Decision Review
by TenPrint in Other
Attested policy evaluation: submit a proposed agent action, its context, and the policy it must satisfy. Returns a verdict, reasoning and the clauses applied, binding hashes of all three inputs into an ML-DSA-65 signed, Hedera-anchored record.
https://rubric-protocol.com/v1/x402/decision-review- Price
- $0.1
- per call in USDC
- Uptime
- 100%
- last 30 days
- Response time
- 384 ms
- 460 ms slowest 5%
- Last check
- Passed
- 14 min ago, next in 15 min
Reliability
Status and outage history · Atom feed · Watch with other listings
How to call it
POST https://rubric-protocol.com/v1/x402/decision-review
Each call costs $0.1 in USDC on Base, paid with the request over x402.
Run a free test callOne unpaid request, the way an agent sends it. You see the payment challenge it gets back. Nothing is charged.
Example request
From the listing.
POST https://rubric-protocol.com/v1/x402/decision-review
content-type: application/json
{
"action": "Issue a $4,200 refund to customer 88213",
"context": {
"supervisorApproval": null
},
"policy": "Refunds above $1,000 require supervisor approval"
}Example response
The provider's example. We can't check it without paying.
{
"actionHash": "b71c9f2e4a883d15",
"contextHash": "e83f2b5c71d90a48",
"evaluator": "rubric-decision-review/1",
"missingContext": [
"supervisor approval reference"
],
"model": "gpt-4o-mini-2024-07-18",
"operator": "TenPrint",
"paid": true,
"policyClausesApplied": [
"refunds over $1,000 require supervisor approval"
],
"policyHash": "5d0ac4e1f9b27a63",
"reasoning": "Refund exceeds the $1,000 discretionary limit; no supervisor approval in context.",
"settled": true,
"success": true,
"verdict": "inconsistent",
"vsr": {
"hashProfile": "vsr/v0.4/sha3-256",
"spec": "https://rubric-protocol.com/specs/vsr-v0.4.md",
"vsrVersion": "0.4-draft"
}
}Call it from code
The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.1.
curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i -X POST 'https://rubric-protocol.com/v1/x402/decision-review' \
-H 'content-type: application/json' \
--data-raw '{"action":"Issue a $4,200 refund to customer 88213","context":{"supervisorApproval":null},"policy":"Refunds above $1,000 require supervisor approval"}'
# x402 v2 sends the challenge base64-encoded in the PAYMENT-REQUIRED header (v1 sends it in the body).
# To read the header:
curl -sS -g -o /dev/null -D - -X POST 'https://rubric-protocol.com/v1/x402/decision-review' \
-H 'content-type: application/json' \
--data-raw '{"action":"Issue a $4,200 refund to customer 88213","context":{"supervisorApproval":null},"policy":"Refunds above $1,000 require supervisor approval"}' \
| grep -i '^payment-required:' | cut -d' ' -f2 | tr -d '\r' | base64 --decodeJavaScript: pay and call
// npm i @x402/fetch @x402/evm viem
import { wrapFetchWithPayment, x402Client } from "@x402/fetch";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";
// Pays at most $0.1 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.1" });
registerExactEvmScheme(client, { signer: privateKeyToAccount(process.env.EVM_PRIVATE_KEY) });
const pay = wrapFetchWithPayment(fetch, client);
// Not sure it's safe to pay? ToolVet checks it first for $0.005. Pay for that from a separate
// client: this one is capped at $0.1 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Frubric-protocol.com%2Fv1%2Fx402%2Fdecision-review&method=POST
const res = await pay("https://rubric-protocol.com/v1/x402/decision-review", {
method: "POST",
headers: { "content-type": "application/json" },
body: JSON.stringify({
"action": "Issue a $4,200 refund to customer 88213",
"context": {
"supervisorApproval": null
},
"policy": "Refunds above $1,000 require supervisor approval"
}),
});
console.log(res.status, await res.text());Python: pay and call
# pip install "x402[requests,evm]"
import os
from eth_account import Account
from x402 import x402ClientSync
from x402.http.clients import x402_requests
from x402.mechanisms.evm import EthAccountSigner
from x402.mechanisms.evm.exact.register import register_exact_evm_client
# Pays at most $0.1 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.1"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))
with x402_requests(client) as session:
res = session.post(
"https://rubric-protocol.com/v1/x402/decision-review",
json={
"action": "Issue a $4,200 refund to customer 88213",
"context": {
"supervisorApproval": None,
},
"policy": "Refunds above $1,000 require supervisor approval",
},
)
print(res.status_code, res.text)Security scan
No findings
We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.
Recent checks
| When | Result | HTTP | Time | Price |
|---|---|---|---|---|
| 14 min ago | Passed | 402 | 358 ms | $0.1 |
| 5 h ago | Passed | 402 | 431 ms | $0.1 |
| 9 h ago | Passed | 402 | 387 ms | $0.1 |
| 14 h ago | Passed | 402 | 132 ms | $0.1 |
| 18 h ago | Passed | 402 | 528 ms | $0.1 |
Show 10 older checks
| 22 h ago | Passed | 402 | 405 ms | $0.1 |
| 27 h ago | Passed | 402 | 382 ms | $0.1 |
| 31 h ago | Passed | 402 | 410 ms | $0.1 |
| 35 h ago | Passed | 402 | 398 ms | $0.1 |
| 39 h ago | Passed | 402 | 384 ms | $0.1 |
| 44 h ago | Passed | 402 | 352 ms | $0.1 |
| 2 days ago | Passed | 402 | 407 ms | $0.1 |
| 2 days ago | Passed | 402 | 369 ms | $0.1 |
| 2 days ago | Passed | 402 | 358 ms | $0.1 |
| 3 days ago | Passed | 402 | 384 ms | $0.1 |