<?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>Caddy on Dulan Dissanayake</title>
    <link>https://dulandissanayake.co.uk/tags/caddy/</link>
    <description>Recent content in Caddy on Dulan Dissanayake</description>
    <generator>Hugo -- 0.125.7</generator>
    <language>en</language>
    <lastBuildDate>Thu, 19 Nov 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://dulandissanayake.co.uk/tags/caddy/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Private AI for a Small Team (Part 1): Building the Platform</title>
      <link>https://dulandissanayake.co.uk/posts/2026/private_ai_platform_part_1/</link>
      <pubDate>Thu, 19 Nov 2026 00:00:00 +0000</pubDate>
      <guid>https://dulandissanayake.co.uk/posts/2026/private_ai_platform_part_1/</guid>
      <description>We recently set up a private AI platform for a small organisation. The staff wanted a ChatGPT-style assistant to help with their daily work, but the documents they deal with (contracts, client records, internal policies) could not be sent to a third-party AI service. So we built one that runs on infrastructure we control.
This is the first post in a four-part series, and I will cover each part of the setup:</description>
    </item>
  </channel>
</rss>
