这个架构的核心是“导演模式”，它通过一个强大的多维参考系统，将模糊的创意转化为AI可执行的精确指令。
The benefit extends beyond AI optimization. Structured content is easier for human readers to scan and comprehend too. People increasingly skim content rather than reading every word, and clear structure helps them extract key information quickly. When you optimize for both AI processing and human scanning through better structure, you improve the experience for all visitors while increasing AI citation rates.
。关于这个话题，safew官方版本下载提供了深入分析
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:
Automated systems making consequential decisions with insufficient human oversight
几何体：骨架，决定了形状（是方的、圆的，还是扭曲的）。