Notes · Note 02
The four habits that get better answers
Most people get mediocre output because they ask like it’s Google. Four changes fix it, and you can learn them in an hour.
The short version
- Tell it who it is and who the work is for.
- Give it the raw material instead of describing the raw material.
- Show it one thing you already liked.
- Tell it what to do when it does not know — then push back at least once.
The instinct everyone has on day one is to type a short question, the way you would into a search box. Write a follow-up email. You get back something generic, you conclude the tool is overhyped, and you go back to writing it yourself.
The fix is a change of posture. You are not searching. You are briefing a capable new hire who is fast, widely read, and has never seen your business. Everything below follows from that.
1. Say who it is and who it is for
One sentence of role and audience changes the output more than any other single thing.
Compare that to “write a text about a missed appointment.” Same model, completely different result — because the second version has no idea whether you are a hospital or a barber.
2. Give it the material, not a description of the material
The most common mistake is describing your information instead of providing it. Do not summarise the email — paste the email. Do not describe the spreadsheet — attach it. These tools handle enormous amounts of text now; some read a million words at once. You are not going to overwhelm it.
If your answer depends on something the model cannot see, it will invent a plausible version. That is not the model lying to you. That is you asking a question that cannot be answered from what is on the table.
3. Show it one thing you liked
This is the highest-leverage habit on the list and almost nobody does it. If you want output that sounds like you, paste something you already wrote that worked.
One example beats a paragraph of adjectives describing the tone you want. Three examples beat one.
4. Tell it what to do when it does not know
Left to itself, a model fills a gap with something that reads well. Give it a different instruction and it will take it.
Add that line to anything that matters. It converts confident nonsense into a short list of questions — which is what you actually wanted.
The part people skip: go again
The first output is a draft, not a delivery. The single biggest difference between people who get value out of this and people who do not is that the second group stops at attempt one.
Say what is wrong in plain language — too formal, cut it in half, lose the last paragraph — and it will fix it. Three rounds takes ninety seconds and gets you something you would actually send.
When a prompt finally produces the right thing, paste it into a note. In a month you will have a dozen you reuse constantly, and that file is worth more than any course.