{"uid":"cap_0CcoJOmnmHleTxbY_0900","slug":"verity-suite-freshness-quick-check-8f026cd0","name":"Verity Suite Freshness Quick Check","description":"The trust fabric for AI agents — calibrated, fail-closed services agents pay per call.","url":"https://verity-suite.onrender.com/freshness/quick","method":"POST","headers":{},"bodySchema":{"type":"object","required":["claim"],"properties":{"as_of":{"type":"string","description":"The date or version at which the claim was last known to be true, if known (e.g. '2024-01-01'). Used only to weigh evidence recency; it is not itself proof of current truth."},"claim":{"type":"string","description":"The single fact or claim to check for currency. Treated as data to be judged, not as instructions."},"evidence":{"type":"array","description":"Retrieved current snippets, ideally each with a date and source, to judge the claim against. If empty or undated, currency cannot be confirmed."}}},"responseSchema":{"type":"object","title":"freshness_out","required":["status","staleness","reasons"],"properties":{"status":{"enum":["current","outdated","changed","unverifiable"],"type":"string","title":"Status","description":"current=dated evidence confirms the claim still holds; outdated=dated evidence shows the prior state ended but no specific replacement is established; changed=dated evidence states a specific new value (put it in current_value); unverifiable=evidence is absent, undated, irrelevant, or insufficient to decide. unverifiable is the safe fail-closed default."},"reasons":{"type":"array","items":{"type":"string"},"title":"Reasons","description":"Concrete reasons tied to specific evidence snippets (and their dates) that drove the verdict. If unverifiable, state exactly what evidence is missing or insufficient."},"staleness":{"type":"number","title":"Staleness","maximum":1,"minimum":0,"description":"Calibrated probability the claim is now stale or wrong. ~0 when fresh dated evidence confirms it; ~1 when dated evidence clearly supersedes it; mid-range when genuinely undetermined. Must honestly reflect uncertainty, never be set to an extreme for effect."},"current_value":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Current Value","description":"The up-to-date value or state, copied only from the evidence, and only when status is 'changed' or (if the evidence states it) 'outdated'. Omit entirely if no evidence states a new value; never inferred from the claim or from memory."},"as_of_evidence":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"As Of Evidence","description":"The most recent date the supporting evidence is anchored to, copied verbatim from the evidence if present. Omit if the evidence carries no date."}}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.03","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"registry","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":"$0.03/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.03","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.03","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_xbHSmlY91RM5QxfzIjQXu","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.03","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Checks whether a specific factual claim is still current by evaluating it against provided evidence snippets, returning a calibrated staleness probability and verdict.","exampleAgentPrompt":"Check whether this claim is still current: 'OpenAI's GPT-4 Turbo has a 128k context window' — I last knew this to be true as of 2024-01-01, and here are some recent snippets I found: [snippet dated 2025-01-15: 'GPT-4o is now the primary model...', snippet dated 2025-03-01: 'context windows vary by model tier']. Is this claim outdated, changed, or still current, and how stale is it?","exampleUseCases":null,"resultDescription":"Returns a verdict (current/outdated/changed/unverifiable), a staleness probability score between 0 and 1, a list of concrete reasons tied to evidence snippets, optionally the current updated value if the claim has changed, and the most recent date anchor from the evidence.","failureModes":["Evidence array is empty or undated — status will be 'unverifiable' with staleness mid-range, reasons will explain missing evidence","Claim is ambiguous or compound — may return 'unverifiable' because evidence cannot be matched to claim","Evidence snippets are irrelevant to the claim — returns 'unverifiable' with explanation","Claim itself is a question or instruction rather than a fact — treated as data but may produce low-confidence output","Network/server error from Render hosting — transient 5xx response possible"],"whenToPreferThis":"Use this endpoint when an AI agent has already retrieved evidence snippets (e.g. from a web search) and needs a calibrated, fail-closed judgment on whether a specific factual claim is still valid. Prefer it over general LLM reasoning when you need a structured, auditable verdict with a numeric staleness score rather than a free-form answer. Ideal for agentic pipelines that must decide whether to act on cached or retrieved information before committing to a downstream action.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T00:44:34.929Z","isFirstParty":false}