Anyone can get a fluent paragraph. Fluency is the default now. The scarce move is knowing whether the paragraph is true, useful, and worth sending to a human who pays.
Evaluation is not a vibe. It is a list you write before you generate: claims that must be true, tone that must not slip, numbers that must match the brief, a “kill” condition if the output is generic.
If you cannot say how you will reject the answer, you were never doing the work. You were collecting text.
That check is the Stress step of the Loop. Starting prompts so you reach something worth stressing: Prompt Secrets.