<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>code-review on Lankan Lion — Practical Engineering Notes</title><link>https://blog.lankanlion.com/tags/code-review/</link><description>Recent content in code-review on Lankan Lion — Practical Engineering Notes</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><lastBuildDate>Sat, 26 Sep 2026 08:50:00 -0500</lastBuildDate><atom:link href="https://blog.lankanlion.com/tags/code-review/index.xml" rel="self" type="application/rss+xml"/><item><title>AI Agents for Developers: What Changes When Your Coding CLI Can Act</title><link>https://blog.lankanlion.com/post/ai-agents-for-developers/</link><pubDate>Sat, 26 Sep 2026 08:50:00 -0500</pubDate><guid>https://blog.lankanlion.com/post/ai-agents-for-developers/</guid><description>&lt;p>If you use Codex or Claude Code in a terminal, you&amp;rsquo;ve seen the shift: the tool doesn&amp;rsquo;t just answer questions about your code. It reads files, edits them, runs commands, and reacts to the output. That&amp;rsquo;s the practical meaning of &amp;ldquo;agent&amp;rdquo;, and it changes what you supply and what you check.&lt;/p>
&lt;p>This post is for developers who use these tools but haven&amp;rsquo;t studied how agents work. We&amp;rsquo;ll walk through one small change in an unfamiliar repository and mark where the engineer sets the boundary and verifies the outcome.&lt;/p></description></item></channel></rss>