Learn how LLMs work: a free, interactive Generative AI & LLM Engineering course

Most AI tutorials either drown you in maths or skip straight to copy-pasting API calls. The free Generative AI & LLM Engineering course sits in between: every idea comes with a small simulator you can play with in your browser.

What the chapters cover

• What an LLM actually is: watch a model predict the next token one step at a time.
• Tokens: see text split into pieces and why tokens decide cost.
• Temperature, sampling & context windows: move a slider and watch answers get safer or more creative.
• Embeddings: meaning drawn as points on a map.
• Vector databases & similarity search: how search finds the closest ideas fast.
• RAG step by step: chunk, retrieve, rerank and answer from your own documents.
• Prompt engineering & structured output: get reliable JSON and defend against prompt injection.
• Reducing hallucinations: ground answers and measure quality with simple rubrics.

Practise with real tools

Each chapter links to a matching tool so you can try the idea on your own text:

• Count tokens with the AI Token Counter and price a feature with the LLM API Cost Calculator.
• Split documents for RAG with the RAG Text Chunker and compare vectors with the Embedding Similarity Calculator.
• Compare prompt versions in Prompt Diff and check JSON answers with the Structured Output Validator.

Free and private

There is no sign-up. Your progress is saved only in your browser, and the next chapters on tool calling, agents and shipping AI to production are on the way. Browse every track on the Free Courses page.