Reference card· Module 4 — Diagnosis· Prints on one page

When It Gives You Garbage

Bad output is not one thing and the repairs are not interchangeable. Name the class, then apply its repair.

Read the output in front of you against the middle column. The row you land on tells you what to change. Rerolling is not on the list, and neither is giving up.

The six classes

FailureLooks likeRepairMechanism
Missing informationConfidently answers a different situation than yoursSupply what it couldn’t haveLesson 2
Under-specifiedValid, competent, not what you wantedAdd constraints or an exampleLesson 3
FabricationSpecifics that are wrong — numbers, names, citationsGround it, or scope it to a sourceLesson 1
Wrong shapeRight content, wrong length, format or registerSpecify format, or show oneLesson 3
Lost the threadContradicts itself, drops earlier instructionsFresh chat, restated briefLesson 2
Insufficiently decomposedDoes all of it, shallowlyBreak into steps; give it room to workLesson 1
The pair people genuinely confuse

Under-specified and wrong shape both come back competent and unwanted, which is why they blur. The test is not what you’d change — it’s what you’d keep.

Would you keep the substance and repackage it? Wrong shape — a container problem, and the content is already right. Would you throw the substance out and start again? Under-specified — a content problem, and no reformatting reaches it. The repairs overlap (one good example can fix either), which is why the classes keep blurring and why keep-or-discard is the question that stays sharp.

Before you rewrite anything

The reroll trap. Regenerating an unchanged prompt draws again from the same place. If the prompt is the problem, so is every reroll. Change something, or stop running it.

Ask it to diagnose itself — then treat the answer as a hypothesis. “What in my prompt led you to produce that?” is a useful move that almost nobody makes. What comes back is a hypothesis about your prompt, not a log of what happened. Good for generating leads. Not evidence. Test it before acting on it.

The seventh option: settings, not specification. A shallow answer to a genuinely hard task is sometimes fixed by letting Claude work harder — thinking on, more effort — rather than by rewriting anything. Check your specification first. Reaching for the dial before checking the spec is the exact habit this card exists to prevent, and it is much more often a spec problem.

The one case where the answer is stop

If the answer turns on a fact that is private and appears in no source you can supply, nothing on this card reaches it. That is not a hard prompt, it is the wrong tool, and the correct move is to stop. A diagnostic that can never return stop is a motivational poster. You want calibrated persistence, not unlimited persistence.