How LLMs work, how to write prompts that get reliable results, and how to check what comes back.
Large language models (LLMs) such as Claude and GPT can draft, summarise, classify and reason over text — but the quality of what you get depends heavily on what you ask. This course covers what these models actually do, the building blocks of a good prompt, and the habits that stop you trusting a confident wrong answer.
No coding is needed, though the last lessons include optional examples for people who call models from code.
4 lessons · 57 min
Tokens, prediction and the context window.
Context, task, audience, constraints — and the line almost everybody leaves out.
Few-shot examples and output you can parse.
Why models make things up, and a routine for catching it.
5.0 (1)
Sign in to leave a rating. Sign in
Tks. This is helpful.
Use @handle to bring somebody in, and #tag to file it.
Nothing here yet. Ask a question, or say how you used it.
Sign in to join the discussion. Sign in
2 min read
2 min read
2 min read
2 min read
From a promising demo to something you can operate: scope, evaluation, interface and rollout.
Build test sets, grade outputs with code, people and model-based graders, and catch regressions before your users do.
How LLM agents call tools in a loop, how to design tools they use well, and how to keep agents safe and reliable.