<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Coding on DataThrillz</title><link>https://datathrillz.com/tags/coding/</link><description>Recent content in Coding on DataThrillz</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Fri, 06 Mar 2026 14:35:47 +0000</lastBuildDate><atom:link href="https://datathrillz.com/tags/coding/index.xml" rel="self" type="application/rss+xml"/><item><title>Understanding How Claude Code Works</title><link>https://datathrillz.com/posts/2026-03-06-understanding-how-claude-code-works/</link><pubDate>Fri, 06 Mar 2026 14:35:47 +0000</pubDate><guid>https://datathrillz.com/posts/2026-03-06-understanding-how-claude-code-works/</guid><description>&lt;h2 id="inside-claude-code-how-sub-agents-and-parallel-execution-define-next-gen-coding-agents"&gt;Inside Claude Code: How Sub-Agents and Parallel Execution Define Next-Gen Coding Agents&lt;/h2&gt;
&lt;h2 id="introduction-the-evolution-of-coding-agents"&gt;Introduction: The Evolution of Coding Agents&lt;/h2&gt;
&lt;p&gt;Coding agents represent a fundamental shift in how developers interact with their codebases. Unlike traditional autocomplete tools or simple code generation models, modern coding agents operate autonomously across multiple files, maintain context over extended sessions, and can break down complex tasks into manageable subtasks. These systems leverage Large Language Models (LLMs) in sophisticated agentic loops where the model can call tools, observe results, and iteratively work toward task completion.&lt;/p&gt;</description></item></channel></rss>