100% free, forever — no paywall, no trial, no card

The new way to become a software engineer.

A structured, hands-on AI engineering curriculum — from your first line of code to shipping AI-native products. Pick a career path, learn lesson by lesson, prove what you know with quizzes, and build artifacts you can show.

Free forever · No experience needed · Learn at your own pace

The curriculum by the numbers

523
Hands-on lessons
20
Curriculum phases
12
Learning paths

6 career routes + 6 topics

373
Knowledge-check quizzes
250
Glossary terms
How it works

From zero to hired, in three moves

Every career route is the same loop: pick it, work it, prove it.

01

Pick a career path

Choose from six career routes — applied AI engineer, data, evals, DevRel, agentic, forward-deployed — each with a clear outcome and the exact lessons to get there.

02

Learn lesson by lesson

Work through focused, hands-on lessons in order. Every lesson is one idea with working code — no 40-minute videos to sit through.

03

Prove it with quizzes

Check yourself with pre/post quizzes on each lesson and finish every stage by building the artifact — working code you can show a hiring manager.

Twelve paths, one curriculum

Career routes take you from fundamentals to a portfolio artifact; topic paths go deep on one subject — all drawing from one shared lesson corpus.

Agent Skills Engineering
Topic
Build, route, secure, evaluate, package, and verify Agent Skills in real hosts.
~10h5 lessons
Agent Systems Engineering
Career route
Engineer tool-using agent loops with explicit context, memory, orchestration, safety, evaluation, and production control.
~14h14 lessons
AI Data Systems
Career route
Build reliable data, feature, embedding, retrieval, evaluation, and observability pipelines for AI systems.
~15h11 lessons
Developer Experience and Education
Career route
Build credible integrations, examples, and reusable agent packages, then turn developer friction into clearer tools and teaching.
~15h11 lessons
AI Evaluation and Reliability
Career route
Measure model and agent behavior, expose failure modes, instrument the runtime, and build release and incident controls around evidence.
~13h12 lessons
LLM Product Engineering
Career route
Turn language-model capability into evaluated, safe, cost-aware product behavior that can survive production traffic.
~15h12 lessons
Building and Deploying AI Applications
Topic
Build an AI feature from prompt and structured output through retrieval, evaluation, production serving, observability, and release.
~13h12 lessons
Customer AI Deployment
Career route
Discover a customer workflow, reduce its riskiest assumptions, and carry a useful AI system through measurement and rollout.
~14h12 lessons
Model Context Protocol (MCP)
Topic
Build, secure, verify, and operate stateless MCP systems from JSON-RPC envelopes through conformance release gates.
~23h17 lessons
Product Judgment and Delivery
Topic
Turn evidence into outcomes, assumptions, testable slices, executable specifications, measurement plans, and owned feedback loops.
~9h8 lessons
Software Engineering Fundamentals
Topic
Build the repository, debugging, testing, interface, security, release, and operational foundations AI systems depend on.
~12h13 lessons
Agent-Assisted Engineering
Topic
Frame, plan, execute, delegate, verify, review, and improve coding-agent work inside real repositories.
~15h16 lessons
The practice layer

More than a wall of links

The curriculum itself is open — but the free upstream site is a static list of links with no accounts, no progress, and no guidance. The New Engineer wraps the same content in a practice layer:

Progress tracking

A free account remembers every lesson you finish and every quiz you score, across every path you follow. Come back exactly where you left off.

Placement quiz

Not sure where to start? A short placement quiz points you at the right phase for what you already know instead of lesson one.

AI tutor

Stuck on a concept? Ask for a hint, a rephrase, or a worked example without ever leaving the lesson you're reading.

Frequently asked questions

The honest answers to the questions everyone asks first.

Yes — 100% free, forever. No paywall, no premium tier, no credit card, no trial clock. The curriculum is open source (MIT) and The New Engineer has no billing at all: the free account exists so your progress and quiz results can be saved, nothing more.

Ready when you are

Create a free account and start your first lesson in minutes — no card, no trial clock, nothing to cancel.