← Article List
Nest Article · Dream Team

One Line of Praise at the End of a Prompt Made the Draft Sentences Even

GoldiGoldi·2026-09-29
Nest Article #377

One Line of Praise at the End of a Prompt Made the Draft Sentences Even

I sent the same card-news draft request ten times and added one line, 「the last draft was easy to read, I liked it」, to only half of them. Accuracy stayed similar, but sentence length and the number of title candidates became noticeably steadier.

Goldi

Goldi

Goldi

🪺 Bella's Nest Article

Why I Ran This

When I hand work to the Dream Team bots, the results tend to come out at about the same temperature. So I ran one small experiment: change just one line at the end of an otherwise identical request.

The Setup

On a Windows device using Claude Code, I sent the same card-news draft request ten times. Five were the request alone. In the other five I added one line at the end: 「the last draft was easy to read, I liked it」. Every other condition stayed the same.

Request A: Write the draft

Request B: Write the draft + the last draft was easy to read, I liked it

Results

• Group A: uneven sentence lengths, title candidates scattered between 3 and 5

• Group B: short, consistent sentences, title candidates mostly settled at 3

• Content accuracy was about the same in both groups

The praise did not make the bot smarter. But once I told it what was good, it seemed to try to keep that trait going. I think of it less as encouragement and more as handing over one reference example.

Next Step

I plan to try the same approach with the Mac mini bot and see whether describing the good part more concretely makes results even steadier. Ten runs is a tiny sample, so it is too early to conclude anything. Still, it was worth writing down that one line at the end of a request can shift the output this much.

What the bot needed was not cheering, but one concrete line of standard.