Part 1 · Course guide

AI Engineering: The Complete Course

3 min read·13 Oct 2026

Learn to build AI applications that keep working when real people use them.

Most courses stop when the demo works. This one starts there. Across 14 modules you build one product, a customer-support assistant for a fictional online store called BrightCart, and you take it all the way from a single model call to a deployed, tested, monitored service.

Who this course is for

You are…	Start at
New to programming, or new to Python	Module 0, then Module 1
Comfortable with Python	Module 0, then Module 2
A working developer who has built and deployed software	Module 0, skim Modules 3-6, then go deep from Module 7
A data scientist who knows ML already	Module 0, then Modules 1, 7-13

Every module's first page lists what you need to know before starting it, so you can check whether it is safe to skip the one before.

What you need

A Google account, to run code in Google Colab. Nothing to install.
One free API key, from Groq or Google Gemini, to use in Colab. Or no key at all, if you run a model on your own computer with Ollama and work in a code editor.

Setup takes about ten minutes: course-guide/02-setup-colab-and-llm-providers.md.

The modules

#	Module	What you add to BrightCart	Status
0	Quick Win	A first working model call	Ready
1	Programming Foundations	An API client with retries and safe secrets	Ready
2	Data Handling	Clean, validated help-centre documents	Ready
3	Machine Learning Basics	A ticket-classifier baseline	Ready
4	Deep Learning Basics	A tiny neural network and an embedding explorer	Ready
5	NLP for Applications	Keyword search over the documents	Ready
6	Transformers	A prompt-versus-retrieve-versus-fine-tune decision	Ready
7	LLM Engineering	A reliable, structured, cost-tracked, defended answer engine	Ready
8	RAG	Answers grounded in documents, with citations	Ready
9	Agents and Tool Use	Tools and actions with human approval	Ready
10	Backend Engineering	A FastAPI service with auth and tests	Ready
11	Data Stores	PostgreSQL, vector storage, caching, background jobs	Ready
12	Evaluation and Observability	An evaluation harness, tracing and dashboards	Ready
13	Deployment and Operations	Docker, CI, cloud deployment, rollback	Ready
14	Professional Practice	A portfolio-ready write-up	Ready

How each lesson works

Every lesson is a walk through one BrightCart example, one picture at a time: a figure, a short paragraph that says what it shows, a short block of code that proves it, and a walkthrough of every line. Each lesson:

The situation: a problem at BrightCart.
A real case, first: something that really happened, from a published source, cited.
The idea: fifteen to thirty figures, one idea each, one running example.
Run it: the smallest code that works, ready to paste into Colab, with a code walkthrough.
Break it: you make it fail on purpose, then fix it.
In production: what teams do with this at scale.
Check yourself: a few questions, one exercise, key terms and sources.

Each module ends with a lab (a guided build of that module's piece of BrightCart) and an incident file (a real, published failure replayed on BrightCart and fixed).

More detail: course-guide/01-how-this-course-works.md.

The tools you will use

Python throughout. LangChain for calling language models and LangGraph for multi-step workflows and agents, so the same code works with Groq, Gemini or Ollama. Where it helps you understand, a lesson builds the mechanism by hand first and then shows the framework's version.

Course guide

File	Read it when
01-how-this-course-works.md	Before your first lesson
02-setup-colab-and-llm-providers.md	Before you run any code
03-the-brightcart-project.md	To see what you are building
06-shared-data.md	To see the BrightCart data every module reuses
04-style-guide.md	Only if you are writing or editing lessons
05-image-style-guide.md	Only if you are drawing the course figures