<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Company Knowledge on Amit Naik</title>
    <link>https://amitnaik.com/tags/company-knowledge/</link>
    <description>Recent content in Company Knowledge on Amit Naik</description>
    <generator>Hugo -- 0.144.2</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 28 Sep 2026 08:59:42 -0700</lastBuildDate>
    <atom:link href="https://amitnaik.com/tags/company-knowledge/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Turn team corrections into reusable knowledge</title>
      <link>https://amitnaik.com/til/2026-09-28-turn-team-corrections-into-reusable-knowledge/</link>
      <pubDate>Mon, 28 Sep 2026 08:59:42 -0700</pubDate>
      <guid>https://amitnaik.com/til/2026-09-28-turn-team-corrections-into-reusable-knowledge/</guid>
      <description>This article proposes capturing corrections, decisions, and useful workflows as shared company knowledge. The central idea is a learning loop: improvements discovered in one person&amp;#39;s AI workflow should become reusable context for the rest of the organization.</description>
    </item>
    <item>
      <title>Semantic layers and context layers solve different problems</title>
      <link>https://amitnaik.com/til/2026-09-28-semantic-layers-and-context-layers-solve-different-problems/</link>
      <pubDate>Mon, 28 Sep 2026 08:59:33 -0700</pubDate>
      <guid>https://amitnaik.com/til/2026-09-28-semantic-layers-and-context-layers-solve-different-problems/</guid>
      <description>MotherDuck distinguishes semantic layers, context layers, and ontologies. Shared metric definitions, business context, and explicit relationships each contribute something different; choosing an architecture starts with identifying which of those problems an AI application actually needs to solve.</description>
    </item>
    <item>
      <title>Comparing approaches to the company brain</title>
      <link>https://amitnaik.com/til/2026-09-28-comparing-approaches-to-the-company-brain/</link>
      <pubDate>Mon, 28 Sep 2026 08:59:25 -0700</pubDate>
      <guid>https://amitnaik.com/til/2026-09-28-comparing-approaches-to-the-company-brain/</guid>
      <description>Femke Plantinga highlights the variety of architectures being described as a company brain. Slite&amp;#39;s accompanying research looks at components, maintenance costs, and build-versus-buy choices, helping turn a broad label into concrete design decisions.</description>
    </item>
    <item>
      <title>Design company knowledge for agents to use</title>
      <link>https://amitnaik.com/til/2026-09-28-design-company-knowledge-for-agents-to-use/</link>
      <pubDate>Mon, 28 Sep 2026 08:59:23 -0700</pubDate>
      <guid>https://amitnaik.com/til/2026-09-28-design-company-knowledge-for-agents-to-use/</guid>
      <description>Jacob Posel argues for company brains designed around agent use and connections to live business systems. A static collection of documents is only part of the picture; usefulness depends on whether an agent can access relevant, current information in its actual workflow.</description>
    </item>
  </channel>
</rss>
