<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
	<channel>
		<title>Software-Development on c-blog</title>
		<link>https://blog.ssdindo.com/tags/software-development/</link>
		<description>Recent content in Software-Development on c-blog</description>
		<generator>Hugo</generator>
		<language>en-us</language>
		
		
		
		
			<lastBuildDate>Wed, 21 Oct 2026 09:00:00 +0700</lastBuildDate>
		
			<atom:link href="https://blog.ssdindo.com/tags/software-development/index.xml" rel="self" type="application/rss+xml" />
			<item>
				<title>I am feeling lucky again?</title>
				<link>https://blog.ssdindo.com/posts/i-am-feeling-lucky-again/</link>
				<pubDate>Wed, 21 Oct 2026 09:00:00 +0700</pubDate>
				<guid>https://blog.ssdindo.com/posts/i-am-feeling-lucky-again/</guid>
				<description>Evaluation metric became a tremendous help for me to measure and optimize the system. While doing it stumbling a metric MRR (Mean Reciprocal Rank) give me a light bulb &lt;em&gt;&amp;ldquo;Hmm it&amp;rsquo;s similar with the google I am feeling lucky ya&amp;rdquo;&lt;/em&gt;</description>
			</item>
			<item>
				<title>Will AI Code Review Replace our existing review/scan tools?</title>
				<link>https://blog.ssdindo.com/posts/will-ai-code-review-replace-our-existing-review-scan-tools/</link>
				<pubDate>Mon, 05 Oct 2026 09:00:00 +0700</pubDate>
				<guid>https://blog.ssdindo.com/posts/will-ai-code-review-replace-our-existing-review-scan-tools/</guid>
				<description>I tried AI powered code review alongside SCA and SAST to see what it catches, where it helps, and how it might fit into our workflow.</description>
			</item>
			<item>
				<title>Back to Basics: Understanding ReAct Agent Pattern</title>
				<link>https://blog.ssdindo.com/posts/back-to-basics-understanding-react-agent-pattern/</link>
				<pubDate>Fri, 25 Sep 2026 09:00:00 +0700</pubDate>
				<guid>https://blog.ssdindo.com/posts/back-to-basics-understanding-react-agent-pattern/</guid>
				<description>Going back to basics with ReAct agent pattern taught me that most of the complexity is about handling a LLM output by parsing and adjusting prompt as to make sure the LLM output pattern matches what we expect while also handling the unexpected.</description>
			</item>
	</channel>
</rss>
