Prompt craft
How to write a prompt that works — clarity, structure, examples, roles, and the patterns that hold across models.
If you are new to AI, read these in order. The first guide is the 30-minute starter path that links to every other piece. The rest go deeper on the questions everyone hits early: which model to use, what AI gets wrong, what is safe to share at work, and how to prompt.
What makes a prompt actually work
The patterns that hold across every model — clarity, context, examples, format constraints. The "brilliant new employee" mental model, and why showing your prompt to a colleague is the test that catches most failures.
Structuring prompts with XML, roles, and sections
Why <tags> work better than plain text for non-trivial prompts. How role assignments steer behavior. The hierarchy that makes long, mixed-input prompts work — context, instructions, examples, input.
Few-shot examples: when they help, how to write them
When examples are the single biggest unlock you have, and when they hurt. The rules: relevant, diverse, structured. How many is enough. Why one bad example can corrupt the whole output.
Use AI for work
Apply the foundations and prompt patterns to specific work tasks: email, meetings, research, weekly reports.