<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Site on Swapnil Sharma</title><link>https://swappysh.github.io/categories/site/</link><description>Recent content in Site on Swapnil Sharma</description><generator>Hugo</generator><language>en</language><copyright>&lt;a href="https://creativecommons.org/licenses/by-nc/4.0/" target="_blank" rel="noopener">CC BY-NC 4.0&lt;/a></copyright><lastBuildDate>Wed, 25 Feb 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://swappysh.github.io/categories/site/index.xml" rel="self" type="application/rss+xml"/><item><title>Hello, World</title><link>https://swappysh.github.io/posts/welcome/</link><pubDate>Wed, 25 Feb 2026 00:00:00 +0000</pubDate><guid>https://swappysh.github.io/posts/welcome/</guid><description>&lt;p>I&amp;rsquo;ve spent the last few years building production AI systems: multi-agent architectures, LLM evaluation pipelines, safety-critical patient conversation platforms, code generation tools. A lot of that work happened in fast-moving startups where the goal was to ship, not to document.&lt;/p>
&lt;p>This blog is an attempt to fix that.&lt;/p>
&lt;h2 id="what-ill-write-about">What I&amp;rsquo;ll write about&lt;/h2>
&lt;p>Most of what I&amp;rsquo;ll cover sits at the intersection of &lt;strong>research and production engineering&lt;/strong>, the gap that doesn&amp;rsquo;t get enough attention. Things like:&lt;/p></description></item></channel></rss>