AI Starter Course

The honest definition

Forget the robots and the sci-fi. Artificial intelligence, at its most useful and honest, is software that learns patterns from examples ins…

What AI is great at (and bad at)

It predicts the next word

Strip away the mystique and a chatbot does one thing: it predicts the next word. Type 'The cat sat on the…' and it guesses 'mat', because af…

The consequence: it doesn't look things up

When you ask a fact-based question, the model isn't searching a library — it's assembling the most probable answer from what it learned duri…

The three ingredients

Before and after

Weak: 'Write me an email.' Strong: 'Write a short, warm email to a customer named Sam explaining their order is delayed two days, offering 1…

It's a conversation, not a one-shot

Write a decent prompt, read the result, tell it what to change: 'shorter', 'more formal', 'try again'. That back-and-forth — steering, not n…

What a hallucination really is

When AI states something false with total confidence, we call it a 'hallucination'. But it isn't lying — it's predicting. Sometimes the most…

When to trust it — and when not

Start boring, not impressive

Find the small, repetitive, annoying task you already do every day, and hand AI just that one thing. Drafting routine emails, summarising me…

Do it well once, then repeat

Do the task yourself once and keep a good example. Write a prompt with context, that example, and a clear ask. Run it, refine it, save it. Y…

Prove it

Finish with a short multiple-choice assessment covering everything you've learned. Pass and earn your shareable AI Starter certificate — a s…