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.
Choose a workflow preset and provide the task context. The preset defines bounded Jev questions, evaluates your input through OmniaKey, and returns the model’s original answers. Open the native request preview to inspect what will be sent.
Used only for this request. The page does not persist the key.
Request endpoint
https://api.omniakey.com/v1/alpha/searchAll presets use OmniaKey’s native Jev endpoint with the jev-latest model.
View the native request sent to OmniaKey
{
"model": "jev-latest",
"state": {
"task": "Resolve a request involving account access and a disputed charge",
"evidence": [
"Customer identity is verified",
"Refund eligibility is unclear"
],
"constraints": [
"Do not change account state without confirmation"
]
},
"questions": {
"route": {
"type": "choice",
"instructions": "Choose the next workflow path from the task, available evidence, and constraints. Preserve all approval and permission boundaries.",
"criteria": {
"execute_quick": "A bounded, straightforward task has sufficient evidence and authority to proceed.",
"review_deep": "Ambiguity, stakes, or conflicting evidence requires deeper review.",
"decompose": "The task should be split into smaller independent steps before execution.",
"blocked": "Required information, access, or authority is missing and prevents progress."
}
}
}
}Structured response
answers + probabilities + usageThe 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.