What you will learn Not a chapter to read but one to do. You will ask for exactly the same thing three times, adding one technique from the last chapter each round, and see with your own eyes which technique actually changes the answer.
"Not written yet" matters. Use something you already wrote and you will mark the answer that resembles yours too generously.
Use no technique at all. Throw it in the way you would type a search.
The third is usually "no." This is where most people conclude "AI is not there yet." Round 2 changes that conclusion.
Same request, plus the situation and nothing else. Leave the format alone for now.
| Compared to round 1 | Check |
|---|---|
| Did the tone match the relationship? | □ |
| Does the cause avoid sounding like an excuse? | □ |
| Did the new date make it into a sentence? | □ |
This is where most of the gain appears. Of the five techniques, the situation alone does about half the work.
Now add the format and the constraints.
The third is the point of this round. Watching a "do not" get obeyed tells you what is worth writing down next time.
Stack the three answers and mark them.
| Round 1 | Round 2 | Round 3 | |
|---|---|---|---|
| Could you send it as is? | |||
| How many fixes needed | |||
| Faster than writing it yourself? |
It was already usable at round 2 — the common case. Write the situation and stop; save the format work for documents that are fussy about it.
It only became usable at round 3 — format mattered for this document. Save that format block and reuse it verbatim next time.
None of them were any good — the problem is not the request, it is the task you picked. Work you lack the information for is work the model lacks it for too. That is the subject of things to watch out for.
That last line is the real output of this exercise. Save the instructions that worked and use them again — this is where the gap opens up against people who start from scratch every time.
1. If you could use only one of the five techniques, which would it be?
The situation. Round 2 produced the largest jump. Saying who the reader is and what position you are in aligns the tone and the content at the same time.
2. Why check whether a "do not" was obeyed?
So you know what is worth writing down. Once you have seen prohibitions land, you can pre-empt the things that catch you every time — filler, guessing, overstatement.
3. All three rounds were poor. What should you suspect?
The choice of task. Work that does not improve with better instructions is usually work you lack the information for. Check the task before polishing the request further.
Finally, the limits and cautions you must know before using it → Things to watch out for
HyperTeams□ 20 minutes□ One piece of writing you actually owe today — an email, a notice, a reply · pick one you have not written yet□ Somewhere to put the three answers side by side (a scratch file is fine)write an apology email to a client about a late delivery□ Is it longer than what you would have written?□ Does it contain phrases you would never use?□ Could you send it as is?Write an apology email to a client about a late delivery.Recipient: a major client of three years; I am on easy terms with the contactCause: parts shortage. Not our fault, but it must not read as an excuseNew date: 15 MarchContext: this is the first delay we have had with this client(everything above, unchanged)Format:- five sentences maximum- open with the apology, close by asking them to confirm the new date- do not use filler like "we will do our very best"□ Did it hold to five sentences?□ Are the first and last sentences what you asked for?□ Did the banned filler actually disappear?Scoring rule: two fixes or fewer counts as "usable"□ You actually placed the three answers side by side□ You can say in one sentence what changed between rounds 1 and 2□ You checked whether the "do not" was obeyed in round 3□ You saved one fragment of instruction to reuse