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:
(func (export "run")，更多细节参见WPS下载最新地址
Google в России оштрафовали на миллиарды рублейСуд в Москве оштрафовал Google на 16 миллиардов рублей за неуплату штрафа，更多细节参见91视频
非 GAAP 每股收益为 0.81 美元，同样超过市场一致预期的 0.77 美元。