A useful request
A good prompt names what a stranger would need to do the work.
EXPLORE THE ATLAS
Switch your lens to change examples and recommendations. The underlying concepts stay shared and trustworthy.
WHAT THIS ISA landmark is one idea you can learn in about five minutes, ending in a decision you make. Rings group them by how far along you are, not by topic. See the legend
A good prompt names what a stranger would need to do the work.
AI can draft captions, alt text, and read-aloud in seconds — a real independence gain, as long as someone still checks.
Tell the model to flag what it doesn’t know instead of filling the gap.
Split a big task into stages you can check before the next one runs.
For brainstorming, being wrong is free — the model’s job is quantity, yours is taste.
One good example often teaches the model more than a paragraph of rules.
The format changes; the trust rules don’t. A generated image or a described photo can be as confidently wrong as any sentence.
Naming the specific gap — “shorten the intro,” “drop the second example” — beats asking for “better” or rerolling and hoping.
Put a person between the AI and any output or action that has consequences — before it goes out, not after it goes wrong.
A tutor that never tires — but is sometimes confidently wrong about the very thing you can’t yet check.
AI is good at finding leads and bad at being the evidence. Let it point; verify in the real source.
An AI answer with citations is a fast first draft, not a verdict. Open the links; the summary can misread them.
Great for getting the gist, risky for anything where the exact words carry weight.
The model can draft, but you sign — so read it as your own words.