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:
./build/parakeet model.safetensors audio.wav --vocab vocab.txt --gpu。新收录的资料是该领域的重要参考
。新收录的资料是该领域的重要参考
Интервьюер прервал Зеленского в момент обсуждения ядерного оружия. Что рассказал глава Украины о выборах и встрече с Путиным?Дмитриев объяснил, почему британский репортер прервал Зеленского по ЯО
await blocking.writer.write(chunk3); // waits until consumer reads，更多细节参见PDF资料
// Synchronous transforms