<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Codex on Bruce on AI Engineering</title><link>http://www.heyuan110.com/tags/codex/</link><description>Recent content in Codex on Bruce on AI Engineering</description><generator>Hugo</generator><language>en</language><lastBuildDate>Fri, 06 Mar 2026 22:00:00 +0800</lastBuildDate><atom:link href="http://www.heyuan110.com/tags/codex/index.xml" rel="self" type="application/rss+xml"/><item><title>OpenAI Symphony: From Issue Ticket to Pull Request Without a Developer</title><link>http://www.heyuan110.com/posts/ai/2026-03-05-openai-symphony-autonomous-coding/</link><pubDate>Fri, 06 Mar 2026 22:00:00 +0800</pubDate><guid>http://www.heyuan110.com/posts/ai/2026-03-05-openai-symphony-autonomous-coding/</guid><description>&lt;p&gt;&lt;img src="http://www.heyuan110.com/posts/ai/2026-03-05-openai-symphony-autonomous-coding/cover.webp"
 alt="OpenAI Symphony — autonomous coding agent orchestration framework"
 
 loading="lazy"
 decoding="async"
 fetchpriority="low"
 width="1200"
 height="630"
/&gt;
&lt;/p&gt;
&lt;p&gt;What if your issue tracker could fix its own tickets?&lt;/p&gt;
&lt;p&gt;OpenAI just open-sourced &lt;strong&gt;Symphony&lt;/strong&gt;, an automation service that monitors your project&amp;rsquo;s issue tracker (like Linear), spawns autonomous coding agents (like Codex) for each task, and delivers verified pull requests — complete with CI status, code reviews, and walkthrough videos — before a human even looks at the code.&lt;/p&gt;
&lt;p&gt;This isn&amp;rsquo;t another AI code assistant that waits for your prompt. Symphony represents a fundamental shift in how software gets built: from &lt;strong&gt;developer-driven coding&lt;/strong&gt; to &lt;strong&gt;project-driven orchestration&lt;/strong&gt;. In this guide, we&amp;rsquo;ll break down Symphony&amp;rsquo;s architecture, explain how it works under the hood, and show you how to set it up for your own projects.&lt;/p&gt;</description></item><item><title>Xcode 26.3 Agentic Coding: Claude Agent &amp; Codex in Apple IDE</title><link>http://www.heyuan110.com/posts/ai/2026-02-20-xcode-agentic-coding/</link><pubDate>Fri, 20 Feb 2026 10:00:00 +0800</pubDate><guid>http://www.heyuan110.com/posts/ai/2026-02-20-xcode-agentic-coding/</guid><description>&lt;p&gt;On February 3, 2026, Apple released Xcode 26.3 Release Candidate, officially introducing &lt;strong&gt;Agentic Coding&lt;/strong&gt; to its flagship IDE. This is a landmark moment for Apple&amp;rsquo;s developer tools — developers can now use Anthropic&amp;rsquo;s Claude Agent and OpenAI&amp;rsquo;s Codex directly inside Xcode, letting AI agents autonomously plan, code, build, and test entire features.&lt;/p&gt;
&lt;p&gt;This goes far beyond code completion or chat-based assistance. Unlike the AI features in Xcode 26, Agentic Coding gives AI the ability to &lt;strong&gt;make decisions and take action independently&lt;/strong&gt; — it can understand your project architecture, search Apple documentation, modify multiple files, trigger builds and tests, and even capture Xcode Previews screenshots to visually verify that the UI matches design intent before iterating further.&lt;/p&gt;</description></item></channel></rss>