Jev Explained.

    Esc Close⌘ / Ctrl + K
    EN

    Independent field guide

    Jev AI,
    explained.

    The independent guide to a different kind of AI. Understand what Jev does, find where it fits, and turn your first question into a working application.

    Understand Jev Make your first request

    Choice · Score · Noul

    STATE → DECISION

    Input01

    “My integration keeps failing. Can someone help me fix it?”

    JevSystem One
    Choice

    Which team should handle this?

    Structured answer02

    "technical" Model output
    Application actionRoute or review

    Illustrative example · not a live API response

    Typed decisions Choice · Score · Noul

    Text in, structure out Keep your code in control

    An independent perspective Examples, sources & limitations

    01 / Start with the basics

    What is Jev AI?

    Jev AI is TypeSafe AI’s System One model for structured decisions. You provide context, called state, and typed questions. Jev returns choices, scores, or yes/no probabilities that your software can use directly. It does not write a reply or carry out an action. Your code validates the decision, applies thresholds, and decides what to do next.

    Think of a customer message about a broken integration. Instead of asking a model to compose a support email, ask which team should receive the ticket. Jev chooses from the options you supplied; your application routes the ticket or sends it for human review.

    TypeSafe AI · System One

    02 / Choice, Score, Noul

    Three ways to ask.

    Ask a narrow question, choose the right answer type, and let ordinary code handle the action. You can ask several questions about the same state in one request.

    01

    Choice

    Pick one option.

    Classify a ticket as billing, technical, or sales. Receive a selected option, option probabilities, and confidence.

    choice: "technical"
    02

    Score

    Rate against clear levels.

    Define ordered levels such as calm, frustrated, and very angry. Read the score, level probabilities, and confidence.

    score: number
    03

    Noul

    Estimate a yes/no probability.

    Ask whether a message is urgent. The result is a probability between 0 and 1; your code chooses an action threshold.

    noul: 0…1

    03 / Guides

    One practical learning path.

    04
    01

    Find a useful task

    Six examples, from ticket classification to agent routing.

    Read the guide     02

    Understand the cost

    Input-token billing, with transparent cost examples.

    Read the guide     03

    Make a first request

    From an API key to a typed answer you can read.

    Read the guide     04

    Know the boundaries

    Failure modes, language support, and human review.

    Read the guide

    Where Jev fits

    Use Jev for narrow judgments inside a larger application: selecting a route, checking relevance, or assessing a criterion. Your application still owns retrieval, exact calculations, access control, and execution.

    Use cases

    Where to use another tool

    Use a generative model to draft a reply, a parser to extract exact fields, and normal code for arithmetic. A well-formed output is not a guarantee of a correct judgment.

    Limitations

    Understand it. Build with it.

    Start with one useful decision.

    Read the short setup guide, send a small request, and inspect the result before putting it into a workflow.

    Get started

    Reviewed: · Applies to: Jev 1.13.0