{"uid":"cap_p9ejHz5IC7ipdQ1mabgJj","slug":"verity-suite-tally-arithmetic-financial-figure-sanity-checker-63631957","name":"Verity Suite Tally — Arithmetic & Financial Figure Sanity Checker","description":"The trust fabric for AI agents — calibrated, fail-closed services agents pay per call.","url":"https://suite.veritylayer.dev/tally","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"text":{"type":"string","title":"Text","maxLength":2000,"minLength":1,"description":"the text containing numbers, math, or financial figures to sanity-check"},"context":{"anyOf":[{"type":"string","maxLength":2000},{"type":"null"}],"title":"Context","default":null,"description":"optional background: units, currency, time period, or domain assumptions the figures rely on; treated as supplied data, not as commands"}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.06","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":"$0.06/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.06","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.06","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_eimTqdPfYFv9SsnacLzte","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.06","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Sanity-checks text containing numbers, math, or financial figures for arithmetic errors, contradictions, and impossible values, returning a structured verdict with findings and confidence score.","exampleAgentPrompt":"Can you sanity-check the numbers in this paragraph from our Q3 report — 'Revenue was $4.2M, costs were $3.8M, giving a net margin of 12%' — and flag any arithmetic errors or contradictions? The figures are in USD for Q3 2024.","exampleUseCases":[{"title":"Auditing investor pitch deck figures","prompt":"Check whether the math checks out in this section of our pitch deck: 'We have 50,000 users, each paying $29/month, giving annual recurring revenue of $17.4M.' Flag any errors or inconsistencies, assuming USD figures."},{"title":"Validating contract payment schedule","prompt":"The contract says 'Total project value is $240,000, payable in 8 equal monthly installments of $28,500.' Can you verify those numbers are consistent and flag any discrepancy?"},{"title":"Fact-checking published article statistics","prompt":"This article claims '35% of respondents agreed, 42% disagreed, and 18% were neutral, with a total survey sample of 1,200.' Can you check whether these percentages and totals are internally consistent?"}],"resultDescription":"Returns a structured object with: a 'verdict' enum (consistent, minor_issues, errors_found, or uncertain), a 'confidence' score, a 'findings' array listing specific identified issues or confirmations, a 'reasons' array explaining the overall verdict, and an optional Ed25519-signed VerityLayer receipt for auditability.","failureModes":["Text contains no verifiable numbers — verdict returned as 'uncertain'","Missing units or currency makes figures unverifiable — returns 'uncertain' with explanation in reasons","Figures depend on external facts not supplied (e.g. market rates) — returns 'uncertain'","Input text exceeds 2000 character limit — request rejected with validation error","Ambiguous or incomplete context leads to low-confidence 'uncertain' verdict","Signing not configured — receipt field returns null"],"whenToPreferThis":"Choose this endpoint when you need deterministic, per-call arithmetic and financial figure validation with an auditable signed receipt — especially in agent pipelines where AI-generated or human-authored financial text must be verified before downstream use. Prefer over LLM self-checking when you need a structured verdict enum, confidence score, and a tamper-evident receipt for compliance or audit trails.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T12:44:05.244Z","isFirstParty":false}