# Verity Suite Ground — Calibrated Question Answering

> Verity Suite Ground — Calibrated Question Answering is a paid API for AI agents from suite.veritylayer.dev, paid per call via x402, $0.25/call, status unknown (last checked 2026-09-14).

Answers a question with a calibrated confidence score, cited sources, caveats, and an optional Ed25519-signed receipt for auditability

## Facts

- Endpoint: POST https://suite.veritylayer.dev/ground
- Price: $0.25/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/verity-suite-ground-calibrated-question-answering-b5c27a71
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_GNyFmvo5aaRF26ABaM0yf

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability verity-suite-ground-calibrated-question-answering-b5c27a71 -d '<json body>'
```

Example prompt: Is it true that the FDA approved semaglutide for cardiovascular risk reduction? Give me a calibrated confidence score, the real sources you used, and any caveats — I need a signed receipt so I can log this for compliance.

## When to prefer this

Choose this endpoint when your agent needs not just an answer but a trust signal: a calibrated confidence score, real source attribution, explicit caveats, and optionally a cryptographically signed receipt for audit trails. It is ideal for autonomous agent pipelines where hallucination risk must be quantified, for compliance-sensitive workflows requiring loggable provenance, or when a human-in-the-loop needs to review AI certainty before acting. Prefer it over generic LLM calls when you need fail-closed behavior — the endpoint is designed to say 'I don't know' honestly rather than confabulate.

## Known failure modes

- Question too vague or unanswerable — returns answer stating it cannot be determined, with low confidence
- Context field exceeds 2000 characters — schema validation error
- Question field empty or missing — 400-level validation error
- Signing not configured — receipt field returns null
- Payment not included or insufficient — x402 payment required error
- Network timeout — no response returned

## How this service works

The trust fabric for AI agents — calibrated, fail-closed services agents pay per call.

## Output

Returns a structured JSON object containing: a plain-language answer (or honest statement that the answer cannot be determined), a calibrated probability score (0–1) representing confidence the answer is correct, an array of real sources used, an array of caveats covering gaps or uncertainties, and an optional Ed25519-signed VerityLayer receipt for independent verification.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "context": {
   "anyOf": [
    {
     "type": "string",
     "maxLength": 2000
    },
    {
     "type": "null"
    }
   ],
   "title": "Context",
   "default": null,
   "description": "optional context to consider"
  },
  "question": {
   "type": "string",
   "title": "Question",
   "maxLength": 2000,
   "minLength": 1,
   "description": "the question to answer"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/verity-suite-ground-calibrated-question-answering-b5c27a71/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from suite.veritylayer.dev](https://www.zero.xyz/host/suite.veritylayer.dev/llms.txt)