TypeSafe AI Introduces Jev: Structured System One Decisions Instead of Text Generation

ArticleTypeSafe AITool

TypeSafe AI has launched Jev, described as the first System One model designed to return fast, structured decisions directly for code consumption without generating or parsing text.

Key points

  1. Jev evaluates typed questions against a state and directly returns structured values and probability distributions without text generation or parsing.
  2. The system provides three modular primitives: Choice (selection from a list with probabilities and confidence), Score (rubric scoring with probabilities and confidence), and Noul (truth value between 0 and 1).
  3. Multiple question types can be batched into a single API call, evaluating in parallel and in isolation against the same state without causing context rot.
  4. Architectural guidance recommends decomposing complex reasoning into atomic gut-check questions and combining outcomes using deterministic code logic.

Why it matters

Integrating generative LLMs into programmatic workflows usually requires forcing structured JSON outputs and parsing strings. TypeSafe addresses this friction by producing typed values, probability distributions, and confidence scores designed specifically for routing and branching in software.

Analysis

By focusing on fast deterministic primitives rather than conversational output, TypeSafe targets high-throughput decision-making pipelines. Decomposing complex evaluations into atomic questions handled in parallel lets developers adjust weighting through code coefficients rather than fragile prompt engineering.

Found in

Summary generated by AI (Gemini 3.8 Flash, 29 September 2026). It may contain errors – the original source is authoritative.

Similar in content, found by the AI search.

  • Article:vercel.com

    Jev Breaks Adoption Records on Vercel AI Gateway

    TypeSafe AI's Jev model has become the fastest-adopted model in Vercel AI Gateway history, reaching nearly 13% of paid teams within its first 24 hours.

    AI & LLMs· Announcement

  • Video

    Video:CURT

    Jev Design Patterns: Operating Workflows with Decision Models

    This video introduces Jev by TypeSafe, a specialised decision model designed for low-cost, low-latency micro-decisions rather than text generation. It covers three decision types, ten functional shapes, and four architectural design patterns through practical examples.

    AI & LLMs· Tutorial

  • X post:Ruben Hassid

    TypeSafe's Jev: Ultra-Fast AI Classification Without Chatbot Latency

    Ruben Hassid highlights Jev by TypeSafe as a fast, low-cost decision engine designed to bypass standard LLM text generation. Rather than generating word-by-word paragraphs, Jev answers predefined multiple-choice questions with a direct decision and confidence score. Hassid details how to integrate it into Claude Code and Codex for tasks like bulk contact classification.

    1.6kbookmarks112.5kviews

    AI & LLMs· Tool

  • X post:Guillermo Rauch

    Jev Becomes Fastest-Adopted Model in Vercel AI Gateway History

    Guillermo Rauch and Vercel reported that Jev, a probabilistic decision model by TypeSafe AI, saw record-breaking adoption on Vercel AI Gateway, reaching approximately 13% of paid teams within 24 hours.

    303bookmarks123.5kviews

    AI & LLMs· News

  • Link:Featherless.ai

    Simple Jev: Open-Source Decision and Classification Engine Using Model Logits

    Featherless.ai has introduced Simple Jev, an open-source implementation that turns open language models into structured decision engines. Instead of requiring a separate classifier head, it reads next-token logits for allowed labels and returns probabilities and choices directly as JSON.

    AI & LLMs· Tool

Let's talk about your project

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.