<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>schristoph.online</title><link>https://schristoph.online/tags/strandsagents/</link><description>Personal homepage and blog of Stefan Christoph</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><copyright>Stefan Christoph. All rights reserved.</copyright><lastBuildDate>Tue, 02 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://schristoph.online/tags/strandsagents/index.xml" rel="self" type="application/rss+xml"/><item><title>Welcome to the Family: I Sat GPT-5.5 and Claude Opus Down on Bedrock</title><link>https://schristoph.online/blog/openai-on-bedrock-welcome-to-the-family/?utm=rss-feed</link><pubDate>Tue, 02 Jun 2026 00:00:00 +0000</pubDate><guid>https://schristoph.online/blog/openai-on-bedrock-welcome-to-the-family/</guid><description>&lt;div class="tldr" data-pagefind-weight="5" data-pagefind-meta="tldr" style="display:block;font-size:.875em;margin:2rem 0;border-left:4px solid #ccc;padding-left:1rem;line-height:1.5;">&lt;strong>TL;DR:&lt;/strong> OpenAI&amp;rsquo;s GPT-5.5, GPT-5.4, and Codex went GA on Amazon Bedrock on June 1, 2026. To get a feel for it, I wired up two Strands agents — Claude Opus 4.8 and GPT-5.5 — and let them chat, with Opus playing the older sibling welcoming the newcomer. It took about 50 lines. The charming part was the banter. The instructive part was that the two agents needed two different APIs to talk, which is a nuance in the &amp;ldquo;one API for every model&amp;rdquo; story worth understanding before you build.&lt;/div>
&lt;p>A new model moved into the house this week, so somebody had to show it around.&lt;/p></description></item><item><title>Building Agents That Read the Web Right</title><link>https://schristoph.online/blog/building-agents-that-read-the-web-right/?utm=rss-feed</link><pubDate>Tue, 14 Apr 2026 00:00:00 +0000</pubDate><guid>https://schristoph.online/blog/building-agents-that-read-the-web-right/</guid><description>&lt;h2 id="the-other-side-of-the-coin">The Other Side of the Coin&lt;/h2>
&lt;p>In a recent article, I made my website AI-agent friendly [1], adding llms.txt, Markdown output, and content negotiation to a Hugo site on AWS. That article was about the &lt;em>producer&lt;/em> side: how to serve content that agents can consume efficiently.&lt;/p>
&lt;p>But I left a question unanswered: &lt;strong>what does it look like from the agent&amp;rsquo;s perspective?&lt;/strong>&lt;/p>
&lt;p>In this article, I&amp;rsquo;m building two agents. Same task, same website, same model. The only difference: one reads the web the old way, the other uses the infrastructure I just built. The code is written with the Strands Agents SDK [2], an open-source framework from AWS for building AI agents in Python.&lt;/p></description></item></channel></rss>