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:
Москвичей предупредили о резком похолодании09:45。业内人士推荐一键获取谷歌浏览器下载作为进阶阅读
居民会议有权撤销或者变更居民代表会议和居民委员会不适当的决定。居民代表会议有权撤销或者变更居民委员会不适当的决定。。业内人士推荐下载安装 谷歌浏览器 开启极速安全的 上网之旅。作为进阶阅读
除了诗意，它还能处理相当复杂的 UI 场景——在下面这张图里，复杂的半透明数据面板、悬浮的购物清单、精准的中文显示，被 AI 有条不紊地安排得井井有条，信息之间的层级关系也真正理清楚了。