@vercel 's fx uses Jev to review every command. @rauchg says it's up to 18x faster than GPT Luna and more accurate. @JoshARosen built Foreman, where Jev watches coding agents for drift, missed tests and getting stuck. @shantanugoel's Hermes agent installed an "ask Jev" skill on Show more
Primitives
Instructions
The field that states what a question should judge; accepts a string, an object, or an array for extra structure.
- Category
- Primitives
- Also known as
- —
- Related terms
- 5
- Directory entries
- 2
- Docs
- docs.typesafe.ai
- Added
- 2026-09-24
Definition
Instructions are where your evaluation logic lives. Write a clear, specific question or a statement for the model to judge, and state the exact condition rather than relying on implied intent — Jev answers the question you wrote, not the one you meant.
A string is enough for most questions. An object or array can hold the question in one field and the data it refers to in others, which keeps long context, examples, and values from your code out of a string template.
Tagsprimitivesdesign
Related terms
Definitions that connect to this one.
CriteriaThe possible answers for a question: a map of options for Choice, an ordered list of levels for Score, or true/false for Noul.PrimitivesStructured instructionsPutting the question in one field and its supporting data, examples, or focus notes in others instead of one long string.PrimitivesQuestion IDThe key you choose for a question; answers come back under the same key, and the ID is never sent to the model.PrimitivesBacktick path referenceNaming a state field inside instructions with backticked dot-and-index paths, such as `ticket.messages[0].text`.PrimitivesLiteral readingJev answers the question you wrote, not the one you meant; scoping words, negations, and implied conditions are read at face value.Evaluation & Training
From the directory
The three TypeSafe question types, the typed answers they return, how to choose between them, and how to ask several in a single call.
Practices & PatternsDocs#official#primitives#choice
Official
Instructions, option descriptions, score levels, and noul criteria all accept JSON, so you can label question parts, pass schemas and taxonomies, and keep candidate paths alive.
Practices & PatternsDocs#official#primitives#architecture
Official
From the community
Posts from builders shipping with Jev right now.
Vercel's fx safety reviewer, measured at 18× faster
A game where you race Jev at spotting slop
A small game to show how fast TypeSafe's Jev actually is. Try to beat it at detecting a spam message beatjev2it.jlamberts86.workers.dev
Jev plays itself at 3D chess
got access to jev and instead of doing anything useful i made it play itself at 3D chess same model on both sides, slowly developing beef with itself you can watch jev vs jev or jump in and ruin its day chess-jev.loomens.com
@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
dmx.to reshapes the timeline in plain language
the next version of dmx.to will let you fully customize the timeline both with dumb rules (how did i not think of these until now lol) and smart rules using Jev (BYOK also supports vercel gateway) 🤓 you can filter 3 lvls of usefulness, tweet types, topics, etc
GPT and Jev compared live
Built a live tool using @typesafeai JEV ! See live comparison btwn GPT & JEV at gptvsjev.vercel.app Get benchmarks like Money Spent ! Time Taken ! Tokens Used!
LitJev: Jev-style decisions on any local LLM
开源了 LitJev：我们对 Jev 类型化决策 API 实现方式的猜想，可接入任意现成 LLM。 小测试：Qwen3.8-27B，10 道 MMLU-Pro 一次完成，0.3 s。比让模型只生成答案快 2.9x；比生成完整 schema JSON 快更多（显然）。更多测试马上来。 非官方，基于公开信息。