{"uid":"cap_dIdpPFFfb0isggLWLPVRK","slug":"verity-claim-verification-5bf41f4b","name":"Verity Claim Verification","description":"Grounded reality-check with live web citations.","url":"https://verity-bzw7.onrender.com/verify","method":"POST","headers":{},"bodySchema":{"type":"object","required":["claim"],"properties":{"claim":{"type":"string"},"context":{"type":"string"}}},"responseSchema":{"type":"object","title":"Verdict","required":["verdict","confidence","reasoning","evidence"],"properties":{"verdict":{"enum":["supported","unsupported","uncertain"],"type":"string","title":"Verdict"},"evidence":{"type":"array","items":{"type":"string"},"title":"Evidence"},"reasoning":{"type":"string","title":"Reasoning"},"confidence":{"type":"number","title":"Confidence"}},"description":"The structured judgment an agent pays for."},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.25","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.25/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.25","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.25","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_7XmIihGsPu3afYGd9pJAO","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.25","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Verifies a textual claim and returns a structured verdict (supported/unsupported/uncertain) with confidence score, reasoning, and evidence","exampleAgentPrompt":"Can you verify this claim for me: 'The Eiffel Tower is taller than the Statue of Liberty' — I want to know if it's supported or unsupported, how confident you are, and what evidence backs the verdict.","exampleUseCases":[{"title":"Fact-check user testimonials before publishing","prompt":"Before we post customer reviews on our website, can you verify each one? I need you to check if the claims they're making are actually true — like if someone says our product reduced their costs by 50%, verify that's realistic and supported by evidence."},{"title":"Validate AI-generated content for accuracy","prompt":"My AI chatbot just drafted some product descriptions for our catalog. Can you fact-check the technical specs and claims in there? I want to make sure nothing's overstated or false before it goes live, and I need a confidence score for each claim."},{"title":"Audit competitor claims in market research","prompt":"We're analyzing competitor marketing materials and I'm seeing a lot of bold claims about their features and performance. Can you systematically verify whether their statements hold up with evidence? I need structured verdicts so we can compare what's actually true versus what's just marketing hype."}],"resultDescription":"A structured Verdict object containing: a verdict enum ('supported', 'unsupported', or 'uncertain'), a numeric confidence score (0–1), a human-readable reasoning string explaining the judgment, and an array of evidence strings cited to support the verdict.","failureModes":["Missing required 'claim' field returns a validation error","Ambiguous or overly vague claims may return 'uncertain' with low confidence","Claims requiring real-time data may be marked uncertain if evidence is unavailable","Service unavailable on Render cold-start may cause timeout or 503","Payment failure via x402 protocol blocks the request from being processed"],"whenToPreferThis":"Choose Verity when an AI agent needs a structured, paid, high-accountability fact-check with explicit reasoning and evidence — particularly when the output needs to be machine-readable (verdict enum + confidence float) for downstream logic. Prefer this over a generic web search when you need a single authoritative verdict rather than a list of results, or when verifying AI-generated claims before acting on them.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T12:33:13.492Z","isFirstParty":false}