Do I need to pay for two API keys to follow along?

Only the TypeSafe key is required from Level 0 on. The LLM half in later levels accepts any LiteLLM string, including free tiers and local models, and the written levels read fine without any key.

How much time does the whole course take?

About 65 minutes of reading plus running each paired example, or one level a day. Level 10 alone is estimated at 15 minutes with its capstone project, tests, and evals.

How is this different from reading the API docs?

Each level pairs one idea with a runnable script isolating it, ending in a capstone structured as a shippable package where the lesson explains the unit-test versus eval split.

What if my provider's free tier disappears mid-course?

The README warns free tiers shift often and points at each provider's own pricing page. Only the example env var names are stable, and the local model path needs no key at all.

How do I set up and run the first example?

Install uv, run uv sync, copy .env.example to .env and fill in your keys, then run uv run examples/00_hello_world.py. A probability and a millisecond timing mean you are set up.

What is the difference between the tests and evals directories?

tests/ holds fast, free, mocked unit tests for the capstone, run with uv run pytest. evals/ runs quality checks against a golden dataset using real API calls and tracks them over time rather than passing or failing.

What is in the capstone package?

Level 10's pipeline ships as an importable package with client.py, pipeline.py, and cli.py, structured like a real project so it can be shipped rather than only read.

CommunityJev Benchmarks & Evaluations

Jev Crash Course — nadeemcite

Eleven-level Jev course from hello-world to a ticket-triage capstone, pairing short lessons with runnable scripts against the live API and using LiteLLM so the writing half works with any provider.

See highlights

Open github.com

Stars: 1
Language: Python
License: MIT
Published by: Community
Author: nadeemcite
Last verified: Oct 2026

nadeemcite/jev-crash-course

User repository on GitHub

View on GitHub

An 11-level crash course on Jev, TypeSafe AI's System One decision model — runnable examples against the real API, plus a capstone project with unit tests and evals. Works with any LLM provider via LiteLLM.

Forks: 0
Last pushed: Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

About this project

Traditional software can only handle the branches you hardcoded. Agentic systems hand every step to an LLM — flexible, but slow, expensive, and hard to predict. Smart software is the middle path: a fast, cheap decision model at each branch point, with the LLM reserved for the one step that actually needs to write something. That third column is what Jev is for.

Quoted from the project's README. Read the full README.

Tagscommunity github

Works forJev for Evaluation

Used inJev for Software & DevTools

Languages: Python

Highlights

Levels progress through primitives, the raw API, Jev-versus-LLM timing, agent loops, and confidence gating.
Setup is dependency sync plus a .env with keys; the hello-world script confirms a probability and timing output.
Capstone ships as an importable package with unit tests run mocked and evals tracked against goldens.
A dedicated limits and skepticism level covers where the decision-model pattern breaks down.

Watch out

Runnable examples need a requested TypeSafe key, and free-tier provider options shift often; the written levels stand alone without one. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

Other listings of this project

Forks and copies of this project in the directory. This entry is the canonical one.

jev-crash-course

Eleven-level Jev crash course from zero with runnable examples, LiteLLM write-half, and a ticket-triage capstone with tests and evals.

Jev Benchmarks & Evaluations#community#github

Community

nadyth/jev-crash-coursePython

More Jev resources like this

jev-sim

Wire-compatible Jev re-implementation reading typed decisions from an LLM's next-token logits, plus a reproducible JevBench-based comparison of that approach against Jev on identical items.

Jev Benchmarks & Evaluations#community#github

Community

dashbi1/jev-simPython

apple-silicon-systemone-benchmark

Native Apple Silicon harness comparing local decision models through one decision interface, running models serially and emitting an offline dashboard with latency and accuracy.

Jev Benchmarks & Evaluations#community#github

Community

Giamme/apple-silicon-systemone-benchmarkPython

jev-crash-course

Eleven-level Jev crash course from zero with runnable examples, LiteLLM write-half, and a ticket-triage capstone with tests and evals.

Jev Benchmarks & Evaluations#community#github

Community

nadyth/jev-crash-coursePython

SREGym

338

SREGym stands up live Kubernetes clusters so SRE agents can be evaluated against 90 fault scenarios, including OS-level faults and metastable and concurrent failures, in containers that cannot see the grading logic.

Jev Benchmarks & Evaluations#community#jevbest

Community

SREGym/SREGymPython

tasksource

217

Standardizes hundreds of public datasets into interchangeable multiple-choice, classification, and token-classification templates, and deterministically recasts them into typed choice, score, and noul decision requests.

Jev Benchmarks & Evaluations#community#jevbest

Community

sileod/tasksourcePython

hev reranker

A BEIR reranking recipe that asks up to 30 parallel Noul relevance questions in one Jev state, with RESULTS.md against cross-encoders and hosted rerankers.

Jev Benchmarks & Evaluations#community#evaluation#python

Community

hev/rerankerPython

Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai