Skip to content
Open-source · Hands-on · Production-minded

Build reliable AI systems,
from prompt to production.

A practical engineering curriculum for building, evaluating, securing, and operating modern LLM applications.

27 core modules · Interactive labs and quizzes · Learn at your own pace

ai-engineering / roadmap

01 Design prompts with measurable contracts

02 Build secure retrieval and tool workflows

03 Evaluate quality, latency, and cost

04 Ship observable production agents

Your roadmap is ready
27Core modules
3Specialization tracks
100%Open source
LocalPrivate progress tracking

Choose the route that fits your goal

Whether you have a weekend or want a complete engineering foundation, begin with a focused route and expand when you need to.

A curriculum built around five engineering gates

The modules move from dependable model interactions to complete production systems. Each gate is a working-system exit criterion — the previous gate's failure mode is what forces the next one.

Gate 1Dependable model service

Make model behavior explicit, schema-valid, and safe against hostile input.

Gate 2Measurable quality

Trustworthy output is unmeasured output until it has an eval suite.

Gate 3External knowledge

Give models the right context, and prove retrieval is even needed.

Learn by building, not by collecting vocabulary

Understand the system

Incident stories and visual mental models show where data, trust, and tokens move.

Make the tradeoff

Focused questions turn abstract concepts into concrete engineering decisions.

Prove it works

Labs, tests, and interactive quizzes end in a small artifact you can actually ship.

Ready when you are

Start with a working environment.

Set up the repository, run your first examples, and begin Module 01.

Get started

Progress and XP stay in your browser via localStorage. No account, analytics service, or backend is required.