
  <rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
      <title>KShivendu</title>
      <link>https://www.kshivendu.dev/blog</link>
      <description>Kumar Shivendu&#39;s blog</description>
      <language>en-us</language>
      <managingEditor>mail@kshivendu.dev (Kumar Shivendu)</managingEditor>
      <webMaster>mail@kshivendu.dev (Kumar Shivendu)</webMaster>
      <lastBuildDate>Thu, 27 Aug 2026 00:00:00 GMT</lastBuildDate>
      <atom:link href="https://www.kshivendu.dev/tags/evaluation/feed.xml" rel="self" type="application/rss+xml"/>
      
  <item>
    <guid>https://www.kshivendu.dev/blog/relevance-tail</guid>
    <title>Stop Averaging Search Evals: Report percentiles, not just the mean.</title>
    <link>https://www.kshivendu.dev/blog/relevance-tail</link>
    <description>Search evals are broken. We track p50/p99 for latency because an average hides the tail, then report search quality as one average NDCG and call it a day. A mean of 52.5 can sit on top of a fifth of queries finding nothing at all. Track p25 and p50 alongside the mean.</description>
    <pubDate>Thu, 27 Aug 2026 00:00:00 GMT</pubDate>
    <author>mail@kshivendu.dev (Kumar Shivendu)</author>
    <category>search</category><category>evals</category><category>evaluation</category><category>metrics</category>
  </item>

    </channel>
  </rss>
