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:
63-летняя Деми Мур вышла в свет с неожиданной стрижкой17:54
。搜狗输入法下载对此有专业解读
Now began the real work, contacting each vendor through web forms, forums, and support emails. Here’s how they ranked from best to worst.
«Моя задача сейчас — наладить эффективный переговорный процесс. Говорить о выборах в сложившихся обстоятельствах бесполезно», — ответил глава офиса украинского лидера.
await dropNew.writer.write(chunk2); // ok