Resource
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.
Add Output Control to Any Prompt
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.
Overview
A prompt without output control gets whatever shape the model feels like producing — usually too long, unstructured, and including things you didn't want. Output control is three lines: the format the result should take, how long it should be, and what must stay out. This resource loads a control-free research ask and applies the control-focused rewrite, which retrofits all three lines without touching the question being asked.
How to use this resource
-
Rewrite with Add Output Control
The mode adds Format, Length, and Do-not-include lines as placeholders, and converts 'be thorough' into a coverage list slot.
-
Fill the three lines
A table? 300 words? No vendor marketing claims? Three quick decisions, each one constraining the output where it drifts most.
-
Test the difference
Run the original and the rewrite on the same model — shape consistency is the first thing you'll notice.
Why This Works
- Models default to the most statistically common output shape — control lines override that default
- Exclusion rules are cheaper than post-editing: one line saves the same deletion every run
- Length caps force prioritization, which usually improves content too
Best for
- Prompts whose output you always reformat or trim by hand
- Recurring prompts where consistent shape matters more than prose quality
- Anyone who has never written 'Output:' in a prompt
Not for
- Choosing between output format styles for a finished prompt — the Prompt Formatter renders those
- Diffing controlled vs uncontrolled versions — that's the Prompt Version Diff
Use cases
- Stopping a prompt from producing 2,000 words when you needed 300
- Getting output in a shape you can paste directly into a doc or ticket
- Adding exclusion rules so the output stops including what you keep deleting
FAQ
What exactly does the Add Output Control rewrite add to a prompt?
Three control lines and a coverage slot. The mode inserts Format, Length, and Do-not-include lines as placeholders, and converts vague "be thorough" into a coverage-list slot you fill — on the loaded example that's "Research the best note-taking apps... Be thorough and cover everything important." The prompt-rewriter reshapes the prompt; it doesn't do the research itself.
Does adding output control change the question my prompt is asking?
It retrofits the three lines without touching the ask. The rewrite leaves the underlying question intact and only constrains the shape of the answer: a format like a table, a length cap like 300 words, and exclusions like no vendor marketing claims. You fill those placeholders yourself, then run original and rewrite on the same model to see the shape consistency.
When would I not bother adding these control lines?
When you're picking between finished format styles or diffing versions, not retrofitting control. notFor sends choosing among output format styles to the Prompt Formatter, and diffing controlled versus uncontrolled versions to the Prompt Version Diff. This rewrite is for a prompt that has no Format, Length, or exclusion lines at all — like the example that only says "be thorough."
More resources from Prompt Rewriter
Resource
Rewrite an AI Prompt to Get Better Output
The fastest fix for mediocre AI output is rewriting the prompt: vague words become concrete instructions, hedges become commitments, and missing elements get filled.
Resource
Add Success Criteria to a Prompt
If you can't say what makes the output right, the model can't either. Success criteria turn 'make it good' into a checkable definition of done.
Resources that pair well
Resource
Compare Two Versions of a Prompt
See exactly what changed between v1 and v2 of a prompt — added, removed, and modified instructions, plus whether the revision reduced or introduced risk.
Resource
Compare Two ChatGPT Prompts
A side-by-side way to decide between two ChatGPT prompt drafts — scored on clarity, specificity, output control, and risk instead of gut feeling.
Resource
Prompt Cleanup Examples (Before & After)
A set of before-and-after examples showing exactly what prompt cleanup removes — and what it deliberately leaves alone.
Related tools
Tool
Prompt Rewriter
Rewrite a weak prompt into a stronger one — vague wording fixed, gaps filled, goal unchanged.