Start with language, prompts, and your first model request. No coding needed for the opening lessons.
View beginner syllabusA free course in AI engineering
Learn how language models work.
How does a model turn your words into an answer? Work through the ideas, then use them in your own code.
First lesson: What is NLP? Read it now. Create a free account afterward to save your place.
- Lessons
- 198
- Modules
- 37
- System builds
- 6
Move to turn. Click for a surprise.Tap the robot for a surprise.
Read the request, not just the keyword
Please refund my ticket asks for money back. I don’t need a refund; I need the joining link asks for access. Can I get my money back asks for a refund without using the keyword. Highlighted phrases show what changes the meaning.
The keyword and the request agree
“Please refund my ticket.”
Return the payment. “Refund” names what the person wants.
A small phrase reverses the request
“I don’t need a refund; I need the joining link.”
Help the person join. “Don’t need” rules out a refund. The second part supplies the actual request.
The request stays; the keyword disappears
“Can I get my money back?”
Return the payment. Different words express the same request as the first message.
From lesson 1
What is NLP?
Natural language processing helps computers work with human language. Here is a small problem: which team should get this message?
Choose an answer to see the explanation.
Example 1 of 3
Continue the first lesson The syllabus
Beginner to advanced
Begin at lesson one, or go straight to a topic you want to understand.
Look inside a transformer, search your documents, and connect a model to tools.
View intermediate syllabusStudy fine-tuning, agent reliability, and the trade-offs of running models in production.
View advanced syllabusBuild something you can keep
Build a support assistant.
Give it a policy, handle a customer’s question, and check whether its answer follows the policy. Write each part in the guided workspace, then download the project.
Build the support assistantFrequently asked questions
Do I need coding experience to start?
No. The first lessons explain NLP, machine learning, and neural networks in simple words. You can follow the examples without writing code. Later lessons introduce Python and explain the setup for each exercise.
Where should I start?
Start with Beginner if language models are new to you. If you already use Python and model APIs, browse Intermediate. Advanced covers training choices, retrieval, evaluation, agents, and deployment.
What does a lesson include?
Every lesson includes an explanatory figure, a worked example, and practice with feedback. Use the figure zoom controls to inspect details, or open its walkthrough for more explanation. Use the matching challenge to apply the idea yourself.
Can I learn on my phone?
The reading layout, knowledge checks, and written responses adapt to smaller screens. Figures have an enlarge control for closer inspection. Longer Python programs are easier to work through on a computer with the packages listed in the lesson.
Where do I run the code?
Follow the example's setup notes for Python, packages, or a model account. Some activities work directly on the lesson page. Playground sends prompts to a configured model provider; it does not execute Python programs.
What can I practise in the labs?
Choose a guided system build to make an application such as a document assistant or ticket router. You write code, run it, and can download the project. Smaller exercises focus on prompts, search, agents, and deployment, with hints and worked answers.
What do the advanced lessons cover?
They cover topics such as fine-tuning, retrieval, model evaluation, agent systems, and serving. Worked examples explain the choices and tradeoffs. Follow the prerequisites before attempting exercises that need extra software or hardware.
What does my account save?
Your account saves completed lessons, completed challenges, and saved system-build projects. Written challenge drafts and saved Playground runs stay in this browser. Download them if you need a copy on another device.
How is the content maintained?
Lessons include references and review dates. We revise explanations, examples, and activities as the course develops. Use Contact to report a broken example or an explanation that needs more work.
Is LearnLLM free?
Yes. You can read the first lesson before creating an account. A free account unlocks the rest of the course, practice workspaces, and saved progress. Examples that you run with your own model provider may have separate API costs.