typesafe-tutorial
Deno Jupyter notebooks teaching TypeSafe System One from core concepts through patterns and cookbooks.
This repository is mostly documentation or write-up rather than runnable code.
Overview
typesafe-tutorial is a set of notebooks written while learning TypeSafe's System One models in preparation for a conference talk. Lessons run in Deno's Jupyter kernel inside VS Code, with a TypeSafe key in a .env file.
The material is organized into numbered core-concept lessons (what a System One model is, the primitives, structure, confidence), numbered pattern lessons covering the four architectural patterns from TypeSafe's docs (fan-out, confidence-gated routing, composite scoring and intent routing), and unnumbered cookbooks by category (self-consistency, batching, how-to, extraction, classification and integrations). A glossary, resource list and research notes accompany them. A contributing guide explains conventions for adding lessons and cookbooks, and a resources file lists the primary sources each lesson is grounded in.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Other | Teaching examples of Choice, Score and Noul questions across patterns | — |
How it works
- Install Deno and its Jupyter kernel.
- Add a TypeSafe key to .env.
- Work through lessons in order.
- Use cookbooks as reference.
Strengths
- Structured, sequential learning path.
- Covers official patterns with runnable code.
Caveats
- Requires Deno, VS Code Insiders and a TypeSafe key.
- Personal learning material.
Getting started
Install Deno, run deno jupyter --install, add TYPESAFE_API_KEY to .env, and open a lesson in VS Code.At a glance
- Type
- Project
- Status
- prototype
- Language
- TypeScript
- Runtime
- Deno Jupyter notebooks
- Has code
- yes
Use cases and integrations
How curated lists describe it
Notebooks built while learning TypeSafe AI.
wh000wh000/awesome-jev-live
Frequently asked questions
What does it cover?
Core concepts, the four official patterns and cookbooks by category.
What do I need?
Deno v2+, its Jupyter kernel, VS Code with Jupyter, and a TypeSafe key.
Is it ordered?
Lessons are numbered 1 to 9; cookbooks are reference material.
Related projects
- Building with Jev★ 155
Agent skill for writing and improving programs that call Jev: question design, state structure, thresholds and diagnosing wrong answers.
Agent skillproduction Server behind api.typesafe.pro, a free anonymous System One-compatible endpoint that forwards to TypeSafe on the operator's key.
ServiceproductionPortable Agent Skill teaching coding agents to use Jev as a bounded judgment layer, plus an optional MCP bridge.
MCP serverbetaTypeScriptIndependent agent skill that makes a coding agent design, build, test and tune a bounded Jev decision layer with a contract first.
Agent skillbetaAgent skill that guides you in finding, designing and testing Jev decision loops, including when to keep logic in code.
Agent skillbetaBrowser form for building Jev requests from pasted text without hand-writing JSON, then rerunning to see how steady the answers are.
ProjectbetaJavaScript