How LLMs work, how to instruct them, and how to fill their context.
Python
Claude
OpenAI
GeminiTokenisation, attention and sampling — enough to know why a model answers the way it does. Then testable prompt engineering, context engineering (what goes in the context window, RAG, memory), building on the APIs, and evaluation. That last part is the least taught and the most decisive: nearly every LLM project fails not because the model was not clever enough but because nobody could show the output was getting better.
Read a free lesson: How an LLM Reads Your PromptEvery module and lesson in this track. Lessons marked free are open to everyone; the rest open once you own the track.
Every lesson in this track, with summariesTokens, embeddings, attention and next-token prediction — the mechanics that explain almost every LLM behaviour.
Clear instructions, examples, step-by-step reasoning and structured output — proven techniques, no incantations.
What goes into the context window, where it comes from and in what order — the core skill of building LLM applications.
Calling APIs, streaming, tool calling, caching, and keeping cost and latency under control in production.
Eval sets, LLM-as-judge and regression tests for prompts — replacing "looks good to me" with a number.
Hallucination, prompt injection and guardrails — the risks to understand before an LLM app meets users.
The real one, from a lesson — it runs in your browser. No account needed.
This track is part of a larger path. Buy the whole path as a bundle and every track in it costs 40% less.
