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:
（三）与本案当事人有其他关系，可能影响案件公正处理的。，详情可参考WPS官方版本下载
:first-child]:h-full [&:first-child]:w-full [&:first-child]:mb-0 [&:first-child]:rounded-[inherit] h-full w-full，推荐阅读服务器推荐获取更多信息
Digest: sha256:bb6169309e6c0d728f7a726330360b505bd2e60931f86c38b81c773291f4daf0
Part of the approach involves developing actuators that output lots of data about their current position and function, so that computers can adjust their operation in real-time. But the hardware also needs to step up, too.