What it is
A curated collection of resources for developers using TypeSafe's Jev, a System One model that returns calibrated probabilities for typed questions. Includes SDKs, live demos, agent tools, and independent evaluations.
How it uses Jev
Jev answers typed questions (Choice, Score, Noul) on a given state, returning probabilities. Application code uses these probabilities to make routing or escalation decisions, as shown in the support-ticket example.
Primitives:choicescorenoul
Technique worth stealing
Separate rule-based logic (code), bounded judgment (Jev), and open-ended generation (text LLM).
Try it
Explore live builds or copy the runnable example from the README.
Evidence
Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.
- Jev-centricyes0.86
- Shows a System One patternno0.17
- Handles uncertaintyno0.04
- Measuredno0.08
- Runnableno0.35
- Worth recommendingunclear0.51
- Model replicano0.05
- Problem scopescore on a 0–2 scale1.02
- About Jevyes0.97
Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 23 Sept 2026.