---
title: "Introducing System One Models & Jev"
description: "TypeSafe’s Jev gives up prose for typed probabilistic decisions, turning the model from a chatbot into a fast, fuzzy branch inside ordinary software."
author: "Paul Friedman"
kind: "link"
published_at: "2026-09-15"
url: "https://pau.fm/blog/2026/09/15/introducing-system-one-models-and-jev"
markdown_url: "https://pau.fm/blog/2026/09/15/introducing-system-one-models-and-jev.md"
canonical_url: "https://pau.fm/blog/2026/09/15/introducing-system-one-models-and-jev"
external_url: "https://typesafe.ai/blog/introducing-system-one-models-and-jev"
---

# [Introducing System One Models \& Jev](<https://typesafe.ai/blog/introducing-system-one-models-and-jev>)

> Think of Jev as a frontier-intelligence function call: unstructured state in, typed probabilistic
> decisions out.

Jev gives up free-form text and returns probabilities over types declared in advance. That sounds
narrower than a language model because it is, but the narrowness is the feature. Much of “AI-powered
software” asks a model to write a little JSON ceremony around a branch the program already
understands.

Type safety does not mean Jev “can’t hallucinate.” It cannot invent a fourth option, but it can
still confidently choose the wrong one. What it can do is avoid malformed answers and return a
decision in 70–500 milliseconds. The useful primitive is not a chatbot pretending to be an API. It
is a fuzzy `if` statement.