0
Diagnose why a prompt underperforms before rewriting it
⁂auto-checked, 23 hours oldAauraNovice
The prompt
I have a prompt that isn't producing the results I want. Before you rewrite it, diagnose it. Paste the prompt, 2-3 example outputs it produced, and what I actually wanted instead. Then:
1. Classify the failure: is this an instruction-following gap (the prompt asked for X but the model didn't do X), an ambiguity gap (the prompt is genuinely underspecified and the model guessed reasonably), a format gap (content is right but structure is wrong), or a capability gap (the task is genuinely hard for the model regardless of prompt wording).
2. For instruction-following and ambiguity gaps, quote the exact phrase in the prompt responsible, don't just describe it abstractly.
3. Only after diagnosis, propose a fix, and make the fix as small as possible, changing only what the diagnosis points to, not a full rewrite, so I can see what specifically mattered.
4. If it's a capability gap, say so honestly rather than proposing a prompt tweak that won't actually help, and suggest a structural workaround instead (breaking into steps, adding a verification pass).
Prompt: prompt
Example outputs: example_outputs
What I wanted instead: desired_outcome
Where it has been run
| Model | Version | People | Broke | Auto | Last |
|---|---|---|---|---|---|
| Claude | Haiku 4.5 | 0 | 0 | 1/1 | 23 hours ago |
Example output
Diagnosis: ambiguity gap. The prompt says 'summarize the key points' without specifying length or audience, so the model reasonably produced a 400-word summary when you wanted 3 bullet points for an executive.
Responsible phrase: 'summarize the key points' has no length or format constraint attached, that's the specific gap, not a model failure to follow instructions that were actually given.
Minimal fix: change to 'summarize the key points in exactly 3 bullet points, each under 15 words, written for someone who has 30 seconds to read this.' Everything else in the prompt stays the same, this is the only clause responsible for the mismatch.
Not a capability gap: the model clearly can produce concise executive summaries when asked, the outputs you showed me demonstrate good content selection, just wrong length, so no structural workaround is needed here, this is purely a specification fix.
0 comments
Sign in to comment or report what this prompt did for you.
Sign inNo comments yet. Run the prompt and report what you got.