I built Agent Handoff Gate with typesafe Jev An experimental protocol for AI agents to verify worker evidence before handing results back to the lead. Less blind trust, fewer useless review loops. github.com/zsoXi/agent-ha…
Primitives
Entry type
The value shapes accepted throughout a request — string, object, array, or null — for state, instructions, and criteria fields.
- Category
- Primitives
- Also known as
- —
- Related terms
- 5
- Directory entries
- 2
- Docs
- docs.typesafe.ai
- Added
- 2026-09-24
Definition
Every field in a question is an entry type: a string, an object, an array, or null. State, instructions, option descriptions, score levels, and Noul criteria all accept the structured forms, which is what makes JSON taxonomies, schemas, and example sets passable without prompt string-building.
The flexibility is a design tool, not a requirement. The docs recommend strings for short unambiguous questions and structure where data or contrast needs its own field.
Tagsprimitivesapi
Related terms
Definitions that connect to this one.
StateThe content a request asks Jev to evaluate: a string, a named object, or an array of messages, shared by every question in the request.Core ConceptsInstructionsThe field that states what a question should judge; accepts a string, an object, or an array for extra structure.PrimitivesCriteriaThe 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.PrimitivesNull criteriaPassing null as a Choice option description when the option name needs no extra explanation.Primitives
From the directory
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
The raw HTTP contract behind every SDK: POST a state plus typed noul, choice, and score questions to /v1/systemone, and get one answer per question, with error codes and retry guidance.
Sites & GuidesDocs#official#docs#api
Official
From the community
Posts from builders shipping with Jev right now.
Agent Handoff Gate: agents verify what they hand off
A local Telegram analyzer with Jev as the classifier
I vibe-coded this simple, open-source and local Telegram content analyzer using Jev as a classifier. Jev Classifier • jevclassifier.vercel.app Export your channel data as JSON and it will analyze each post's intent, quality, sentiment, and reaction tone and if it's a DM/Group 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
A Krunker-inspired FPS, decided by Jev
Maybe I’m just washed, but Jev is beating me at my own game. Built a Krunker-inspired FPS where you 1v1 Jev. Try it out yourself: jev-arcade.vercel.app/duel
@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
Pixel art out of 256 multiple-choice questions
I turned @typesafeai Jev model into a pixel art model. 256 multiple choice questions, one per pixel, plus refinement passes. These were the best results out of the bunch I tested. Code: github.com/Wizhill05/type…
@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 Elixir port of the official SDK
[Announcing] TypeSafe SDK - Jev, the first System One model from TypeSafe forum.elixirforum.com/t/76700 #ElixirLang #MyElixirStatus
jod: Zod validates data, Jev judges it
Zod validates data you already understand. Jev judges data you don't. jod is the seam: your state validates locally and for free, every question goes out in one parallel request, and typed answers come back. github.com/mateonunez/jod
