<?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 Ted Factory</title><link>https://tedfactory.com/en/tags/codex/</link><description>Recent content in Codex on Ted Factory</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sun, 19 Apr 2026 16:28:05 +0900</lastBuildDate><atom:link href="https://tedfactory.com/en/tags/codex/index.xml" rel="self" type="application/rss+xml"/><item><title>Where Should You Use Codex? A Guide to CLI, App, Cursor, and Claude Code</title><link>https://tedfactory.com/en/notes/essays/codex-usage-environments-guide/</link><pubDate>Sun, 12 Apr 2026 00:00:00 +0900</pubDate><guid>https://tedfactory.com/en/notes/essays/codex-usage-environments-guide/</guid><description>&lt;h1 id="where-should-you-use-codex-a-guide-to-cli-app-cursor-and-claude-code"&gt;Where Should You Use Codex? A Guide to CLI, App, Cursor, and Claude Code&lt;a class="anchor" href="#where-should-you-use-codex-a-guide-to-cli-app-cursor-and-claude-code"&gt;#&lt;/a&gt;&lt;/h1&gt;
&lt;p&gt;2026-04-12&lt;/p&gt;
&lt;p&gt;&lt;img src="https://tedfactory.com/images/notes/codex-usage-environments-guide-cover.png" alt="Codex environment guide cover" /&gt;&lt;/p&gt;
&lt;p&gt;These days, a lot of people are saying good things about &lt;code&gt;Codex&lt;/code&gt;. But the moment you try to actually use it, things get confusing.&lt;/p&gt;
&lt;ul&gt;
&lt;li&gt;Should you use &lt;code&gt;Codex CLI&lt;/code&gt;?&lt;/li&gt;
&lt;li&gt;Is there a separate &lt;code&gt;Codex App&lt;/code&gt;?&lt;/li&gt;
&lt;li&gt;Should you install the Codex extension inside &lt;code&gt;Cursor&lt;/code&gt;?&lt;/li&gt;
&lt;li&gt;Or is it enough to simply choose a &lt;code&gt;Codex model&lt;/code&gt; inside Cursor chat?&lt;/li&gt;
&lt;li&gt;Should you connect it to &lt;code&gt;Claude Code&lt;/code&gt; as a plugin?&lt;/li&gt;
&lt;/ul&gt;
&lt;p&gt;I had the same questions, so I went through the official documentation and organized what I found. I tried to write this in a way that even beginners, or people who do not usually work with coding tools, can follow comfortably.&lt;/p&gt;</description></item><item><title>How to Add Coding Runtimes to an AI Agent Web Service</title><link>https://tedfactory.com/en/notes/essays/ai-agent-webservice-coding-runtime-strategy/</link><pubDate>Sun, 19 Apr 2026 00:00:00 +0900</pubDate><guid>https://tedfactory.com/en/notes/essays/ai-agent-webservice-coding-runtime-strategy/</guid><description>&lt;h1 id="how-to-add-coding-runtimes-to-an-ai-agent-web-service"&gt;How to Add Coding Runtimes to an AI Agent Web Service&lt;a class="anchor" href="#how-to-add-coding-runtimes-to-an-ai-agent-web-service"&gt;#&lt;/a&gt;&lt;/h1&gt;
&lt;p&gt;2026-04-19&lt;/p&gt;
&lt;p&gt;&lt;img src="https://tedfactory.com/images/notes/ai-agent-webservice-coding-runtime-strategy-cover.png" alt="Cover for coding runtime strategy in an AI agent web service" /&gt;&lt;/p&gt;
&lt;p&gt;When you start designing or building an AI agent web service, one question shows up surprisingly early:&lt;/p&gt;
&lt;p&gt;&lt;strong&gt;&amp;ldquo;If these agents are supposed to do real work, where does their coding ability actually come from?&amp;rdquo;&lt;/strong&gt;&lt;/p&gt;
&lt;p&gt;At first, it is tempting to think the answer is straightforward. Call a strong model API, add file editing, let it run shell commands, execute tests, and package the results. But once you look more closely, the problem expands fast.&lt;/p&gt;</description></item></channel></rss>