An after-school bus-tracker tester has never asked an LLM to cluster anomalies in a messy completion log and does not know how to phrase a good prompt. Which technique should they select first?
Select an answer to reveal the explanation.
Short Explanation
New task, blank playbook—ask the model to help write the prompt itself. That is meta prompting for flexible, first-time work.
Full Explanation
Meta prompting is selected when the task is flexible or novel and the tester needs help crafting an effective prompt. Wrong-domain few-shot examples, CT-AI style SUT testing, or an empty one-shot template do not address that need.