A building-permit portal tester pastes a wireframe into a multimodal chat and writes only “what do you see?” Which change best aligns the prompt with a testing goal?
Select an answer to reveal the explanation.
Short Explanation
“What do you see?” is tourist talk, not a test charter. Steer the multimodal prompt toward mismatches with the story or cases for unlabeled controls. Give the model a testing job, not a generic caption request.
Full Explanation
Effective multimodal testing prompts state a concrete testing objective—compare UI to requirements, surface unlabeled controls, suggest cases—rather than open-ended captioning. Generic “what do you see?” yields descriptions that may not advance analysis or design. The syllabus expects applying multimodal capability to a testing goal.