<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Workflow on Rohit Garg</title><link>https://rohit-garg.me/tags/workflow/</link><description>Recent content in Workflow on Rohit Garg</description><generator>Hugo</generator><language>en</language><copyright>© Rohit Garg</copyright><lastBuildDate>Mon, 01 Jun 2026 11:30:00 +0530</lastBuildDate><atom:link href="https://rohit-garg.me/tags/workflow/index.xml" rel="self" type="application/rss+xml"/><item><title>How to Create an AI Agent: A Calendar Planning Example</title><link>https://rohit-garg.me/langgraph-openai-calendar-agent/</link><pubDate>Mon, 01 Jun 2026 11:30:00 +0530</pubDate><guid>https://rohit-garg.me/langgraph-openai-calendar-agent/</guid><description>&lt;p>AI agents become easier to understand when you stop imagining them as magic.&lt;/p>
&lt;p>The useful version is more ordinary: a goal, a few steps, some shared state, one or two model calls, clear stop conditions, and a human review point before anything important changes. LangGraph is good for this because it lets you describe the work as a graph instead of hiding everything inside a chat loop.&lt;/p></description></item><item><title>Codex Skills in Practice</title><link>https://rohit-garg.me/codex-skills-real-example/</link><pubDate>Tue, 28 Apr 2026 13:30:00 +0530</pubDate><guid>https://rohit-garg.me/codex-skills-real-example/</guid><description>&lt;p>Codex skills are small instruction packs that teach Codex how to do a specific kind of work. They are not magic plugins. A skill is closer to a documented workflow: when the task matches the skill, Codex reads the instructions and follows the steps.&lt;/p></description></item></channel></rss>