Jev just landed and the agent stack moved in three days. TypeSafe AI released Jev on September 15. It is built for the work agents actually do most of the time: choose the next tool, score a risk, decide whether to retry, or answer yes or no. Latency is under half a second. Show more
CommunityGuides & Articles
JEV: How It Works and What You Can Build
Riley Brown on a decision model that cannot write: a model router, Choice, Score, and Noul, then speed, cost, and where to get access.
- Category
- Guides & Articles
- Format
- Video
- Published by
- Community
- Author
- Riley Brown
- Added
- 2026-09-28
- Last verified
- 2026-09-28
Highlights
- The description frames Jev as a decision model that cannot write, but can route, classify, and filter.
- Chapters: model router at 2:08, what Jev is at 3:56, Choice, Score, and Noul at 5:19.
- Later chapters cover structured output, speed, and cost, then monitoring, context window, and how to get access.
Watch out
Chapter times are from the video description. This entry does not restate any benchmark numbers from the talk.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
YouTube: Riley Brown on a model that cannot write: routing, Choice, Score, Noul, then cost and access.
Hacker News: Vercel on using Jev for defined decisions and GPT-6 Astra when the job also has to write or use tools.
flashbrew4 pointsTypeSafe AI Jev vs. GPT-6 AstraRead the thread on Hacker NewsX: How the agent stack moved in Jev's first three days
YouTube: LangChain walks through Jev as a System 1 layer in an agent loop: model routing, auto mode for risky tools, and judged evals.
More like this
Joe Maddalone on using Jev for routing and filtering before a generative model, with demo code in a transcript-analyzer repo.
Guides & ArticlesVideo#community#video#routing
Community
KodeKloud on why a System One model returns calibrated probabilities, then a Papers, Please-style queue where Jev is compared with GPT-5.5 and DeepSeek.
Guides & ArticlesVideo#community#video#explainer
Community
A Krish Naik explainer on whether Jev replaces LLMs and where decision models fit next to generative models.
Guides & ArticlesVideo#community#video#explainer
Community
From the community
Posts from builders shipping with Jev right now.
Foreman keeps coding agents on task
I just open sourced Foreman: a software factory foreman built with @typesafeai's Jev. Coding agents work the factory floor. Foreman watches them, continuously assessing progress, completeness, tests, drift, and verification, and intervenes when needed. GitHub: Show more
Unclutter: an ad and slop blocker that runs on Jev
introducing Unclutter: a smart ad + slop blocker with Jev 🤓 it auto cleans up pages from slop elements: ⬖ ads ⬖ cookie banners ⬖ upsells ⬖ bs dialogs BYOK. open source + free, download below 👇
An open-source BS meter for debates and investor calls
🚨 Open Source Jev BS meter you can use this to analyze any debate / investor call / interview / sales pitch / podcast video fact check live , for example this dario interview cost 60 Jev calls / 111K tokens / $0.0047 github.com/ChetasLua/jevm…
🚨 I gave the Trump vs Kamala debate a live BS meter using Jev every sentence, both candidates, 5 yes/no questions each 1,191 Jev calls / 1.18M tokens / 415 ms median total cost : $0.0497 same questions for both, clips picked by one fixed rule, not a fact-check
A Jev-shaped model on Cerebras and Qwen
Built an alternative version of @typesafeai but on @cerebras with Qwen 3.8 27b. Similar quality, similar performance, but vastly different cost. TypeSafe was way cheaper, and did beat Qwen on performance. Closest we can get using LLMs I think. Source: github.com/iammrduncan/ty…
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x
Jev benchmarked on two public safety corpora
1/ Benchmarked TypeSafe's Jev on two public safety corpora. It doesn't generate text, it returns calibrated probabilities you threshold in code. 96.5% on prompt injection, all 662 messages in deepset/prompt-injections. No tuning. 325ms p50.
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x
An open 151M-parameter decision engine
TypeSafe AI came out of stealth with Jev, and access is behind a waitlist. I built an open source version Verdict (Open-jev) you can run right now in a browser tab: And its a real post trained model..(link in comments) It is a post trained 151M parameters model. ModernBERT-base Show more
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x