<?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 Experiment, Fail, Learn, Repeat</title>
    <link>https://www.hairizuan.com/categories/ai/</link>
    <description>Recent content in Ai on Experiment, Fail, Learn, Repeat</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en</language>
    <copyright>Copyright © 2026 Hairizuan Noorazman</copyright>
    <lastBuildDate>Sat, 02 May 2026 22:59:55 +0800</lastBuildDate><atom:link href="https://www.hairizuan.com/categories/ai/index.xml" rel="self" type="application/rss+xml" />
    
    <item>
      <title>Building a Custom MCP Server with Chrome DevTools Protocol</title>
      <link>https://www.hairizuan.com/building-a-custom-mcp-server-with-chrome-devtools-protocol/</link>
      <pubDate>Mon, 15 Jun 2026 00:00:00 +0000</pubDate>
      
      <guid>https://www.hairizuan.com/building-a-custom-mcp-server-with-chrome-devtools-protocol/</guid>
      <description>&lt;p&gt;When using Claude Code inside Worklayer&amp;rsquo;s terminal panel, I wanted it to be able to interact with web pages displayed in adjacent web panels. The standard approach would be to use the Playwright MCP server, but that spawns a separate Chromium instance outside the app. The page Playwright controls and the page the user sees are two different browser sessions with no shared state.&lt;/p&gt;</description>
      
    </item>
    
    <item>
      <title>Measuring Coding Tool Effectiveness</title>
      <link>https://www.hairizuan.com/measuring-coding-tool-effectiveness/</link>
      <pubDate>Sun, 22 Mar 2026 00:00:00 +0000</pubDate>
      
      <guid>https://www.hairizuan.com/measuring-coding-tool-effectiveness/</guid>
      <description>&lt;p&gt;Most online content regarding AI coding tools focuses heavily on input and output token counts. While these metrics are useful for understanding the raw volume of data processed, they often fail to address the actual effectiveness of those tokens in solving real-world engineering problems. Measuring the true impact of these tools on development workflows remains a challenge because volume does not equate to value.&lt;/p&gt;</description>
      
    </item>
    
  </channel>
</rss>
