<?xml version="1.0" encoding="UTF-8" ?>
  <rss version="2.0">
    <channel>
      <title>Samip Devkota</title>
      <description>Portfolio of Samip Devkota, a software engineer building scalable APIs, data pipelines, and retrieval-backed AI systems.</description>
      <link>http://localhost:3000</link>
      
        <item>
          <title>So… who actually signed off on this??</title>
          <description>I use AI agents because they help me build faster. But the more work I hand off, the more I wonder whether our review layers, permissions, and accountability systems are keeping up. and what happens when something goes wrong?</description>
          <link>http://localhost:3000/blog/so-who-actually-signed-off-on-this</link>
          <guid>http://localhost:3000/blog/so-who-actually-signed-off-on-this</guid>
          <pubDate>Thu, 25 Jun 2026 00:00:00 GMT</pubDate>
        </item>
        <item>
          <title>Algorithmic Redistricting: How to Use Simulation Methods for Analyzing Large Datasets</title>
          <description>Over Winter Term I had the opportunity to take a class on how mathematics plays a role in gerrymandering and redistricting elections. This got me thinking can we use mathematical and statistical concepts in drawing these districts? This blog explores how I used Markov Chain Monte Carlo simulations can  to detect gerrymandering and create fairer electoral maps.</description>
          <link>http://localhost:3000/blog/algorithmic-redistricting-how-to-use-simulation-methods-for-analyzing-large-datasets</link>
          <guid>http://localhost:3000/blog/algorithmic-redistricting-how-to-use-simulation-methods-for-analyzing-large-datasets</guid>
          <pubDate>Fri, 07 Feb 2025 00:00:00 GMT</pubDate>
        </item>
        <item>
          <title>What can text data on goodreads tell us? Data analytics for predictive modelling.</title>
          <description>Could we use the readability and sentiment of reviews to understand user preferences and make better book recommendations? It seemed simple enough on the surface—analyze the text, derive some meaningf</description>
          <link>http://localhost:3000/blog/what-can-text-data-on-goodreads-tell-us-data-analytics-for-predictive-modelling</link>
          <guid>http://localhost:3000/blog/what-can-text-data-on-goodreads-tell-us-data-analytics-for-predictive-modelling</guid>
          <pubDate>Thu, 09 Jan 2025 00:00:00 GMT</pubDate>
        </item>
        <item>
          <title>Design to Deployment, Building a CMS from scratch: A Reflection.</title>
          <description>When I set out to improve my portfolio website, I realized that adding new content like experiences or projects was unnecessarily tedious. Each update required me to modify the codebase, commit change</description>
          <link>http://localhost:3000/blog/design-to-deployment-building-a-cms-from-scratch-a-reflection</link>
          <guid>http://localhost:3000/blog/design-to-deployment-building-a-cms-from-scratch-a-reflection</guid>
          <pubDate>Thu, 09 Jan 2025 00:00:00 GMT</pubDate>
        </item>
    </channel>
  </rss>