Evaluate Batch

Last 30 days

Uptime

100%

Response time

242 ms typical, 385 ms slowest 5%

Last check

2 h ago

Next check

any minute now

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://bazaar.fronesislabs.com/evaluate/batch" \
  -H "content-type: application/json" \
  -d '{"agent_id":"agent-123","items":[{"policy":"default","response":"example agent output"}],"max_items":20}'

import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { ExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

const client = new x402Client().register(
  "eip155:8453",
  new ExactEvmScheme(privateKeyToAccount(process.env.AGENT_KEY)),
);
const pay = wrapFetchWithPayment(fetch, client);

// Not sure it's safe to pay? Preflight it first for $0.005:
// GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fbazaar.fronesislabs.com%2Fevaluate%2Fbatch
const res = await pay("https://bazaar.fronesislabs.com/evaluate/batch", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"agent_id":"agent-123","items":[{"policy":"default","response":"example agent output"}],"max_items":20}),
});
console.log(await res.json());

Example input

{
  "agent_id": "agent-123",
  "items": [
    {
      "policy": "default",
      "response": "example agent output"
    }
  ],
  "max_items": 20
}

Example output

{
  "agent_id": "agent-123",
  "batch_id": "ab12cd34",
  "count": 1,
  "results": [
    {
      "chain_index": 42,
      "confidence": 0.95,
      "drift_mode": "NORMAL",
      "drift_score": 0,
      "input_hash": "0xdef456...",
      "pipeline_id": "abc12345",
      "policy_version": "1.0.0",
      "reason": "All policy checks passed",
      "seal_text": "Verified by Leibniz Layer",
      "timestamp": 1721635200,
      "tx_hash": "0xabc123...",
      "verdict": "COMMIT",
      "verify_url": "https://x402.fronesislabs.com/verify/abc123"
    }
  ]
}

Security scan

• No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks