"tags": self.tags,
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:
。业内人士推荐同城约会作为进阶阅读
Фото: Another77 / Shutterstock / Fotodom
"Having Neil with us this year has been great - we of a certain age all know who he is and what he's done, and we're thrilled that he offered to come along and help."