Jevlish: A JavaScript front end for Jev

Jevlish, a new JavaScript front end for the Jev judgment system from TypeSafe, has been released to bring Jev judgments into ordinary TypeScript business logic through `given` and `from` verbs. The library wraps the official Jev SDK, which is shaped like an LLM SDK, and instead expresses application operations as conditions, filters, rankings, and choices, compiling string conditions and `means(...)` into Jev Noul questions, `scale` into Score questions, and `chooseFrom` into Choice questions. Jevlish uses the TypeSafe/Jev SDK, requiring the `TYPESAFE_API_KEY` environment variable and defaulting to the `TypeSafeClient` transport.

Introduction jevlish brings Jev https://docs.typesafe.ai judgments into ordinary TypeScript business logic. Use given to judge one value and from to filter or rank a collection. What it solves Section titled “What it solves” what-it-solves The official Jev SDK is shaped like an LLM SDK: build a request, send it, and read the response. That is useful when the response goes to a person. In application logic, the response usually decides what code does with a value it already has—whether a ticket escalates, which rows a query keeps, or who gets assigned. jevlish expresses those operations as conditions, filters, rankings, and choices. Exact checks remain TypeScript functions. Semantic checks remain plain-language Jev questions. How it works Section titled “How it works” how-it-works 1. given , from , and the question builders create a lazy expression. Building it sends nothing. 2. .plan shows the state and questions that would leave the process. 3. await or .run folds code predicates, compiles the remaining Noul, Score, and Choice questions, and asks Jev. 4. The acceptance policy turns model probabilities and confidences into decided or uncertain judgments. 5. The result retains the requests, answers, local predicate outcomes, usage, cache status, and policy as evidence. One decision Section titled “One decision” one-decision means ... defines a reusable Noul question with an explicit boundary. given ticket supplies the subject. .seenAs ... controls what leaves the process; predicates and handlers still receive the complete Ticket . The branch has three outcomes. do handles true, otherwise handles false, and whenUncertain handles an answer that did not meet the policy. A false code predicate under and settles the condition locally, so a closed ticket sends no request. Jev vocabulary Section titled “Jev vocabulary” jev-vocabulary - A string condition or means ... compiles to a Jev Noul question. - A scale compiles to a Score question. - chooseFrom compiles to a Choice question and maps the answer back to one of your objects. - ask sends related Noul, Score, and Choice questions about one subject together. - A Sense is a configured set of given , from , and grade verbs bound to one runtime. Jevlish uses the TypeSafe/Jev SDK. That is why the environment variable is TYPESAFE API KEY and the default transport is TypeSafeClient . Where to go next Section titled “Where to go next” where-to-go-next - Install and configure https://jacobgoldfarb.github.io/Jevlish/start/install/ gets a key into the process and explains the shared Sense. - Quickstart https://jacobgoldfarb.github.io/Jevlish/start/quickstart/ builds one decision and one ranked query line by line. - Support desk https://jacobgoldfarb.github.io/Jevlish/examples/support-desk/ runs the same domain as a complete pipeline. - The guides cover each verb in turn, starting with Judging one thing https://jacobgoldfarb.github.io/Jevlish/guides/given/ . - The Reference https://jacobgoldfarb.github.io/Jevlish/reference/ is generated from the root package entry point. Advanced subpath APIs are introduced in the Runtime https://jacobgoldfarb.github.io/Jevlish/guides/runtime/ , Testing https://jacobgoldfarb.github.io/Jevlish/guides/testing/ , and Running https://jacobgoldfarb.github.io/Jevlish/guides/running/ guides.