Meet Jev
A System One model for software
Traditional LLMs mainly generate text for people to read. Jev focuses on decisions software can consume directly: send one state and typed questions, then get structured results your code can branch on, sort, and route.
Typed results
Parallel decisions
Probability and confidence
Quickstart
Validate one decision in the playground
The Playground is the fastest way to understand Jev’s inputs and outputs. Once the question is useful, create an API key and connect it to your product.
- 1
Open the playground
Sign in, open the Jev AI playground, and enter a real piece of business state.
- 2
Prepare state
Use text, a JSON object, or an array of text to provide the context the decision needs.
- 3
Add questions
Choose choice, score, or noul. You can mix all three types in one request.
- 4
Connect your code
Create an API key in your workspace and call the production endpoint with an SDK or REST.
Input
Give state the context the decision needs
State is the content every question reads. Use a string for a simple case; use a JSON object when the decision needs a ticket, order, and policy together.
textNatural language, a ticket, or a message
objectStructured records and nested fields
arrayContext made of multiple text items
Current input boundary: Jev accepts text, JSON objects, and arrays of text. Image, audio, and video inputs are not supported yet.
Question types
Compose decisions from small questions
Each question should ask one specific, well-scoped thing. Multiple questions are evaluated in parallel against the same state, so you do not need to chain calls just to split a decision.
Choice
Use Choice to select one answer from predefined options. Give each option a name and optional description; add an other or none-of-the-above option when unknown cases are possible.
Score
Use Score for descriptive levels on a spectrum, such as severity or satisfaction. Levels are ordered low to high; the returned score is probability-weighted and can fall between levels.
Noul
Use Noul for a yes / no judgment. Noul is the probability that the answer is yes, not a second confidence field; use criteria to define what true and false mean when needed.
Output
What the response gives your code
result.answers uses the same question IDs you sent. Typed output guarantees the field shape, but your application should still set thresholds by risk and keep a human-review path where appropriate.
- answers: Choice returns the selected choice, probabilities, and confidence; Score returns score, legend, per-level probabilities, and confidence; Noul returns noul.
- usage: Includes input_tokens and output_tokens, and may include cost in USD.
- elapsedMs: Time from sending the request to receiving the result, including validation—not pure model inference time.
Probability and confidence are signals for automation, not a guarantee of business accuracy. Use higher thresholds or human review for high-risk actions.
Integration
Put the decision back in your service
After validating a workflow in the console, create an API key in your workspace. Production requests use three top-level fields: state, model, and questions.
curl -X POST https://thejevai.com/v1/systemone \
-H "Authorization: Bearer <API_KEY>" \
-H "Content-Type: application/json" \
-d '{
"model": "typesafe/jev-1.13",
"state": "A customer has tried to connect Stripe for three days.",
"questions": {
"urgent": {
"type": "noul",
"instructions": "Does this message express urgency?"
}
}
}'Keep your API key in a server-side environment variable. Never put it in browser code or commit it to your repository. Use the official docs for the complete field reference, SDKs, and current model details.
What to do next
Start with one low-risk, well-scoped decision. Then connect it to routing, queues, guardrails, or an agent workflow as you learn where the signal is useful.