Fix a Vague Prompt
'Make it good', 'be detailed', 'keep it interesting' — vague prompts get vague output. The fix is mechanical: replace every fuzzy word with a checkable instruction.
'Be nice and fix their issue' is a liability in a support prompt. The rewrite adds the control lines support actually needs: boundaries, length, and a next step.
Weak support prompts fail dangerously rather than just blandly: a reply prompt with no boundaries will happily promise refunds, timelines, and exceptions. The rewrite treatment for support prompts is therefore control-first — exclusion rules for what must never be promised, a length cap, a defined ending — with the empathy wording kept but demoted from being the entire prompt. This resource loads the classic 'be nice and fix it' prompt and applies the control-focused rewrite.
Rewrite with Add Output Control
Exclusion, format, and length slots appear; 'try to fix quickly' gets de-hedged; the politeness filler is stripped.
Fill the exclusion line first
What must never be promised — refund before verification, exact timelines, exceptions to policy. This is the line that pays for the rewrite.
Keep the warmth, bounded
'Professional' became a tone line; the reply stays kind — it just stops being legally creative.
Run the rewrite with Add Output Control, which surfaces an exclusion slot — fill it first with what must never be promised: a refund before verification, exact timelines, or exceptions to policy. That's the line that pays for the rewrite; the empathy wording stays but stops being the whole prompt. The Prompt Rewriter reshapes the text; the reply is drafted later in your assistant, and you review it.
No loss of warmth — the rewrite keeps the original empathy wording but demotes "professional" from the entire instruction to a tone line, while adding a length cap and a defined ending that closes on the next step. The reply stays kind; it just stops being legally creative. This is a control-first reshape of one starter prompt, not building a full policy-bounded agent.
'Make it good', 'be detailed', 'keep it interesting' — vague prompts get vague output. The fix is mechanical: replace every fuzzy word with a checkable instruction.
The fastest fix for mediocre AI output is rewriting the prompt: vague words become concrete instructions, hedges become commitments, and missing elements get filled.
Format, length, and exclusions are the three levers that make AI output land in usable shape. A rewrite shows how to retrofit them onto a prompt that has none.
See exactly what changed between v1 and v2 of a prompt — added, removed, and modified instructions, plus whether the revision reduced or introduced risk.
A side-by-side way to decide between two ChatGPT prompt drafts — scored on clarity, specificity, output control, and risk instead of gut feeling.
A set of before-and-after examples showing exactly what prompt cleanup removes — and what it deliberately leaves alone.
Rewrite a weak prompt into a stronger one — vague wording fixed, gaps filled, goal unchanged.