I then added a few more personal preferences and suggested tools from my previous failures working with agents in Python: use uv and .venv instead of the base Python installation, use polars instead of pandas for data manipulation, only store secrets/API keys/passwords in .env while ensuring .env is in .gitignore, etc. Most of these constraints don’t tell the agent what to do, but how to do it. In general, adding a rule to my AGENTS.md whenever I encounter a fundamental behavior I don’t like has been very effective. For example, agents love using unnecessary emoji which I hate, so I added a rule:
商务部公布调整对加拿大反歧视措施
Девятилетняя школьница из Смоленска вышла погулять с собакой утром 24 февраля и не вернулась домой. К ее поискам были привлечены волонтеры и полиция, которые нашли ее спустя два дня в квартире вместе с мужчиной.。快连下载安装对此有专业解读
If this sounds familiar to you, it’s because this method works very similarly to error-diffusion. Instead of letting adjacent pixels compensate for the error, we’re letting each successive candidate compensate for the combined error of all previous candidates.
，这一点在搜狗输入法2026中也有详细论述
让 MaxClaw 帮我们干活，都只用在飞书里面指挥它。我们直接把之前创建的「热点追踪」专家的指令发给它，然后在飞书里对话，输入一句简单指令，「帮我整理今天的快讯」。
“My belief [is] that coming out with a fresh mind, first principles, is important. That’s why young people are particularly helpful in tech, because they’re less biased,” Amper recently told Fortune. “I think too much knowledge is actually bad in tech: You’re biased.”，这一点在同城约会中也有详细论述