<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>AI on Joel Hanson</title>
    <link>https://joelhanson.com/tags/ai/</link>
    <description>Recent content in AI on Joel Hanson</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en</language>
    <managingEditor>joelhanson025@gmail.com (Joel Hanson)</managingEditor>
    <webMaster>joelhanson025@gmail.com (Joel Hanson)</webMaster>
    <copyright>&amp;copy; Joel Hanson</copyright>
    <lastBuildDate>Sat, 01 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://joelhanson.com/tags/ai/index.xml" rel="self" type="application/rss+xml" />
    
    <item>
      <title>ContextLayer</title>
      <link>https://joelhanson.com/projects/contextlayer/</link>
      <pubDate>Mon, 01 Dec 2025 00:00:00 +0000</pubDate>
      <author>joelhanson025@gmail.com (Joel Hanson)</author>
      <guid>https://joelhanson.com/projects/contextlayer/</guid>
      <description>Transform any REST API into an MCP server — connectors that make existing APIs usable by LLM tools.</description>
      
    </item>
    
    <item>
      <title>Supercharging Your AI: Setting Up RAG with PostgreSQL and pgvector</title>
      <link>https://joelhanson.com/posts/06-setting-up-rag-with-postgre-sql-and-pgvector/</link>
      <pubDate>Mon, 30 Sep 2024 21:28:28 +0530</pubDate>
      <author>joelhanson025@gmail.com (Joel Hanson)</author>
      <guid>https://joelhanson.com/posts/06-setting-up-rag-with-postgre-sql-and-pgvector/</guid>
      <description>Learn how to implement a powerful Retrieval-Augmented Generation (RAG) system using PostgreSQL and pgvector. This comprehensive guide covers everything from setting up a custom PostgreSQL Docker image to creating a fully functional RAG query system with vector embeddings and language model inference.</description>
      
    </item>
    
    <item>
      <title>Convert Your Django DRF Project to MCP in 5 Minutes</title>
      <link>https://joelhanson.com/posts/20-convert-your-django-drf-project-to-mcp-in-5-minutes/</link>
      <pubDate>Sun, 03 Aug 2025 15:20:06 +0530</pubDate>
      <author>joelhanson025@gmail.com (Joel Hanson)</author>
      <guid>https://joelhanson.com/posts/20-convert-your-django-drf-project-to-mcp-in-5-minutes/</guid>
      <description>&lt;h2 class=&#34;relative group&#34;&gt;The Problem: When APIs Meet AI Assistants&#xA;    &lt;div id=&#34;the-problem-when-apis-meet-ai-assistants&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#the-problem-when-apis-meet-ai-assistants&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;p&gt;A few weeks ago, I was experimenting with &lt;a href=&#34;https://modelcontextprotocol.io/&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;Model Context Protocol (MCP)&lt;/a&gt; for a &lt;a href=&#34;https://joelhanson.com/posts/16-breaking-kafka-walls-building-an-mcp-server-for-your-kafka-cluster/&#34; &gt;Kafka integration project&lt;/a&gt;. The experience was eye-opening - being able to interact with complex systems through natural language felt like a glimpse into the future of development workflows.&lt;/p&gt;</description>
      
    </item>
    
    <item>
      <title>Kafka MCP Server</title>
      <link>https://joelhanson.com/projects/kafka-mcp-server/</link>
      <pubDate>Sat, 07 Jun 2025 00:00:00 +0000</pubDate>
      <author>joelhanson025@gmail.com (Joel Hanson)</author>
      <guid>https://joelhanson.com/projects/kafka-mcp-server/</guid>
      <description>Expose Kafka cluster operations as LLM-accessible tools via the Model Context Protocol.</description>
      
    </item>
    
    <item>
      <title>Wayfare</title>
      <link>https://joelhanson.com/projects/wayfare/</link>
      <pubDate>Sat, 01 Aug 2026 00:00:00 +0000</pubDate>
      <author>joelhanson025@gmail.com (Joel Hanson)</author>
      <guid>https://joelhanson.com/projects/wayfare/</guid>
      <description>Travel bucket list and savings tracker with MCP. Same trip context in ChatGPT, Claude, and Cursor.</description>
      
    </item>
    
    <item>
      <title>Wayfare: I Plan Trips More Than I Take Them</title>
      <link>https://joelhanson.com/posts/30-wayfare-mcp-first-travel-context-layer/</link>
      <pubDate>Sat, 01 Aug 2026 00:00:00 +0000</pubDate>
      <author>joelhanson025@gmail.com (Joel Hanson)</author>
      <guid>https://joelhanson.com/posts/30-wayfare-mcp-first-travel-context-layer/</guid>
      <description>I keep losing trip research across ChatGPT, Claude, and Cursor. So I built Wayfare: a travel bucket list with savings tracking, plus MCP so connected chatbots can use the same trip context.</description>
      
    </item>
    
    <item>
      <title>From Prompt to Home Screen: Shipping Nursing Tracker with GitHub Pages</title>
      <link>https://joelhanson.com/posts/27-from-prompt-to-home-screen-booby-tracker-on-github-pages/</link>
      <pubDate>Sun, 07 Jun 2026 00:00:00 +0000</pubDate>
      <author>joelhanson025@gmail.com (Joel Hanson)</author>
      <guid>https://joelhanson.com/posts/27-from-prompt-to-home-screen-booby-tracker-on-github-pages/</guid>
      <description>My wife was losing track of feeds, so I built a one-tap nursing timer that grew into a pumping log, and shipped it for free on GitHub Pages with no database and no app store.</description>
      
    </item>
    
    <item>
      <title>Introducing ContextLayer: Transform Any REST API into an MCP Server in Minutes</title>
      <link>https://joelhanson.com/posts/22-introducing-contextlayer-transform-any-rest-api-into-an-mcp-server/</link>
      <pubDate>Sun, 16 Nov 2025 10:00:00 +0530</pubDate>
      <author>joelhanson025@gmail.com (Joel Hanson)</author>
      <guid>https://joelhanson.com/posts/22-introducing-contextlayer-transform-any-rest-api-into-an-mcp-server/</guid>
      <description>&lt;h2 class=&#34;relative group&#34;&gt;The Problem: Connecting AI Assistants to Your APIs&#xA;    &lt;div id=&#34;the-problem-connecting-ai-assistants-to-your-apis&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#the-problem-connecting-ai-assistants-to-your-apis&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;p&gt;As AI assistants like &lt;a href=&#34;https://claude.ai/&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;Claude&lt;/a&gt; and &lt;a href=&#34;https://github.com/features/copilot&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;VS Code Copilot&lt;/a&gt; become more powerful, developers are discovering a critical bottleneck: &lt;strong&gt;these AI tools can&amp;rsquo;t directly interact with our existing REST APIs&lt;/strong&gt;.&lt;/p&gt;</description>
      
    </item>
    
  </channel>
</rss>
