The Jev launch post
Diogo Almeida introduces Jev, TypeSafe’s structured decision model. Watch the launch film and explore the original thread for the model’s approach, examples and author-reported performance.
Latest addition
Source check
Recent activityA FIELD GUIDE TO JEV / VOL. 01
The best of Jev. Real projects, practical guides and ideas from across the internet.
Diogo Almeida introduces Jev, TypeSafe’s structured decision model. Watch the launch film and explore the original thread for the model’s approach, examples and author-reported performance.
TypeSafe’s official launch announcement introduces the lab and points builders to Jev. It includes Diogo Almeida’s launch film and original introduction.
TypeSafe announces public access to Jev without a waiting list. The official console is the starting point for trying typed decisions in your own application.
TypeSafe highlights Jev’s typed-output approach: applications provide state and questions, then act on probabilities, choices or scores. The linked announcement also covers the Venice API integration.
Start with the Launch Post. Explore four official signals.
107 resources
AI-assisted summaries and translations. Check original sources for context and performance claims.
Launch post: architecture, RLCD training, pricing, Doom and Wikiracing demos, FAQ.
JEVLAB ARTSource-linked curation
Shortest path from an API key to a typed decision.
JEVLAB ARTSource-linked curation
Introduction, primitives, patterns, cookbooks, HTTP API, and SDK references.
Source-linked curation
Official TypeSafe reference: Introduction.
Source-linked curation
Request and response contract for POST /v1/systemone.
Source-linked curation
Choice, Score, and Noul: the three question types and what they return.
Source-linked curation
Known failure modes of the current public model, documented by TypeSafe.
Source-linked curation
Speculative fan-out, confidence-gated routing, composite scoring, and intent routing.
Source-linked curation
Reproducible recipes: parallel questions, reranking, guardrails, citation checks, extraction, hierarchical classification.
Source-linked curation
The case for machine-native intelligence built for software, not conversation.
Source-linked curation
Published eval methodology and per-model results for System One workflows.
Source-linked curation
Official TypeSafe server. Builder demos live in the Show and Tell channel.
Source-linked curation
Paste a state, add questions, and see typed answers in the browser.
Source-linked curation
Official sync and async Python client. pip install typesafe-sdk.
Source-linked curation
Official interactive demo of speculative fan-out: many questions in one call, code keeps the relevant answers.
Source-linked curation
Product and research updates.
Source-linked curation
TypeSafe’s official launch announcement introduces the lab and points builders to Jev. It includes Diogo Almeida’s launch film and original introduction.
Source-linked curation
An unofficial Laravel package offering typed responses and test fakes for Jev integration.
JEVLAB ARTSource-linked curation
Fazt presenta las decisiones estructuradas de Jev con ejemplos de Snake y clasificación de solicitudes de soporte.

Source-linked curation
TypeSafe highlights Jev’s typed-output approach: applications provide state and questions, then act on probabilities, choices or scores. The linked announcement also covers the Venice API integration.
Source-linked curation
Leonardo Bissoli apresenta decisões estruturadas com Jev, incluindo confiança, limites e exemplos de uso em aplicações.

Source-linked curation
Official drop-in TypeSafeClient replacement backed by OpenAI, Anthropic, and compatible LLM APIs, for comparing Jev against chat models.
Source-linked curation
Curated list of official resources and community projects for TypeSafe, System One models, and Jev, with a GitHub Pages site.
JEVLAB ARTSource-linked curation
Official TypeSafe reference: SDE cascade.
Source-linked curation
A Go client for the TypeSafe API, aimed at developer tools and applications.
JEVLAB ARTSource-linked curation
Official TypeSafe reference: Legal.
Source-linked curation
Live verdict page: feeds Jev the day’s Florida Man, odd-news, politics and world headlines and asks all three primitives whether AI should kill us all, refreshed every ten minutes.
Source-linked curation
Official TypeSafe reference: Confidence.
Source-linked curation
Official TypeSafe reference: Function calling.
Source-linked curation
System-architecture skill for TypeSafe AI Jev/System One — find fuzzy semantic judgment and turn it into small Choice/Score/Noul primitives.
Source-linked curation
Official TypeSafe reference: Self-consistency: choices.
Source-linked curation
Official TypeSafe reference: Agent skill.
Source-linked curation
Browser-based request builder for the System One API: compose state plus typed Noul, Choice, and Score questions. Mock mode runs locally without an API key; Live mode requires your TypeSafe key and calls api.typesafe.ai directly. Generates typesafe_sdk Python. Includes companion Jev Suitability Test.
Source-linked curation
Official agent skill for Claude Code, Codex, and compatible agents: primitives, patterns, and how to structure evaluations.
JEVLAB ARTSource-linked curation
Official TypeSafe reference: Speculative fan-out.
Source-linked curation
A community post about using Jev to efficiently crawl job listings from company websites, significantly reducing time compared to an LLM.
Source-linked curation
Unofficial Elixir SDK for the TypeSafe AI API.
Source-linked curation
Official TypeSafe reference: Intent routing.
Source-linked curation
Official TypeSafe reference: State.
Source-linked curation
Discriminative Monte Carlo Tree Search using TypeSafe Jev System One Primitives and Gemini.
Source-linked curation
Official TypeSafe reference: Noul.
Source-linked curation
Diogo Almeida introduces Jev, TypeSafe’s structured decision model. Watch the launch film and explore the original thread for the model’s approach, examples and author-reported performance.
Source-linked curation
Official TypeSafe reference: System One.
Source-linked curation
Bug-hunting crawlers built using Unix-style primitives, designed for automated system analysis.
Source-linked curation
Official TypeSafe reference: API reference.
Source-linked curation
Official TypeSafe reference: Advanced: structure.
Source-linked curation
Official TypeSafe reference: AI primer.
Source-linked curation
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.
Source-linked curation
Official TypeSafe reference: Self-consistency: nouls.
Source-linked curation
Official TypeSafe reference: Re-ranking.
Source-linked curation
LegalForecast-MTD benchmark alpha and official evaluation workflows.
Source-linked curation
Community Java client for the TypeSafe System One API (unofficial).
Source-linked curation
Official TypeSafe reference: TypeSafe Python SDK.
Source-linked curation
Official TypeSafe reference: Date extraction.
Source-linked curation
Hosted typesafe-ai/jev for AI SDK evaluate calls, no TypeSafe waitlist required.
Source-linked curation
Official TypeSafe reference: JavaScript SDK.
Source-linked curation
Unofficial Go SDK for TypeSafe AI's Jev API.
Source-linked curation
A community guide outlining 10 steps to implement Jev for faster decision-making in AI agent systems.
Source-linked curation
Official TypeSafe reference: Classification using confidence.
Source-linked curation
Official TypeSafe reference: Double-checking citations.
Source-linked curation
Official TypeSafe reference: Choice.
Source-linked curation
Jev assists a Mac app by selecting relevant support articles from built-in documentation.
Source-linked curation
Official TypeSafe reference: Autoresearch feature discovery.
Source-linked curation
Official TypeScript/JavaScript client with inferred answer types. npm install @typesafe-ai/sdk.
Source-linked curation
Jev differs from LLMs by evaluating predefined decisions directly, enabling parallel processing of independent questions.
Source-linked curation
A setup using Jev and GrokBot to route AI agent tasks efficiently, reducing costs and execution time with a seven-step configuration process.
Source-linked curation
Official TypeSafe reference: Score.
Source-linked curation
Official TypeSafe reference: Confidence-gated routing.
Source-linked curation
Official TypeSafe reference: Structure recovery.
Source-linked curation
Unofficial Go SDK for the TypeSafe AI System One API — 1:1 parity with the official JS and Python SDKs. Not affiliated with TypeSafe AI.
Source-linked curation
Unofficial typed async Rust client for the TypeSafe System One API.
Source-linked curation
Guía del creador Fazt sobre el uso de Jev para decisiones tipadas, con una introducción y ejemplos de aplicaciones.
Source-linked curation