<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Claude API on AI VOID</title><link>https://ai-blog.noorshomelab.dev/tags/claude-api/</link><description>Recent content in Claude API on AI VOID</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sun, 24 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://ai-blog.noorshomelab.dev/tags/claude-api/index.xml" rel="self" type="application/rss+xml"/><item><title>Integrating Your First AI Agent: Claude Code or Codex</title><link>https://ai-blog.noorshomelab.dev/kanbots-ai-worktrees-2026/integrate-first-ai-agent/</link><pubDate>Sun, 24 May 2026 00:00:00 +0000</pubDate><guid>https://ai-blog.noorshomelab.dev/kanbots-ai-worktrees-2026/integrate-first-ai-agent/</guid><description>&lt;p&gt;This chapter marks a pivotal moment for Kanbots. We&amp;rsquo;re moving beyond a static Kanban board and injecting intelligence by integrating our first AI agent. You&amp;rsquo;ll learn how to connect an AI model like Claude Code or a modern OpenAI equivalent (e.g., GPT-4o) to a Kanban card. This enables the agent to perform specific tasks, such as generating code, within its dedicated git worktree. By the end of this milestone, your Kanbots application will be able to dispatch a task to an AI agent, have that agent generate content (like a simple code file), and observe the results directly within the isolated worktree associated with your Kanban card. This lays the foundation for powerful, automated development workflows.&lt;/p&gt;</description></item></channel></rss>