<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Claude-Sdk on René Zander | AI Automation Consultant</title><link>https://renezander.com/tags/claude-sdk/</link><description>Recent content in Claude-Sdk on René Zander | AI Automation Consultant</description><generator>Hugo</generator><language>en</language><lastBuildDate>Wed, 01 Apr 2026 12:00:00 +0200</lastBuildDate><atom:link href="https://renezander.com/tags/claude-sdk/index.xml" rel="self" type="application/rss+xml"/><item><title>Claude Code SDK Agents: Build Production Agents Without the Loop</title><link>https://renezander.com/blog/claude-code-sdk-agents/</link><pubDate>Wed, 01 Apr 2026 12:00:00 +0200</pubDate><guid>https://renezander.com/blog/claude-code-sdk-agents/</guid><description>&lt;p>Most &amp;ldquo;build an agent with Claude&amp;rdquo; tutorials hand you a while-loop around &lt;code>client.messages.create&lt;/code>, a hand-rolled tool dispatcher, and a promise that you&amp;rsquo;ll wire up file reads and shell execution yourself. That works. It also means you spend two weeks rebuilding the same plumbing that Claude Code already ships with.&lt;/p>
&lt;p>The Claude Code SDK, sometimes called the Claude Agent SDK, is the shortcut. Same runtime as the &lt;code>claude&lt;/code> CLI, exposed as a library in TypeScript and Python, plus a print mode you can call from a bash cron job. You get file tools, bash, MCP client, subagents, hooks, and permission modes without writing any of it.&lt;/p></description></item></channel></rss>