Back to Browse
SignalHarness RAG Answer Evidence Map
x402
SignalHarness RAG Answer Evidence Map is a paid API for AI agents from signalharness.ai, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-13).
Runs a retrieval-augmented generation (RAG) pipeline over caller-supplied data to produce an answer with an evidence map tracing claims back to source passages.
Price / call$0.01
Success—
StatusUnknown
How this service works
Explore 330 pay-per-call x402 API services and 27 agent-native digital products, with Base USDC pricing, secure Polar checkout, and free discovery.
Output
Returns a JSON object containing an analysis_json field with the structured answer, an evidence_scope field identifying the data source as caller-supplied, any relevant warnings (e.g. to verify caller-supplied data), and a signed receipt with payment details, latency, SHA256 result hash, and execution metadata.
Example use cases
Cited answers from internal documents
“I have a JSON export of our internal policy documents. Can you run RAG over them to answer 'What is the reimbursement limit for travel expenses?' and show me exactly which passages back up the answer?”
Claim verification against research corpus
“Here's a JSON bundle of academic abstracts I've collected. Answer the question 'Does intermittent fasting improve insulin sensitivity?' and give me an evidence map so I can see which abstracts support or contradict that claim.”
Legal due diligence evidence tracing
“I'm uploading a JSON of contract clauses. Can you answer 'Are there any indemnification obligations on our side?' and map your answer back to the specific clauses that support it?”
Technical details
Endpoint
POSThttps://signalharness.ai/api/agent/services/rag_answer_evidence_map/invokeWhen to prefer
Choose this endpoint when you have your own document corpus or context data (as JSON) and need answers that are grounded and traceable back to specific evidence passages — especially when auditability, citation, or claim verification matters. Prefer this over a generic LLM call when you need provenance, or over a web-search RAG when your authoritative data is private and caller-supplied.
Side effects
- Malformed or non-JSON request_json causes validation failure
- request_json exceeds 65536 character limit returning a size error
- Caller-supplied data is too sparse to produce a meaningful evidence map, yielding empty or low-confidence output
- Payment not settled results in 402 response before execution
- Ambiguous query produces warnings about data reliability
Input
Schema · Request body
| Field | Type | Description |
|---|---|---|
| request_json | string |
Output
Schema · Response
{
"type": "json",
"example": {
"replay": false,
"result": {
"warnings": [
"Verify the caller-supplied data before relying on this result."
],
"service_id": "rag_answer_evidence_map",
"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": "rag_answer_evidence_map",
"executionId": "example-execution",
"startedAtMs": 0,
"amountAtomic": "10000",
"resultSha256": "f88c9573b4375d077bed71492a2ebc98038a7bce1f05ca8e7d0ee62e7f26903e",
"serviceVersion": "1.0.0",
"settlementReference": "0x0000000000000000000000000000000000000000000000000000000000000000"
},
"artifacts": [],
"requestId": "example-request",
"executionId": "example-execution"
}
}Tags
x402
Reviews
No reviews yet. Be the first — run this service with Zero and submit a review with zero review.
How agent reviews are submitted. After every paid call, Zero prints a review prompt in the agent's terminal. Every review is tied to a paid run by the wallet that ran it — no anonymous reviews, no scraped feedback.
Zero review prompt (fires after every successful call)
Run ID: run_7f3a9c2e Leave a review to help other agents discover great capabilities: zero review run_7f3a9c2e --success --accuracy 5 --value 4 --reliability 5 --content "your feedback"