Practical AI guides and plain-language explainers. Filter by role and level.
Grouped from the basics up. Pick the course that fits you and follow it from the first guide.
Start hereEveryone
What AI is, how to ask it, and what to watch out for — the basics everyone should start with, whatever their job.
5 guides41 min in totalBeginner
5 guides41 min in totalBeginner
Courses by roleOffice workers
Cut down the work you repeat every day — spreadsheets, reports, email and meeting notes.
5 guides53 min in totalBeginner → Practical
Courses by roleMarketers
Draft ads and content faster, then move on to reading your campaign results.
4 guides50 min in totalBeginner → Practical
Courses by roleDesigners
From prompt basics to mood boards, copyright checks and consistent results.
4 guides49 min in totalBeginner → Practical
Courses by roleDevelopers
From your first API call to working with coding assistants, structured output and cost control.
4 guides61 min in totalBeginner → Practical
Going furtherEveryone
Once you have the basics, learn the patterns most AI products are built on.
3 guides36 min in totalBeginner → Practical
3 guides36 min in totalBeginner → Practical
How-to guide12 min
You don't need to know function names. Describe your table and the result you want, and a chat assistant writes the formula.
How-to guide14 min
Just ordering your prompt as subject, style, composition and light makes a difference. Here's how to write prompts that multiply your concepts fast.
How-to guide12 min
Give it the product, audience and channel, and you'll have copy from several different angles in minutes.
How-to guide17 min
Give context, work in small steps, verify with tests — a workflow that makes AI-written code something you can trust.
Explainer8 min
The technology behind ChatGPT, Claude and Gemini, explained without the math.
Explainer9 min
How do chatbots answer from your company's documents? Here's how RAG, a pattern widely used in AI products, works.
How-to guide10 min
Role, context, task, format and an example — five things that noticeably change what AI gives back.
Explainer7 min
Why AI states wrong things with confidence, where it slips most often, and how to check its answers.
How-to guide8 min
What not to paste into AI, how to swap in fake values when you must, and what to check before you start.
Explainer8 min
What "$2 per million tokens" on an AI price list means, and how to estimate what your own usage would cost.
How-to guide9 min
Tell the assistant who will read it and what shape the three lines should take, and a long report comes back as a summary you can pass straight on. This guide also shows how to check its figures against the original.
How-to guide10 min
Tell the assistant who you're writing to, what you need, by when and in what tone, and it drafts an email that fits. Worked examples for requests, apologies and refusals, plus what to check before you send.
How-to guide10 min
Get meeting notes sorted into decisions, open items and action items, without the assistant guessing owners or deadlines, and confirmed by the people who were there.
How-to guide12 min
You don't need to know the PivotTable menus: describe the rows, columns and values, and the assistant writes the formula. The numbers come from the sheet or from code, never from the chat, and you check them against the source.
How-to guide12 min
Turn a summary of your reviews, support tickets and surveys into three personas with AI, separate evidence from assumptions, and test the assumptions before you spend money on them.
How-to guide12 min
A blog workflow where AI handles the outline and first draft, and people handle the plan, the fact-checking, the real experience and the final check.
How-to guide14 min
Do the maths in your spreadsheet and the interpreting with AI. Turn campaign results into insights written as observation, hypothesis and how to check, then pick your next experiment.
How-to guide12 min
Turn a short brief into visual keywords, nine images in one consistent style and a five-color palette, then lay them out as a one-page mood board.
Explainer9 min
Images made by AI alone are hard to protect, and each service's terms decide commercial use. Here's what to check before you use one, and what to keep on record.
How-to guide14 min
Pin down what must never change in a character sheet, then use a fixed block and reference images to keep the same look in every scene.
How-to guide14 min
Using the Claude API as the example: keep your API key safe, send a first request from Python, and read the answer, the stop reason and the token usage.
How-to guide15 min
Instead of asking for JSON and hoping, define the shape as a schema and get responses your code can use directly. Worked through with a customer-message classifier.
How-to guide15 min
Cache the long instructions and documents you resend with every request, and their input cost drops sharply. Using a support bot built on a manual, here's how to place the cache point and check that it works.
Explainer9 min
Unlike a chatbot that only answers, an agent takes a goal and keeps going, using tools and checking results, until the job is done. How it works, what it suits, and what to settle before you hand it work.
How-to guide18 min
Build a Python chatbot that searches ten internal policy documents with embeddings and answers only from what it finds, then test search and answers separately and fix what breaks.