check is neither.

Multi-turn evals score context-keeping and quality across a conversation. They are not a latency measurement, and p95 comes straight from request timings.

Question 2easy

Why do production designs usually set the latency target at p95 instead of at the median?

Included in Master: master every domain.See plans