POST /run
Analyzes a single AI agent tool call and returns a structured reliability report. Detects failure modes including sycophantic gap-filling, context degradation, hallucination, repetition loops, confidence collapse, and schema violations, with remediation suggestions for each.
Start with a quote-only recipe. Payment signing stays in your project.
const response = await fetch("https://app-443.hdgregory.com/run", {
method: "POST",
headers: { "content-type": "application/json" },
body: JSON.stringify({
"type": "http",
"method": "POST",
"bodyType": "json",
"bodyFieldNames": [
"latency_ms",
"parameters",
"response",
"tool_name"
],
"pathParamNames": [],
"queryParamNames": []
}),
});
console.log(response.status);
console.log(Object.fromEntries(response.headers));
console.log((await response.text()).slice(0, 1000));
// A valid 402 is a quote, not a completed paid call.Review the provider input schema before running this non-read-only method. No payment code is included.
- Exact route checked
not safely testable · potentially-mutating-method:POST
- Origin reachable
OPTIONS https://app-443.hdgregory.com/ returned 405.
- Observed in cdp-bazaar
The registry record was observed and retained with provenance.
EVIDENCE
Each record has an exact-route quote outcome. Unresolved templates and potentially mutating methods are labeled instead of being invoked without provider-specific test input. A quote is still separate from a settled paid call.