JEV LAB
Submit a find
English
English한국어日本語EspañolFrançaisDeutsch简体中文繁體中文PortuguêsBahasa IndonesiaไทยItalianoTiếng ViệtTürkçePolskiРусский

A FIELD GUIDE TO JEV / VOL. 01

SMALL
DECISIONS.
BIG
POSSIBILITIES.

The best of Jev. Real projects, practical guides and ideas from across the internet.

Explore the labGuides
1,195resources16languagesFind something
worth building.
IN THE SPOTLIGHT SOURCE: X
Gregor Zunic@gregpr07

Browser Use + Jev

Gregor Zunic's flight-search demo with a dynamic DOM action space.

Browser Use + Jev Explore this project
Source linked · creator-reported demoView on X

01 / A small decision engine. A whole new way to build.

103 resources / The collection

Reset filters

AI-assisted summaries and translations. Check original sources for context and performance claims.

LAB PICKOFFICIAL
TypeSafe AIDOCS

Quick start

Shortest path from an API key to a typed decision.

Start hereEnglish
Open original
LAB PICKOFFICIAL
TypeSafe AIWEB

Manifesto

The case for machine-native intelligence built for software, not conversation.

Start hereEnglish
Open original
LAB PICKOFFICIAL
TypeSafe AIDOCS

HTTP API reference

Request and response contract for POST /v1/systemone.

STATE → QUESTIONS → DECISIONSconst answer = await client.systemOne({
  state, questions
});
// intelligence, in your code.
Start hereEnglish
Open original
LAB PICKOFFICIAL
TypeSafe AIWEB

Playground

Paste a state, add questions, and see typed answers in the browser.

Start hereEnglish
Open original
LAB PICKOFFICIAL
TypeSafe AIDOCS

Primitives

Choice, Score, and Noul: the three question types and what they return.

STATE → QUESTIONS → DECISIONSconst answer = await client.systemOne({
  state, questions
});
// intelligence, in your code.
Start hereEnglish
Open original
LAB PICKOFFICIAL
TypeSafe AIDOCS

Cookbooks

Reproducible recipes: parallel questions, reranking, guardrails, citation checks, extraction, hierarchical classification.

STATE → QUESTIONS → DECISIONSconst answer = await client.systemOne({
  state, questions
});
// intelligence, in your code.
Start hereEnglish
Open original
LAB PICKOFFICIAL
TypeSafe AIDOCS

Jev 1.13 jaggedness

Known failure modes of the current public model, documented by TypeSafe.

STATE → QUESTIONS → DECISIONSconst answer = await client.systemOne({
  state, questions
});
// intelligence, in your code.
Start hereEnglish
Open original
LAB PICKOFFICIAL
TypeSafe AIDOCS

Documentation

Introduction, primitives, patterns, cookbooks, HTTP API, and SDK references.

STATE → QUESTIONS → DECISIONSconst answer = await client.systemOne({
  state, questions
});
// intelligence, in your code.
Start hereEnglish
Open original
LAB PICKOFFICIAL
TypeSafe AIDOCS

Introduction

Official TypeSafe reference: Introduction.

STATE → QUESTIONS → DECISIONSconst answer = await client.systemOne({
  state, questions
});
// intelligence, in your code.
Start hereEnglish
Open original
LAB PICK
typesafeWEB

Discord

Official TypeSafe server. Builder demos live in the Show and Tell channel.

Start hereEnglish
Open original
LAB PICKOFFICIAL
TypeSafe AIDOCS

Patterns

Speculative fan-out, confidence-gated routing, composite scoring, and intent routing.

STATE → QUESTIONS → DECISIONSconst answer = await client.systemOne({
  state, questions
});
// intelligence, in your code.
Start hereEnglish
Open original
LAB PICKOFFICIAL
TypeSafe AIWEB

Workflow evals

Published eval methodology and per-model results for System One workflows.

Start hereEnglish
Open original
LAB PICKOFFICIAL
TypeSafe AIDOCS

Smart home demo

Official interactive demo of speculative fan-out: many questions in one call, code keeps the relevant answers.

STATE → QUESTIONS → DECISIONSconst answer = await client.systemOne({
  state, questions
});
// intelligence, in your code.
Start hereEnglish
Open original
LAB PICK
typesafe-aiGitHub

TypeSafe agent skills

Official agent skill for Claude Code, Codex, and compatible agents: primitives, patterns, and how to structure evaluations.

Start hereEnglish
Open original
LAB PICK
typesafe-aiGitHub

System One adapter (Python)

Official drop-in TypeSafeClient replacement backed by OpenAI, Anthropic, and compatible LLM APIs, for comparing Jev against chat models.

Start hereEnglish
Open original
LAB PICKOFFICIAL
TypeSafe AIWEB

TypeSafe AI

Company homepage, waitlist, and product overview.

Start hereEnglish
Open original
OFFICIAL
TypeSafe AIDOCS

Intent routing

Official TypeSafe reference: Intent routing.

STATE → QUESTIONS → DECISIONSconst answer = await client.systemOne({
  state, questions
});
// intelligence, in your code.
Start hereEnglish
Open original
nshkrdotcomGitHub

typesafe_sdk

An idiomatic, type-safe Elixir port of the official TypeScript AI SDK (ai / ai-sdk) providing unified LLM integrations, streaming text and structured outputs, tool calling, and agentic workflows. Jev is their current flagship model and is the first System One model.

Start hereEnglish
Open original
OFFICIAL
TypeSafe AIDOCS

API reference

Official TypeSafe reference: API reference.

STATE → QUESTIONS → DECISIONSconst answer = await client.systemOne({
  state, questions
});
// intelligence, in your code.
Start hereEnglish
Open original

Privacy, on your terms.

Essential functionality works without analytics. Optional Google Analytics runs only with consent. We respect Do Not Track and Global Privacy Control. External X and YouTube embeds load only when you ask.