Support triage
Route and prioritize an inbound support message in one call.
Live toolRun this on your own data with the Support Ticket Router →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:
What is the primary issue the customer is writing about?
picks one of these options:
billing— billing, payments, refunds or invoicesbug— the product is broken or not workingaccount— login, access or account settingsfeature— a feature request or how-to question
How urgent and high-risk is this message?
rates it on an ordered scale:
- routine, no rush
- should be handled today
- urgent, customer is frustrated
- critical, customer is about to churn or dispute
Should this be escalated to a human agent immediately?
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": "Subject: Charged twice again!!\n\nHi — this is the SECOND month in a row I've been billed twice for the Pro plan. I already emailed last month and nobody replied. I run my whole business on this. If it's not refunded today I'm cancelling and disputing the charge with my bank.",
"questions": {
"topic": {
"type": "choice",
"instructions": "What is the primary issue the customer is writing about?",
"criteria": {
"billing": "billing, payments, refunds or invoices",
"bug": "the product is broken or not working",
"account": "login, access or account settings",
"feature": "a feature request or how-to question"
}
},
"severity": {
"type": "score",
"instructions": "How urgent and high-risk is this message?",
"criteria": [
"routine, no rush",
"should be handled today",
"urgent, customer is frustrated",
"critical, customer is about to churn or dispute"
]
},
"escalate": {
"type": "noul",
"instructions": "Should this be escalated to a human agent 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 in minutes.