Free courses / AI Zero to Hero / Lesson 3
Everyday wins
Try AI where you can judge the result.
Start where you can tell good from bad. A meal plan, a rough email, a packing list or a plain-English explanation of a letter are easy to assess. A medical, legal or financial decision is not, and that is not where to begin.
Ask for two alternatives rather than one answer. Comparing makes you the editor instead of the audience, and it exposes the model's assumptions.
Notice what you change before you use the result. Those edits are the value you add, and over time they tell you what the tool is genuinely good at for you.
- Begin with tasks you can judge.
- Ask for alternatives, then compare.
- Your edits are the real work.
PIXEL / THE COACH
A rubbish packing list is a funny story you tell later. A rubbish letter to the council is a Tuesday you do not get back. Pick your first experiment accordingly.
Try it
Give a tool one small job from today. Time your usual way of doing it, then be honest about whether the result helped once you had tidied it up.
I want to [small job from today]. Do a first version, then tell me what you were unsure about and what you would need from me to do it properly.
Then paste it into whichever assistant you use — ChatGPT, Claude, Gemini or Copilot. Not sure which? Meet them all.
Progress is saved on this device.
Questions about “Everyday wins”Asked by readers, answered by us. Open to read them.
Open to load them.
Ask about this page and we will answer it here, where the next person can read it too.
Nobody else can answer you, and you cannot answer anybody else. This is not a forum — we would rather say that than run a room we cannot watch at three in the morning.
Your question goes up with the answer and without your name. Nothing identifies you, ever.
If we cannot answer it we will tell you why, and that one stays between us.