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:
13:24, 27 февраля 2026Мир
，这一点在同城约会中也有详细论述
Musk 在 X 上也补了一刀：「Anthropic 大规模窃取训练数据，还为此支付了数十亿美元的和解金。这是事实。」
Почему вегетарианство не всегда приносит пользу?Как сохранить здоровье без мяса и в чем плюсы и минусы такой диеты11 сентября 2022
。爱思助手下载最新版本是该领域的重要参考
Historically, LLMs have been poor at generating Rust code due to its nicheness relative to Python and JavaScript. Over the years, one of my test cases for evaluating new LLMs was to ask it to write a relatively simple application such as Create a Rust app that can create "word cloud" data visualizations given a long input text. but even without expert Rust knowledge I could tell the outputs were too simple and half-implemented to ever be functional even with additional prompting.，推荐阅读WPS官方版本下载获取更多信息
"consoleLog": consoleLog,