<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Design Review on Chuanxilu for Skilled Homo sapiens</title><link>https://blog.chuanxilu.net/en/tags/design-review/</link><description>Recent content in Design Review on Chuanxilu for Skilled Homo sapiens</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Fri, 22 May 2026 10:00:00 +0800</lastBuildDate><atom:link href="https://blog.chuanxilu.net/en/tags/design-review/index.xml" rel="self" type="application/rss+xml"/><item><title>Cascade Retrieval: A 15-Year-Old IR Trick Fixed My Design Review Agent</title><link>https://blog.chuanxilu.net/en/posts/2026/05/dual-pass-review-recall-precision-tradeoff/</link><pubDate>Fri, 22 May 2026 10:00:00 +0800</pubDate><guid>https://blog.chuanxilu.net/en/posts/2026/05/dual-pass-review-recall-precision-tradeoff/</guid><description>A design review agent needs to find every issue AND avoid false positives. One agent can&amp;#39;t do both well. Borrowing cascade retrieval from information retrieval — a 15-year-old method — I split the agent into two: one for recall, one for precision. Real defects get caught earlier, and the risk of rework during development drops.</description></item></channel></rss>