Every chat with an AI tool starts with a prompt, and the quality of that prompt has a big effect on the quality of the answer. Prompt engineering is the practice of writing instructions that help a language model give useful, accurate, and consistent results.
You'll start with what prompt engineering is and why it matters, then see how it works in plain terms, including why a model sometimes gets things wrong. From there the module looks under the hood at how large language models work, and finishes with tokens and context windows, the limits that shape what a model can read and remember in a single request.
With a clear picture of how models behave, you'll be ready to write your first real prompts in Prompting Basics, the next module in this course.
Anthropic's Zack Witten explains what prompt engineering is and what the work involves.
A clear guide to what prompt engineering is, why AI sometimes hallucinates, and how plain-English instructions lead to the answers you want.
An animated look at how large language models work, from tokens and context windows to predicting the next word.
A simple explanation of the tokens and context window that determine how AI models like ChatGPT, Claude, and Gemini read your prompts.