<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
    <channel>
        <title>Ai - Tag - shearn89.com</title>
        <link>http://example.org/tags/ai/</link>
        <description>Ai - Tag - shearn89.com</description>
        <generator>Hugo -- gohugo.io</generator><language>en</language><lastBuildDate>Fri, 24 Apr 2026 11:14:36 &#43;0100</lastBuildDate><atom:link href="http://example.org/tags/ai/" rel="self" type="application/rss+xml" /><item>
    <title>Agentic Engineering So Far</title>
    <link>http://example.org/2026/04/24/agentic-engineering-so-far/</link>
    <pubDate>Fri, 24 Apr 2026 11:14:36 &#43;0100</pubDate>
    <author>Author</author>
    <guid>http://example.org/2026/04/24/agentic-engineering-so-far/</guid>
    <description><![CDATA[<div class="featured-image">
                <img src="/images/ai-noodling.webp" referrerpolicy="no-referrer">
            </div>Recently I&rsquo;ve been doing a lot more work with AI agents in my day to day work, so this post is a bit of a rambling write-up of where I&rsquo;ve got to. Some semi-useful learnings that others may benefit from!
I was pretty skeptical at first. My view was that AI coding tools were smart autocomplete - handy for boilerplate, better at filling in parameters in terraform than the built in autocomplete, unit test population, not much else.]]></description>
</item></channel>
</rss>
