<?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>Prompt-Engineering on Kent Yao</title>
    <link>https://yaooqinn.github.io/tags/prompt-engineering/</link>
    <description>Recent content in Prompt-Engineering on Kent Yao</description>
    <generator>Hugo -- 0.157.0</generator>
    <language>en-us</language>
    <lastBuildDate>Wed, 27 May 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://yaooqinn.github.io/tags/prompt-engineering/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Anatomy of a 120-Line Prompt That Lets an LLM Rewrite Physical Plans</title>
      <link>https://yaooqinn.github.io/posts/query-engines/prompt-anatomy-for-plan-generation/</link>
      <pubDate>Wed, 27 May 2026 00:00:00 +0000</pubDate>
      <guid>https://yaooqinn.github.io/posts/query-engines/prompt-anatomy-for-plan-generation/</guid>
      <description>DBPlanBench gets GPT-5 to deliver a 4.78× geometric-mean speedup on DataFusion TPC-H SF10 by letting the model rewrite physical plans directly. I read its sql_optimization_prompts.py end to end — 120 lines, 30 of methodology, 90 of contract. That ratio is the most transferable thing in the paper.</description>
    </item>
  </channel>
</rss>
