BestPromptFinder
Home › Research › Claim Verification and Evidence Grading

Claim Verification and Evidence Grading

Research · Claude, Gemini · text
95AI Quality /100
92AI Usefulness est. /100
81Eval Confidence /100
No votes yetCommunity results

Quality, usefulness and confidence are AI evaluations out of 100 — not user ratings. Community results come from visitors' "worked / didn't work" votes below. How scoring works →

The prompt

Audit the following claims before publication: CLAIMS: [paste] CONTEXT: [advertisement, deck, research report, website, etc.] JURISDICTION: [location] SUPPORTING SOURCES: [links/files] AS-OF DATE: [date] For each claim: 1. Rewrite it as one testable proposition. 2. Classify it: factual, comparative, forecast, opinion or implied promise. 3. Identify the best primary evidence and its date. 4. Assess evidence quality: strong, moderate, weak or absent. 5. Give a conclusion: supported, partly supported, unsupported, outdated or not independently verifiable. 6. State confidence and conflicting evidence. 7. Propose the narrowest accurate replacement wording. Pay special attention to "best," "largest," guaranteed returns, travel time, price, inventory, market share, performance and future-completion claims. Do not treat repetition across websites as independent corroboration. Never convert an estimate into a fact. End with a red-flag list requiring legal or subject-matter review.
Find similar in the app →
Did this prompt work for you?

Why this prompt

Source & licence

Related Research prompts

Competitor Benchmark Scorecard
Quality 97 · Claude, Gemini
Decision-Grade Competitive Report
Quality 96 · GPT-5.6
Institutional Article and Filing Extractor
Quality 95 · Gemini, GPT-5.6, Claude
Market Watch Monitor Design
Quality 93 · GPT-5.6 Sol
Answer a Question From a Book Passage
Quality 92 · Gemini, GPT-5.6, Claude
Strategic Scenario Research
Quality 92 · ChatGPT Deep Research