Data extraction
Turn a free-text note into structured, typed fields.
The decisions Jev makes
In a single call, Jev evaluates each of these — in parallel, against the same input:
Which department should handle this?
picks one of these options:
receiving— warehouse receiving / logisticssales— salesfinance— finance / accounts payableit— IT support
Is the caller reporting a problem or defect?
returns a calibrated yes/no probability.
How time-sensitive is a callback?
rates it on an ordered scale:
- whenever
- this week
- today
- immediately
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": "Voicemail transcript: 'Hey it's Marco from the loading dock, uh, the shipment from Kellerman's showed up but two of the pallets are damaged, looks like water. It's the order from last Tuesday. Can someone call me back, it's kind of urgent, we can't shelve these.'",
"questions": {
"department": {
"type": "choice",
"instructions": "Which department should handle this?",
"criteria": {
"receiving": "warehouse receiving / logistics",
"sales": "sales",
"finance": "finance / accounts payable",
"it": "IT support"
}
},
"is_complaint": {
"type": "noul",
"instructions": "Is the caller reporting a problem or defect?"
},
"priority": {
"type": "score",
"instructions": "How time-sensitive is a callback?",
"criteria": [
"whenever",
"this week",
"today",
"immediately"
]
}
}
}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.