Back to Browse
SignalHarness LLM Response Structure Score
x402
SignalHarness LLM Response Structure Score is a paid API for AI agents from signalharness.ai, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-15).
Scores and analyzes the structural quality of an LLM-generated JSON response against expected schema or format criteria
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 a structure score analysis, warnings about data reliability (e.g. caller-supplied data caveats), an analysis_json field with the scored breakdown, evidence_scope indicating data provenance, plus a full execution receipt with payment details, request/execution IDs, result hash, latency, and settlement reference on the Base network.
Example use cases
QA pipeline for LLM output validation
“I'm running a pipeline where GPT-4 generates structured JSON responses — can you score the structure of this response to make sure it's properly formed before I pass it downstream: {"intent": "book_flight", "entities": {"destination": "NYC", "date": null}}”
Agent output compliance checking
“My AI agent just returned this JSON and I'm not sure if it's structurally sound — can you analyze it and give me a structure score so I know whether to trust it: {"action": "send_email", "to": "user@example.com", "body": ""}”
Benchmark LLM response formatting
“I'm comparing two language models on how well they format their outputs — here's the response from model A, can you give me a structure score for it: {"summary": "The report covers Q1 2024.", "metrics": ["revenue", "churn"], "confidence": 0.87}”
Technical details
Endpoint
POSThttps://signalharness.ai/api/agent/services/llm_response_structure_score/invokeWhen to prefer
Choose this endpoint when you need a lightweight, pay-per-call structural quality check on LLM-generated JSON responses — particularly useful in agent pipelines where downstream systems depend on well-formed outputs. Prefer it over manual validation when you want a scored, evidence-backed assessment rather than a binary pass/fail. Best suited for agentic workflows running on Base USDC micropayment infrastructure where per-call billing is acceptable.
Side effects
- Invalid or malformed JSON string in request_json field causes parsing failure
- Input exceeds 65536 character limit returning validation error
- Empty or minimal JSON (fewer than 2 characters) rejected by minLength constraint
- Ambiguous structure with no clear schema reference may result in low-confidence or generic scoring
- Payment failure or insufficient USDC balance prevents execution
- Network issues on Base/eip155:8453 may cause settlement delays
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": "llm_response_structure_score",
"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_structure_score",
"executionId": "example-execution",
"startedAtMs": 0,
"amountAtomic": "10000",
"resultSha256": "58e1cd6567595c674b09df570b3cdf6d71258b0841da5023f06fc333ce1d9df5",
"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"