<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Architecture on Rafael Zago</title><link>https://www.rafaelvzago.com/en/tags/architecture/</link><description>Recent content in Architecture on Rafael Zago</description><generator>Hugo</generator><language>en-US</language><copyright>© Rafael Zago</copyright><lastBuildDate>Fri, 24 Jul 2026 16:16:10 -0300</lastBuildDate><atom:link href="https://www.rafaelvzago.com/en/tags/architecture/index.xml" rel="self" type="application/rss+xml"/><item><title>Skupper + InstructLab: controlling and protecting AI (act 1)</title><link>https://www.rafaelvzago.com/en/posts/controlando-progetendo-ia-deepseek-skupper-istio-primeiro-ato/</link><pubDate>Fri, 02 May 2025 00:00:00 -0300</pubDate><guid>https://www.rafaelvzago.com/en/posts/controlando-progetendo-ia-deepseek-skupper-istio-primeiro-ato/</guid><description>&lt;p>&lt;a href="https://www.rafaelvzago.com/assets/img/headers/controlando-e-protegendo-modelos-de-ia-pt1.png" class="img-lightbox" data-lightbox>
	&lt;img src="https://www.rafaelvzago.com/assets/img/headers/controlando-e-protegendo-modelos-de-ia-pt1.png" alt="" loading="lazy" decoding="async">
&lt;/a>&lt;/p>
&lt;h2 id="the-story-behind-this-solution-pattern">The story behind this solution pattern&lt;/h2>
&lt;p>Growing demand for AI-driven applications brings a hard problem: how do you deploy and operate AI models securely in environments that need strict data protection, while those models still have to be reachable by public services? That need became clear while building a local AI chatbot meant to handle sensitive and proprietary information — we needed a design that kept the model inside a protected environment.&lt;/p></description></item></channel></rss>