Cryptographic attestation for OpenAI Agents.

REST-based integration. Attest any OpenAI Assistants or Agents API decision with verifiable human oversight, anchored on-chain.

How it wires up

1. Your agent reaches a decision that needs human oversight (high-stakes action, regulated decision, ambiguous case).
2. Call POST /v1/verifications on SanctifAI Trust with the agent's decision context.
3. A qualified human attests via WebAuthn.
4. Receive a verifiable certificate URL. Anchor it in your audit log; share it with auditors and regulators.

In an OpenAI SDK tool definition

import OpenAI from "openai";

const client = new OpenAI();

// Define an attestation tool the agent can call:
const tools = [{
  type: "function",
  function: {
    name: "request_human_verification",
    description: "Request cryptographic attestation of human oversight via SanctifAI Trust.",
    parameters: {
      type: "object",
      properties: {
        decision_context: { type: "string" },
        task_id: { type: "string" }
      },
      required: ["decision_context", "task_id"]
    }
  }
}];

// When the agent calls this tool, your handler calls SanctifAI Trust:
async function handleVerification(args) {
  const res = await fetch("https://trust.sanctifai.com/v1/verifications", {
    method: "POST",
    headers: {
      "Authorization": `Bearer ${process.env.SANCTIFAI_API_KEY}`,
      "Idempotency-Key": crypto.randomUUID(),
      "Content-Type": "application/json"
    },
    body: JSON.stringify(args)
  });
  return res.json();
}