
  <rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
      <title>Elite Software Engineer</title>
      <link>https://elitesoftwareengineer.com/blog</link>
      <description>Building a high performance teams and software</description>
      <language>en-us</language>
      <managingEditor>address@yoursite.com (Mike Camara)</managingEditor>
      <webMaster>address@yoursite.com (Mike Camara)</webMaster>
      <lastBuildDate>Mon, 04 May 2026 14:00:00 GMT</lastBuildDate>
      <atom:link href="https://elitesoftwareengineer.com/tags/code-review/feed.xml" rel="self" type="application/rss+xml"/>
      
  <item>
    <guid>https://elitesoftwareengineer.com/blog/the-session-pr-reviewing-how-the-code-was-made</guid>
    <title>The Session PR: Reviewing How the Code Was Made, Not Just What Changed</title>
    <link>https://elitesoftwareengineer.com/blog/the-session-pr-reviewing-how-the-code-was-made</link>
    <description>Today&#39;s pull request is built around a diff. You review what changed, not how it came to be. With coding agents, that model is starting to leak: a clean diff can hide a messy session, skipped constraints, or a plan that was wrong for three iterations before it was right. This post explores a new kind of PR — one where the artifact under review is the agent session itself: the prompts, the tool calls, the rejected paths, the plan, and the human&#39;s choices along the way. It compares the idea to existing practices like AI review bots, stacked diffs, build provenance, and &quot;session provenance&quot;, and argues that making the session the primary review surface is genuinely new — and probably inevitable.</description>
    <pubDate>Mon, 04 May 2026 14:00:00 GMT</pubDate>
    <author>address@yoursite.com (Mike Camara)</author>
    <category>ai</category><category>coding-agents</category><category>code-review</category><category>pull-requests</category><category>agentic-engineering</category><category>software-engineering</category>
  </item>

    </channel>
  </rss>
