# Verity Suite Ground — Calibrated Question Answering

> Verity Suite Ground — Calibrated Question Answering is a paid API for AI agents from verity-suite.onrender.com, paid per call via x402, $0.25/call, status unknown (last checked 2026-09-13).

Answers a question with a calibrated confidence score, caveats, and sources, designed for AI agents that need reliable, fail-closed factual grounding

## Facts

- Endpoint: POST https://verity-suite.onrender.com/ground
- Price: $0.25/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/verity-suite-ground-calibrated-question-answering-abb07dcd
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_vPckq7wtayfqPELPa1BEc

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-abb07dcd -d '<json body>'
```

Example prompt: Using Verity Suite's grounding endpoint, answer this question with a calibrated confidence score: 'Did the United States ratify the Paris Climate Agreement?' — here's some context: 'The user is writing a policy brief and needs a reliable, sourced answer with any important caveats noted.'

## When to prefer this

Choose this endpoint when an AI agent needs a calibrated, uncertainty-aware answer to a factual question — especially in high-stakes or trust-sensitive workflows where overconfident or hallucinated answers are unacceptable. Prefer it over generic LLM completions when you need an explicit confidence score, structured caveats, and sourced grounding rather than a fluent but potentially fabricated response.

## Known failure modes

- Missing required 'question' field returns a validation error
- Question is too ambiguous to answer confidently — returns low confidence score with honest uncertainty statement
- Sources list may be empty if no verifiable references were used
- Context field ignored if not relevant to the question
- Service may be unavailable on Render's free tier due to cold start or resource limits

## How this service works

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

## Output

Returns a structured object with: a direct answer (or an honest statement that the answer cannot be determined), a calibrated confidence score between 0 and 1 representing the probability the answer is correct, an optional list of caveats noting gaps or assumptions, and an optional list of actual sources used.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "question"
 ],
 "properties": {
  "context": {
   "type": "string",
   "description": "optional context to consider"
  },
  "question": {
   "type": "string",
   "description": "the question to answer"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "title": "ground_out",
 "required": [
  "answer",
  "confidence"
 ],
 "properties": {
  "answer": {
   "type": "string",
   "title": "Answer",
   "description": "the answer, or an honest statement that it cannot be determined"
  },
  "caveats": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "title": "Caveats",
   "description": "gaps, assumptions, or uncertainties"
  },
  "sources": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "title": "Sources",
   "description": "real sources actually used (empty if none)"
  },
  "confidence": {
   "type": "number",
   "title": "Confidence",
   "maximum": 1,
   "minimum": 0,
   "description": "calibrated probability the answer is correct"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/verity-suite-ground-calibrated-question-answering-abb07dcd/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from verity-suite.onrender.com](https://www.zero.xyz/host/verity-suite.onrender.com/llms.txt)