A municipal eel-trap permit shop hires only “prompt people” who lack fishing-rule and testing knowledge to judge generated cases and defect analyses. What expertise combination do testers need?
Select an answer to reveal the explanation.
Short Explanation
Prompt craft without knowing the rules of the fishery—or how to test—is like a fluent tour guide who cannot read the tide chart. Testers blend domain and test expertise with AI skills to judge what GenAI produces. Hybrid judgment beats prompt-only hiring.
Full Explanation
Effective GenAI-assisted testing requires combining domain knowledge and testing expertise with AI skills when evaluating generated cases, defect analyses, or test data. A municipal eel-trap permit shop that hires only “prompt people” who lack fishing-rule and testing knowledge cannot reliably judge generated cases and defect analyses: prompt fluency alone cannot spot domain-wrong oracles. Prompt fluency alone without domain or test judgment is insufficient. Only vendor tool certification with no domain background misses civic rule expertise. Only CT-AI SUT red-team skills without classic test design miss GenAI-for-testing judgment on generated testware. Exam caveat: hybrid domain-plus-test-plus-AI skill is required; vendor badges or SUT-only skills are not substitutes. Operational check: staff eel-trap GenAI review with people who know fishing-permit rules and test design as well as how to prompt and critique model output. Keep civic testware subject to the same review discipline you would apply to human-authored packs. On the written exam, prefer syllabus terminology over vendor marketing language or lab choreography. Treat fluent output as a draft until organizational quality gates and data-handling rules are satisfied.