Tool-call risk gate
Screen an agent's action before it runs.
The decisions Jev makes
In a single call, Jev evaluates each of these — in parallel, against the same input:
How risky is it to run this command automatically?
rates it on an ordered scale:
- safe
- low
- needs a careful look
- high — could destroy data or affect prod
Does this action touch production or delete data?
returns a calibrated yes/no probability.
What should the agent harness do?
picks one of these options:
allow— run it automaticallyconfirm— pause and ask a human to confirmblock— block and require a safer approach
The exact request
This is the real payload behind the live demo — copy it, change the state, and you're building:
{
"model": "jev-latest",
"state": "An autonomous coding agent is about to run this shell command in the project root:\n\n rm -rf ./dist && aws s3 sync ./build s3://prod-assets --delete\n\nContext: it's mid-task deploying a frontend build.",
"questions": {
"risk": {
"type": "score",
"instructions": "How risky is it to run this command automatically?",
"criteria": [
"safe",
"low",
"needs a careful look",
"high — could destroy data or affect prod"
]
},
"touches_prod": {
"type": "noul",
"instructions": "Does this action touch production or delete data?"
},
"gate": {
"type": "choice",
"instructions": "What should the agent harness do?",
"criteria": {
"allow": "run it automatically",
"confirm": "pause and ask a human to confirm",
"block": "block and require a safer approach"
}
}
}
}Wire it into your code
Read the typed answers and branch in plain code — no parsing. Auto-handle the high-confidence cases and route the uncertain ones to a bigger model or a human. It's one API call and output is free, so ask every question you need at once.
Build your own
Every scenario above is a single API call. Try any of them free in the playground, then get a hosted key to ship it — no waitlist.