Verity Suite Ground — Calibrated Question Answering

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.

• 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