{"uid":"cap_HTYcmpLXwBthxa_FCXq6V","slug":"signalharness-llm-response-claim-extractor-8722f20a","name":"SignalHarness LLM Response Claim Extractor","description":"Explore 330 pay-per-call x402 API services and 27 agent-native digital products, with Base USDC pricing, secure Polar checkout, and free discovery.","url":"https://signalharness.ai/api/agent/services/llm_response_claim_extract/invoke","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"request_json":{"type":"string","maxLength":65536,"minLength":2}}},"responseSchema":{"type":"json","example":{"replay":false,"result":{"warnings":["Verify the caller-supplied data before relying on this result."],"service_id":"llm_response_claim_extract","analysis_json":"{\"example\":\"schema-valid caller-supplied data\"}","evidence_scope":"caller_supplied_data"},"status":"succeeded","receipt":{"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","usage":[],"status":"succeeded","network":"eip155:8453","artifacts":[],"endedAtMs":0,"latencyMs":0,"paymentId":"example-payment","receiptId":"example-receipt","requestId":"example-request","serviceId":"llm_response_claim_extract","executionId":"example-execution","startedAtMs":0,"amountAtomic":"5000","resultSha256":"c5d55edd84af5f133e7085a4d5f7494aba00a7817cdfd8bf629392ad09160f01","serviceVersion":"1.0.0","settlementReference":"0x0000000000000000000000000000000000000000000000000000000000000000"},"artifacts":[],"requestId":"example-request","executionId":"example-execution"}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.005","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":"$0.005/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm__qzEdw9wBydyWdlVTjSv2","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts and structures factual claims from LLM-generated text responses, returning a validated analysis JSON with warnings about caller-supplied data.","exampleAgentPrompt":"Extract all factual claims from this LLM response so I can verify them: '{\"response\": \"The Eiffel Tower was built in 1889 and stands 330 meters tall. It receives 7 million visitors annually.\"}'","exampleUseCases":[{"title":"Fact-checking pipeline for AI outputs","prompt":"I need you to pull out every factual claim from this AI-generated article summary so I can run them through a fact-checker: '{\"response\": \"Climate change has increased global temperatures by 1.1°C since pre-industrial times, affecting over 3 billion people.\"}'"},{"title":"RAG response auditing","prompt":"Extract all the claims my RAG system made in this response so I can check which ones are actually supported by the source documents: '{\"response\": \"The policy covers dental and vision, with a $500 annual deductible and no referral needed for specialists.\"}'"},{"title":"LLM output quality monitoring","prompt":"Parse this chatbot reply and give me a structured list of the specific assertions it made — I want to track which claims my model is confidently stating: '{\"response\": \"Our product ships in 3-5 business days, offers free returns within 30 days, and comes with a 2-year warranty.\"}'"}],"resultDescription":"Returns a JSON object containing an analysis_json field with structured extracted claims, an evidence_scope field indicating the data came from caller-supplied input, and a warnings array reminding the caller to verify the data. Also includes a full execution receipt with payment details, latency, and a SHA-256 hash of the result for audit purposes.","failureModes":["Malformed or non-JSON request_json input returns a parsing error","Input text exceeding 65,536 characters is rejected","LLM responses with ambiguous or no extractable claims may return an empty or minimal analysis","Network or payment settlement failures may result in no result with a failed status receipt","Caller-supplied data that is itself invalid JSON may cause unexpected extraction behavior"],"whenToPreferThis":"Choose this endpoint when you need to programmatically decompose LLM or chatbot outputs into discrete, structured factual claims — especially in fact-checking pipelines, RAG audit workflows, or AI output quality monitoring. It is well-suited for agents that need to isolate verifiable assertions from free-form generated text before passing them to a verification or grounding step. Prefer it over general-purpose text parsers when you specifically need claim-level granularity with a structured JSON result and a cryptographic receipt for auditability.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T13:12:56.079Z","isFirstParty":false}