AI Jev: typed decisions for real workflows
Jev AI turns text and JSON into clear, typed answers.
Get probabilities you can route, score, and act on.
Ask questions.
Get probabilities.
AI Jev, also called Jev AI, is a typed decision model for turning text or JSON into structured answers. Ask several questions in one call and get a predictable shape every time—without parsing prose or maintaining a separate classifier.
Yes / No
Binary decisions with a probability you can act on.
Choice
Route text into one of your own labeled options.
Score
Return a score across a scale you define.
From a question to a decision
Write your questions
Describe the decision in plain language.
Send your text
Run one document, or thousands of rows in a batch.
Use the answer
Build routing, scoring, and guardrails on structured output.
One request, many decisions
Keep related checks together and receive a stable answer shape your application can validate.
Fast to test, simple to scale
Start with an AI Jev test in the playground, reuse the same rules in batch jobs, then move to the Jev API.
Spend stays visible
Every playground and API run shows its credit cost. Failed provider calls are reversed server-side.
Questions before you ship?
What is AI Jev?
AI Jev, also called Jev AI, turns text or JSON into typed Yes/No, Choice, and Score decisions with probabilities.
How can I use Jev AI?
Start in the playground, process a file in Batch, or call the Jev AI API from your server with a server-side API key.
What can Jev classify?
Any text or JSON where you need a typed decision: support triage, moderation, routing, review scoring, lead qualification, guardrails, and citation checks.
Can I ask more than one question?
Yes. The playground and API accept up to 64 questions in one request, including Yes/No, Choice, and Score questions.
How does billing work?
A successful playground or API run costs one credit in this deployment. The interface shows that cost before you run, and failed upstream calls are reversed.
Can I move from testing to production?
Yes. Save a decision in the playground, process a file in Batch, or use the API guide before integrating.