{"slug": "jevlish-a-javascript-front-end-for-jev", "title": "Jevlish: A JavaScript front end for Jev", "summary": "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.", "body_md": "# Introduction\n\njevlish 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.\n\n## What it solves\n\n[Section titled “What it solves”](#what-it-solves)\n\nThe 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.\n\njevlish expresses those operations as conditions, filters, rankings, and choices. Exact checks remain TypeScript functions. Semantic checks remain plain-language Jev questions.\n\n## How it works\n\n[Section titled “How it works”](#how-it-works)\n\n1. `given` ,`from` , and the question builders create a lazy expression. Building it sends nothing.\n2. `.plan()` shows the state and questions that would leave the process.\n3. `await` or`.run()` folds code predicates, compiles the remaining Noul, Score, and Choice questions, and asks Jev.\n4. The acceptance policy turns model probabilities and confidences into `decided` or`uncertain` judgments.\n5. The result retains the requests, answers, local predicate outcomes, usage, cache status, and policy as evidence.\n\n## One decision\n\n[Section titled “One decision”](#one-decision)\n\n`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`.\n\nThe 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.\n\n## Jev vocabulary\n\n[Section titled “Jev vocabulary”](#jev-vocabulary)\n\n- A string condition or `means(...)` compiles to a Jev**Noul** question.\n- A `scale` compiles to a**Score** question.\n- `chooseFrom` compiles to a**Choice** question and maps the answer back to one of your objects.\n- `ask` sends related Noul, Score, and Choice questions about one subject together.\n- A **Sense** is a configured set of`given` ,`from` , and`grade` verbs bound to one runtime.\n\nJevlish uses the TypeSafe/Jev SDK. That is why the environment variable is `TYPESAFE_API_KEY` and the default transport is `TypeSafeClient`.\n\n## Where to go next\n\n[Section titled “Where to go next”](#where-to-go-next)\n\n- [Install and configure](https://jacobgoldfarb.github.io/Jevlish/start/install/) gets a key into the process and explains the shared Sense.\n- [Quickstart](https://jacobgoldfarb.github.io/Jevlish/start/quickstart/) builds one decision and one ranked query line by line.\n- [Support desk](https://jacobgoldfarb.github.io/Jevlish/examples/support-desk/) runs the same domain as a complete pipeline.\n- The guides cover each verb in turn, starting with [Judging one thing](https://jacobgoldfarb.github.io/Jevlish/guides/given/) .\n- 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.", "url": "https://wpnews.pro/news/jevlish-a-javascript-front-end-for-jev", "canonical_source": "https://jacobgoldfarb.github.io/Jevlish/", "published_at": "2026-09-22 21:40:53+00:00", "updated_at": "2026-09-22 21:53:51.086946+00:00", "lang": "en", "topics": ["ai-tools", "developer-tools", "large-language-models", "ai-agents"], "entities": ["Jevlish", "Jev", "TypeSafe", "TypeScript", "TypeSafeClient", "TYPESAFE_API_KEY"], "alternates": {"html": "https://wpnews.pro/news/jevlish-a-javascript-front-end-for-jev", "markdown": "https://wpnews.pro/news/jevlish-a-javascript-front-end-for-jev.md", "text": "https://wpnews.pro/news/jevlish-a-javascript-front-end-for-jev.txt", "jsonld": "https://wpnews.pro/news/jevlish-a-javascript-front-end-for-jev.jsonld"}}