<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Knowledge Management on Saurabh Chaubey</title>
    <link>https://saurabh-chaubey.com/tags/knowledge-management/</link>
    <description>Recent content in Knowledge Management on Saurabh Chaubey</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-us</language>
    <lastBuildDate>Tue, 07 Apr 2026 21:27:00 +1000</lastBuildDate><atom:link href="https://saurabh-chaubey.com/tags/knowledge-management/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>The Wiki That Writes Itself: How AI Agents Can Build and Share Your Organisation&#39;s Knowledge — Automatically</title>
      <link>https://saurabh-chaubey.com/post/platformengg/2026-04-07_the-wiki-that-writes-itself-how-ai-agents-can-build-and-share-your-organisations-knowledge-automatically/</link>
      <pubDate>Tue, 07 Apr 2026 21:27:00 +1000</pubDate>
      
      <guid>https://saurabh-chaubey.com/post/platformengg/2026-04-07_the-wiki-that-writes-itself-how-ai-agents-can-build-and-share-your-organisations-knowledge-automatically/</guid>
      <description>Inspired by Andrej Karpathy’s LLM Wiki and extended into an enterprise architecture for centrally governed, continuously improving organisational knowledge.
Last week, Andrej Karpathy published a brilliant gist called LLM Wiki — a pattern for building personal knowledge bases where an LLM incrementally writes and maintains a wiki from raw sources. Instead of the traditional RAG approach — retrieve, hope for the best, and re-derive knowledge on every question — the LLM compiles knowledge once into structured, interlinked markdown pages and keeps them current as new information arrives.</description>
    </item>
    
  </channel>
</rss>
