Live Jev API debugger

Inspect the decision before your agent acts.

Run Jev through OmniaKey with a workflow preset or your own native decision contract. Edit the JSON input and inspect the model’s actual answers, probabilities, and token usage. Your OmniaKey API key stays in memory and is never saved.

Read the guide for this preset →

Use the native Jev Decisions contract to define shared state and bounded questions, then inspect the raw model answers.

OmniaKey API key

Used only for this request. The page does not persist the key.

Request endpoint

https://api.omniakey.com/v1/alpha/search

All presets use OmniaKey’s native Jev endpoint with the jev-latest model.

Jev Decisions input

{
  "model": "jev-latest",
  "state": {
    "customer_message": "I was charged twice for order ord_7429. Please refund the duplicate charge.",
    "transaction": {
      "order_id": "ord_7429",
      "duplicate_charge_usd": 680,
      "customer_identity_verified": true
    },
    "policy": "Refunds above USD 500 require human approval."
  },
  "questions": {
    "action": {
      "type": "choice",
      "instructions": "Choose the safest next action.",
      "criteria": {
        "allow": "Issue the refund immediately.",
        "review": "Require human approval before issuing the refund.",
        "deny": "Reject the refund request."
      }
    },
    "needs_human_review": {
      "type": "noul",
      "instructions": "Does this refund require human review under the stated policy?"
    },
    "risk": {
      "type": "score",
      "instructions": "Score the financial and policy risk.",
      "criteria": [
        "Low: routine and within automatic approval limits.",
        "Moderate: bounded risk with complete verification.",
        "High: exceeds an approval threshold or has material uncertainty.",
        "Critical: unsafe or unauthorized to execute."
      ]
    }
  }
}

{
  "model": "jev-latest",
  "state": {
    "customer_message": "I was charged twice for order ord_7429. Please refund the duplicate charge.",
    "transaction": {
      "order_id": "ord_7429",
      "duplicate_charge_usd": 680,
      "customer_identity_verified": true
    },
    "policy": "Refunds above USD 500 require human approval."
  },
  "questions": {
    "action": {
      "type": "choice",
      "instructions": "Choose the safest next action.",
      "criteria": {
        "allow": "Issue the refund immediately.",
        "review": "Require human approval before issuing the refund.",
        "deny": "Reject the refund request."
      }
    },
    "needs_human_review": {
      "type": "noul",
      "instructions": "Does this refund require human review under the stated policy?"
    },
    "risk": {
      "type": "score",
      "instructions": "Score the financial and policy risk.",
      "criteria": [
        "Low: routine and within automatic approval limits.",
        "Moderate: bounded risk with complete verification.",
        "High: exceeds an approval threshold or has material uncertainty.",
        "Critical: unsafe or unauthorized to execute."
      ]
    }
  }
}

Create an access key

Structured response

answers + probabilities + usage

The typed Jev response will appear here.

Run the request to inspect the original Jev answers, confidence, probability distributions, resolved model version, and token usage returned through OmniaKey.