Fact-check and tighten a draft with a prompt built for Claude and Perplexity. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the variables and treat the result as a structured draft, not a final answer.
4.9(16 ratings)620 copies
Updated By Site Admin
52 words · v1.2
Fill in the blanks · 2 variables
Claude promptReplace every highlighted token before sending
<task>
Review the draft below as a careful fact-checker and copy editor. List every factual claim and mark it verified, needs a source, or likely wrong. Then flag unsupported superlatives, vague attributions and logical gaps. Finally produce a tightened version that keeps only claims supported by the provided sources.
Draft:
{draft}
Sources:
{sources}
</task>
Think carefully before answering. Keep any reasoning separate and put the final deliverable inside <answer> tags.
Share what worked, what broke and which model you used. Comments appear after posting and are moderated for spam.
How to use this prompt
1
Open Claude and start a new chat. Paste the prompt exactly as written.
2
Replace each placeholder ({draft}, {sources}) with your own details. Leave the instructions and the output format untouched.
3
Add one concrete example or data point if the model's first answer is vague. Specific input produces specific output.
4
Run it once, then ask for a single revision with a specific critique rather than regenerating from scratch.
5
Review the result. Every factual claim, quote and number in the final draft against a primary source.
Worked example
This is the kind of input the prompt expects and the shape of output it produces. Your result will differ with the model and the details you supply.
Example input
Draft: We are building a tool that helps teams write better briefs.
Sources: Paste the sources or URLs here.
Example output
Here is the draft using the structure you asked for:
**Opening** — a concrete scene or claim that earns the next sentence, with the audience's problem named in plain language.
**Body** — three short sections, each making one point and supporting it with an example rather than an adjective.
**Close** — a specific takeaway and one next step. I cut two filler sentences, kept your facts intact, and flagged one claim that needs a source before publication.
Tips for a better result
Give the model two short samples of writing you like; cadence is easier to match than abstract adjectives.
Ask for a change log when editing. It makes the revision reviewable instead of invisible.
Force a specific audience and a single desired action; 'general readers' produces general writing.
Change one variable at a time and compare the outputs; it is the fastest way to learn what this model responds to.
Common mistakes
Accepting the first draft without checking whether the central claim is actually supported.
Letting the model invent quotes, statistics or case details to make the prose sound authoritative.
Asking for 'engaging' copy without defining the reader, the channel or the length.
Verified Knowledge · FAQ
Questions about this prompt
Practical answers about running the fact-check and tighten a draft prompt.
Related prompts
Same job, a different angle — or the next step in the workflow.
This copy-ready writing prompt helps you turn an interview transcript into an article with fewer blank-page decisions. Paste it into Claude and ChatGPT, fill the variables, and you get a structured first draft you can edit. It is written for repeatable results and tells you what to check before publishing.
This copy-ready writing prompt helps you write a case study with a measurable result with fewer blank-page decisions. Paste it into ChatGPT and Claude, fill the variables, and you get a structured first draft you can edit. It is written for repeatable results and tells you what to check before publishing.
A writing prompt for write a book blurb that sells without spoilers. It gives ChatGPT and Claude a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
ChatGPTClaude
4.7(62)568 copies
SA
Written and reviewed by Site Admin
Author & Platform Administrator
Administrator and lead editor at AIPrompt123, curating high-performance AI prompts, SEO/AEO/GEO strategies, and developer repositories.
Last reviewed 24 January 2026 · version 1.2 · tested on Claude, Perplexity
Comments
Share what worked, what broke and which model you used. Comments appear after posting and are moderated for spam.