<?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>Quality-Gates on lukaswalter.dev</title>
    <link>https://www.lukaswalter.dev/tags/quality-gates/</link>
    <description>Recent content in Quality-Gates on lukaswalter.dev</description>
    <image>
      <title>lukaswalter.dev</title>
      <url>https://www.lukaswalter.dev/images/LW%20Dev%20Thumbnail.png</url>
      <link>https://www.lukaswalter.dev/images/LW%20Dev%20Thumbnail.png</link>
    </image>
    <generator>Hugo -- 0.150.0</generator>
    <language>en</language>
    <lastBuildDate>Wed, 25 Mar 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://www.lukaswalter.dev/tags/quality-gates/index.xml" rel="self" type="application/rss+xml" /><item>
      <title>Stop Guessing – Use Golden Datasets for Prompt Evals</title>
      <link>https://www.lukaswalter.dev/posts/quick-tip-2/</link>
      <pubDate>Wed, 25 Mar 2026 00:00:00 +0000</pubDate>
      <guid>https://www.lukaswalter.dev/posts/quick-tip-2/</guid>
      <description>Use a small golden dataset to catch prompt regressions, compare changes against a baseline, and validate model updates before users do.</description>
    </item><item>
      <title>Eval-first: Why “It Worked Once” Is Not a Sign of Quality</title>
      <link>https://www.lukaswalter.dev/posts/eval-first-in-.net/</link>
      <pubDate>Sat, 07 Feb 2026 00:00:00 +0000</pubDate>
      <guid>https://www.lukaswalter.dev/posts/eval-first-in-.net/</guid>
      <description>Why eval-first matters for LLM apps and how to use datasets, scoring rubrics, and CI quality gates to catch regressions early.</description>
    </item>
  </channel>
</rss>
