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.
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.
Start from the task and its stakes, not the demo — a tool that dazzles in five minutes can still be wrong for the job.
AI gives you a fast first read of the data — and states trends that aren’t in it just as fluently.
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.
AI is good at finding leads and bad at being the evidence. Let it point; verify in the real source.
A prompt that worked once is luck; write it down as a brief and it becomes a process.
AI is great at the formula you’d have googled — and quietly dangerous when it does the arithmetic itself.