博客
来自不光鲜那一半的记录
关于解析难搞的文档、把权限放在该生效的地方、以及让答案可复现的工程笔记。
Reproducing last quarter's number after the definition changed
The report said 41.2 percent in April. The same question returns 39.8 today, and nothing is wrong with either figure. Whether you can explain the gap in ten minutes or ten days depends on one architectural choice.
Row-level rules belong in the query, not in the prompt
If the only thing stopping an AI from returning another region's salary data is an instruction telling it not to, you do not have access control. You have a suggestion.
Why merged cells break retrieval, and what to do about it
A merged cell that flattens into the wrong row does not produce an error. It produces a confident, wrong number that looks exactly like a right one, and it is the most common silent failure in document AI.
分析规则是知识对象，不是提示词
n 小于 30 的格子要抑制；按婚姻状况做任何对比之前先控制年龄。每个资深分析师都揣着上百条这样的规则，而几乎所有 AI 分析工具都只让你把它们粘进提示词，然后祈祷。
企业数据 AI 的两半，以及几乎没人把它们接起来
文档 AI 读得懂合同，却查不了数仓；分析 AI 查得了数仓，却从没读过那份合同。而真正影响经营的问题，恰恰都落在两者的连接处。