83trust / 100

Jev

by Jev Structured Evaluation in AI models & inference

x402 APIPassing, checked 3 h ago

Structured evaluation with TypeSafe's Jev (System One) model. Send any state plus typed questions — noul (true/false), choice (pick one), or score (ordinal scale) — and get back calibrated probabilities and confidence for each. Built for routing, classification, triage and policy checks where a fast, predictable, machine-readable answer beats prose.

POST https://jev-x402.vercel.app/jev

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
283 ms typical, 283 ms slowest 5%
Last check
3 h ago
Next check
any minute now

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://jev-x402.vercel.app/jev" \
  -H "content-type: application/json" \
  -d '{"model":"jev-latest","questions":{"needs_review":{"criteria":{"false":"a routine question a bot can close","true":"money, legal, or an unanswered complaint"},"instructions":"Does this ticket need a human agent?","type":"noul"},"route":{"criteria":{"billing":"payment or charge problems","shipping":"delivery problems","technical":"application bugs"},"instructions":"Route this ticket to a team.","type":"choice"},"urgency":{"criteria":["low","medium","high"],"instructions":"How urgent is this ticket?","type":"score"}},"state":"My card was charged twice for one order and nobody has replied in three days."}'
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 $0.03:
// GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fjev-x402.vercel.app%2Fjev
const res = await pay("https://jev-x402.vercel.app/jev", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"model":"jev-latest","questions":{"needs_review":{"criteria":{"false":"a routine question a bot can close","true":"money, legal, or an unanswered complaint"},"instructions":"Does this ticket need a human agent?","type":"noul"},"route":{"criteria":{"billing":"payment or charge problems","shipping":"delivery problems","technical":"application bugs"},"instructions":"Route this ticket to a team.","type":"choice"},"urgency":{"criteria":["low","medium","high"],"instructions":"How urgent is this ticket?","type":"score"}},"state":"My card was charged twice for one order and nobody has replied in three days."}),
});
console.log(await res.json());

Example input

{
  "model": "jev-latest",
  "questions": {
    "needs_review": {
      "criteria": {
        "false": "a routine question a bot can close",
        "true": "money, legal, or an unanswered complaint"
      },
      "instructions": "Does this ticket need a human agent?",
      "type": "noul"
    },
    "route": {
      "criteria": {
        "billing": "payment or charge problems",
        "shipping": "delivery problems",
        "technical": "application bugs"
      },
      "instructions": "Route this ticket to a team.",
      "type": "choice"
    },
    "urgency": {
      "criteria": [
        "low",
        "medium",
        "high"
      ],
      "instructions": "How urgent is this ticket?",
      "type": "score"
    }
  },
  "state": "My card was charged twice for one order and nobody has replied in three days."
}

Example output

{
  "answers": {
    "needs_review": {
      "noul": 0.94,
      "type": "noul"
    },
    "route": {
      "choice": "billing",
      "confidence": 1,
      "probabilities": {
        "billing": 1,
        "shipping": 0,
        "technical": 0
      },
      "type": "choice"
    },
    "urgency": {
      "confidence": 0.83,
      "legend": {
        "0": "low",
        "1": "medium",
        "2": "high"
      },
      "probabilities": {
        "0": 0,
        "1": 0.11,
        "2": 0.89
      },
      "score": 1.89,
      "type": "score"
    }
  },
  "model": "jev-1.13.0",
  "usage": {
    "input_tokens": 423,
    "output_tokens": 70
  }
}

Security scan

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

Recent checks

WhenResultHTTPTimePrice
3 h agoPassed402283 ms$0.001