jev
tool judged 52% likely a named technique or architecture
See how it has spread across media tiers
Mentions over time
Table view
| Week | Articles | Sources |
|---|---|---|
| 2026-W37 | 2 | 2 |
| 2026-W38 | 1 | 1 |
| 2026-W39 | 3 | 1 |
| 2026-W40 | 9 | 4 |
| 2026-W41 | 1 | 1 |
In their words
I went through how people actually wire Jev into their agents.
With a VENICE_API_KEY , it asks Venice's JEV decision model (in beta).
Small local decision models such as Jev and Laya can classify a tool call into a fixed set of choices.
We were excited to evaluate Jev when it was released, but unfortunately it underperformed our baseline.
"Decision models" (TypeSafe's Jev API shape, now served locally by both Ollama and llama.cpp) take a state plus typed questions and return a probability for every option in one forward pass.
One of them is autotrust/JEV-27B-VL , a 27B vision-language model that emits a typed verdict with a confidence score instead of a paragraph.
Release: llm-openai-decisions 0.1a0 OpenAI released their new Jev-style Decisions API , as previously announced at last week's DevDay.
JEV is getting a lot of attention right now.