Lead scoring
Qualify an inbound sales lead from raw form text.
Live toolRun this on your own data with the Lead Scorer →Try it live
This is the real thing, not a mockup. Edit the input, hit Run, and Jev returns every typed answer in one round trip — free, no signup. Now picture the same call fired across thousands of items in parallel.
Pick a demo, tweak the input, and hit Run Jev.
The decisions Jev makes
In a single call, Jev evaluates each of these — in parallel, against the same input:
How strong a fit is this lead for a technical B2B infrastructure product?
rates it on an ordered scale:
- poor fit / tire-kicker
- weak fit
- decent fit
- strong fit
- ideal, high-intent buyer
Where should this lead be routed?
picks one of these options:
enterprise— enterprise account executivesmb— self-serve / SMBnurture— marketing nurture sequencedisqualify— not a fit, disqualify
Is this lead actively in a buying cycle right now?
returns a calibrated yes/no probability.
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": "Inbound demo request. Name: Priya Nadkarni. Company: Northwind Robotics (~450 employees). Role: VP of Engineering. Message: 'We're replacing a homegrown rules engine that routes millions of events a day and evaluating vendors this quarter. Need something we can pilot in 2 weeks. Budget approved.'",
"questions": {
"fit": {
"type": "score",
"instructions": "How strong a fit is this lead for a technical B2B infrastructure product?",
"criteria": [
"poor fit / tire-kicker",
"weak fit",
"decent fit",
"strong fit",
"ideal, high-intent buyer"
]
},
"route": {
"type": "choice",
"instructions": "Where should this lead be routed?",
"criteria": {
"enterprise": "enterprise account executive",
"smb": "self-serve / SMB",
"nurture": "marketing nurture sequence",
"disqualify": "not a fit, disqualify"
}
},
"buying_now": {
"type": "noul",
"instructions": "Is this lead actively in a buying cycle right now?"
}
}
}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 in minutes.