Run a five point audit on an AI draft
Audits an AI-generated draft for hallucinations, tone inconsistencies, and unsupported claims before you hit send.
Prompt
You are a meticulous content editor and fact-checker.
Review the draft provided below against five strict criteria: unverified factual claims, dates or numbers, tone shifts, vague fluff phrases, and missing context.
- Quote the specific offending text for every issue found.
- Explain why the item is problematic.
- Offer a ready-to-use replacement sentence or note what to verify manually.
Output format:
Use five numbered sections matching the criteria. If a section has no issues, mark it "Clear". End with a "Safe to Send?" verdict (Yes/No/Needs Revision).
My draft is below:Example output
Paste your generated draft directly underneath this prompt in ChatGPT, Claude or Gemini. If the verdict says 'Needs Revision', ask the model to produce a fully corrected draft incorporating all recommendations.
Make it repeatable
Keep using this prompt without pasting it in every time.
Prompt details
- By
- Prompts-GPT editors
- Published
Did this prompt work?
Keep exploring
More like this
Audit drafts for confidently phrased factual hallucinations
Scans generated text for high-risk assertions, unverified statistics, and false certainty. Use it before publishing AI-written reports or summaries.
Audit AI text for hidden bias and one-sided framing
Detect subtle assumptions, suppressed counterarguments, and one-sided framing in an existing AI-generated answer.
Spot formatting regressions across model updates
Audit outputs from upgraded AI models against your strict formatting rules. Use it to catch broken JSON, lost headers, or leaking chain-of-thought tokens.
Draft content with an internal self critique step
Produce higher quality drafts by forcing the model to critique its work against your constraints before printing the final version.
Create an AI writing cliche blacklist
Generate a practical team reference sheet identifying predictable AI jargon, overused sentence patterns, and fresh human alternatives.
Split documented facts from AI interpretation and speculation
Separates verifiable source facts from analytical assumptions and extrapolations. Use it to keep executive memos, reports, and summaries strictly accountable.