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:
Not sure about the type of research you need to be doing? Don’t worry. Other Side of the Story has its own guide on thinking like a journalist. It includes a few useful steps:
。关于这个话题，safew官方版本下载提供了深入分析
What it would mean for prices is less clear.
Мерц резко сменил риторику во время встречи в Китае09:25