AI Fact-Check Report
Instant download · 30-day money-back guarantee. Pay once, keep forever — no subscription. Refund policy
Evaluate claims systematically — evidence assessment, confidence ratings, verdicts, and primary-source guidance.
- Per claim: decomposition, evidence assessment, confidence rating, verdict
- Seven verdicts including MISLEADING, CONTESTED & NEEDS PRIMARY SOURCE
- I-cannot-verify is an honest output — no false confidence
- Flags context that changes the meaning of a statistic
- Tunable for political, medical, statistical & historical claims
For journalists, researchers & editorial teamsOne published error costs your credibility — this catches it first.
Learning & Research Prompts
Evaluate claims systematically — evidence assessment, confidence ratings, verdicts, and primary source guidance.
This AI fact checker prompt evaluates specific claims, statistics, and assertions against available evidence — producing structured fact-check reports with claim decomposition, evidence assessment, confidence ratings (HIGH / MEDIUM / LOW / CANNOT ASSESS), verdict, and specific guidance on what still requires primary source verification. Paste into Claude, ChatGPT, or any AI chat, list the claims, and get a structured research guide for verification.
Most fact check AI tools issue confident verdicts where the evidence is ambiguous. This prompt doesn't — "I cannot verify" is an honest and valuable output, and every claim requiring current data is explicitly flagged NEEDS PRIMARY SOURCE VERIFICATION. Complex claims are decomposed into components, and context that changes the meaning of a statistic is always called out. Works with Claude, ChatGPT, or any AI chat model.
Important: Primary source verification required for all claims before publishing. AI cannot access real-time data — this prompt structures and guides the verification process, it does not replace it.
What you get
- One production-ready AI fact checker prompt (700+ words)
- Structured fact-check per claim — decomposition, evidence assessment, confidence rating, verdict, source guidance
- Seven verdict categories including MISLEADING, CONTESTED, and NEEDS PRIMARY SOURCE VERIFICATION
- Summary table across all claims — verdict, confidence, and action needed at a glance
- Customisation for political claims, medical and scientific, statistical, historical, and content audits
Built for
ai-fact-check-report-prompt.txt · Works with Claude, ChatGPT & more · Instant use
Four steps. Any AI chat.
- 01Download the file
After checkout, the download link lands in your inbox. Save the file anywhere on your device.
- 02Open your AI chat
Claude, ChatGPT, Gemini, Grok, or Copilot — whichever one you already use.
- 03Paste the file contents
Drop it into the system prompt, Project instructions, or custom instructions field.
- 04Start working
Your AI is now configured as a specialist. Ask it anything inside its domain.
No technical knowledge required. No subscription. Pay once, keep forever.
Works with every major AI chat.
Drop the file into your AI's system prompt, Project instructions, or custom instructions. No setup. No code. No vendor lock-in.
- Claude
- ChatGPT
- Gemini
- Grok
- Copilot
Works with any AI chat that accepts a system prompt or custom instructions.
Ready to specialise your AI?
One drop-in file. Pay once, keep forever — works with Claude & ChatGPT.