<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
	<channel>
		<title>Software Engineering on Catscrdl</title>
		<link>https://catscrdl.io/tags/software-engineering/</link>
		<description>Recent content in Software Engineering on Catscrdl</description>
		<generator>Hugo</generator>
		<language>en</language>
		
		
		
		
			<lastBuildDate>Sat, 15 Aug 2026 00:00:00 +0000</lastBuildDate>
		
			<atom:link href="https://catscrdl.io/tags/software-engineering/index.xml" rel="self" type="application/rss+xml" />
			<item>
				<title>Flowwork</title>
				<link>https://catscrdl.io/blog/flowwork/</link>
				<pubDate>Sat, 15 Aug 2026 00:00:00 +0000</pubDate>
				<guid>https://catscrdl.io/blog/flowwork/</guid>
				<description>&lt;h1 id=&#34;flowwork---an-ai-coding-hardness&#34;&gt;Flowwork - An AI Coding Hardness&lt;/h1&gt;&#xA;&lt;h2 id=&#34;background&#34;&gt;Background&lt;/h2&gt;&#xA;&lt;p&gt;I&amp;rsquo;m a fairly big believer in the power of GenAI for coding. I know there&amp;rsquo;s active debate in this area. If you&amp;rsquo;re not a fan of LLMs for coding, this blog may not be for you. Personally, I believe that humans will not write code for much longer (with some niche exceptions). For the current capabilities of LLMs, I do not think they&amp;rsquo;re good enough to &amp;ldquo;vibe-code&amp;rdquo; production level code. Harnesses that enforce strict coding standards with multiple, layered approaches to enforce them is essential. After almost a year of iteration, I&amp;rsquo;ve got &amp;ldquo;flowwork&amp;rdquo; in a good enough state where I feel comfortable writing about it. (Why &amp;ldquo;flowwork&amp;rdquo;? It was originally called workflow and I called v2 flowwork because I&amp;rsquo;m not creative.)&lt;/p&gt;</description>
			</item>
	</channel>
</rss>
