{"uid":"cap_JwlF1LbnNGN_Cs0L-XrN9","slug":"veritylayer-quick-verify-52c614b7","name":"VerityLayer Quick Verify","description":"Fact-check a claim before your agent acts on, repeats, or ships it — verify a claim, is this true, catch hallucinations. Independent, fail-closed verification for AI agents: a verdict with calibrated 0-1 confidence, reasoning, and web-sourced evidence; abstains rather than guess, never fabricates. Every verdict ships a signed, independently re-verifiable receipt — proof of what was asked and answered, free to verify forever. Tier: quick — fast ungrounded pre-filter (Haiku).","url":"https://api.veritylayer.dev/verify/quick","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"claim":{"type":"string"},"context":{"type":"string"}}},"responseSchema":{"type":"json","example":{"verdict":"supported","evidence":["Encyclopaedia Britannica — Eiffel Tower, Paris, France."],"reasoning":"Multiple authoritative sources place the Eiffel Tower on the Champ de Mars in Paris, France.","confidence":0.97}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.02","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":"$0.02/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_mKoZfeRoIqjgze9pY1b-2","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.02","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Verifies whether an AI-generated claim or citation is factually supported or hallucinated, returning a verdict, evidence sources, reasoning, and confidence score.","exampleAgentPrompt":"Before you send that AI-written summary to the client, run it through VerityLayer to check whether the claims and citations are actually real — I need to know the verdict, any supporting evidence, and how confident it is.","exampleUseCases":[{"title":"Legal brief citation audit","prompt":"The AI just drafted a legal memo citing several court cases — can you verify each citation against VerityLayer to make sure none of them are hallucinated before we file anything?"},{"title":"Research paper fact-check","prompt":"My AI assistant wrote a paragraph about climate data with three specific statistics — please fact-check those claims and tell me which ones are supported by real sources and which might be fabricated."},{"title":"Customer-facing AI output review","prompt":"Before my chatbot sends this response to a customer claiming that our refund policy has a 30-day window, can you verify that claim is accurate and get me the evidence and confidence score?"}],"resultDescription":"A JSON object containing: 'verdict' (e.g. 'supported' or 'refuted'), 'evidence' (array of authoritative source citations backing the verdict), 'reasoning' (human-readable explanation of why the claim is supported or not), and 'confidence' (a 0–1 score indicating how certain the engine is).","failureModes":["Claim is too vague or ambiguous to verify — may return low confidence or inconclusive verdict","Source material unavailable or behind paywalls — evidence array may be sparse","Extremely niche or newly emerging facts may lack sufficient indexed sources for verification","Malformed or empty input claim returns validation error","Network timeout or service unavailability returns HTTP 5xx"],"whenToPreferThis":"Choose VerityLayer when you need a lightweight, fast, per-claim hallucination check with a clear supported/refuted verdict and cited evidence — especially when your AI pipeline is generating citations, legal references, or factual assertions that must be trustworthy before reaching end users. It is particularly strong at catching fabricated citations (8/8 on the Mata v. Avianca benchmark) and operates fail-closed, meaning it errs toward flagging rather than passing suspect content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T00:36:19.956Z","isFirstParty":false}