How LLMs Work
Tokens, embeddings, attention and next-token prediction — the mechanics that explain almost every LLM behaviour.
- 4 lessons
- 1h 4m
- 3 simulations
Clear instructions, examples, step-by-step reasoning and structured output — proven techniques, no incantations.
A suggestion, never a lock — you can start here.
Every lesson's title and summary is public. The lessons themselves open once you own the track.
Every lesson in LLMs, Prompt Engineering & Context EngineeringWriting a prompt like a brief for a brilliant new colleague with no context.
Choosing examples that teach the pattern rather than get copied verbatim.
When asking the model to think step by step helps, and when it only adds tokens.
JSON, schemas and validation so model output can be consumed by code.
Tokens, embeddings, attention and next-token prediction — the mechanics that explain almost every LLM behaviour.
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.