Module 8 · Level II · Practitioner

Prompting well

Context, examples, structure and iteration: how to ask for what you actually want, and get it the first or second time.

6 lessons · about 1 hour

The module in 49 secondsCaptions on · sound optional

What’s inside

  1. 01
    Context: role, audience and goal

    Most disappointing AI answers are context problems, not model problems: the five things an assistant can't guess about your task. · 10 min

  2. 02
    Being specific about format and length

    How to describe the shape of the output you want, from length and layout to tone and where it will end up, so you edit less. · 9 min

  3. 03
    Showing, not telling: giving examples

    How a few well-chosen examples (few-shot prompting) get you consistent tone, format and judgement faster than any description. · 10 min

  4. 04
    Structure: steps, headings and delimiters

    How to lay out a longer prompt so the model can tell instructions from material, follow steps in order and keep the rules in view. · 10 min

  5. 05
    Iterating, critiquing and surfacing assumptions

    How to turn a first draft into a strong one: specific feedback, critique against criteria, real alternatives and the assumptions behind the answer. · 10 min

  6. 06
    Reusable templates, and prompting each tool

    How to turn prompts that work into templates your team can reuse, and how to adapt them to ChatGPT, Microsoft Copilot, Gemini and Claude. · 11 min

Where this sits on your path depends on your assessment. Some people skip this module outright; others start here. The free placement assessment decides, and the first lesson of every module is free to read. Find your level →

Also at Level II

9AI for writing, research and analysis
Drafting, summarising, researching and analysing data with AI, with the checking habits that keep your name safe on the result.10AI for images, audio and video
Generating and editing images, voice, music and video: what the tools can do, what they can't, and the rights questions to ask first.11The Tool Atlas: choosing the right tool
The 32 tools that matter, from ChatGPT to n8n: what each is good at, what to watch out for, and how to judge any new one in five questions.12Checking AI's work
Fact-checking, source-checking and spotting hallucinations: the habits that turn a fluent draft into something you can sign off.