<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Agentic Engineering on Fernando Ruiz</title><link>https://www.fernandoux.com/tags/agentic-engineering/</link><description>Recent content in Agentic Engineering on Fernando Ruiz</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sat, 06 Jun 2026 07:51:58 -0500</lastBuildDate><atom:link href="https://www.fernandoux.com/tags/agentic-engineering/index.xml" rel="self" type="application/rss+xml"/><item><title>I Made Claude Opus 4.8 Manage Another AI Agent While I Worked</title><link>https://www.fernandoux.com/blog/en/claude-opencode-two-agent-workflow/</link><pubDate>Sat, 06 Jun 2026 00:00:00 +0000</pubDate><guid>https://www.fernandoux.com/blog/en/claude-opencode-two-agent-workflow/</guid><description>&lt;p&gt;Have you ever used your best AI model for work that clearly did not deserve your best AI model?&lt;/p&gt;
&lt;p&gt;I have. Not because I did not understand model routing. I use cheaper models for cheaper tasks all the time. But when you are deep inside a real codebase, with tests failing, files changing, and context moving fast, it is easy to let your strongest session become the planner, executor, reviewer, secretary, and background worker at once.&lt;/p&gt;</description></item><item><title>AI Pipelines: How I Built Systems That Work While I Sleep</title><link>https://www.fernandoux.com/blog/en/ai-pipelines-claude/</link><pubDate>Mon, 11 May 2026 00:00:00 +0000</pubDate><guid>https://www.fernandoux.com/blog/en/ai-pipelines-claude/</guid><description>&lt;p&gt;Most people use AI to generate code, write copy, or fix their lives in a thousand small ways. You feed it something, it spits back something better or more structured. That&amp;rsquo;s fine. That&amp;rsquo;s the obvious use case. But one of the highest-value applications I&amp;rsquo;ve found for AI is building &lt;strong&gt;pipelines&lt;/strong&gt;, specifically with Claude.&lt;/p&gt;
&lt;p&gt;Claude is built for this. The model has a strong orientation toward multi-step workflows, tool use, and persistent context. And while there are other capable models out there, including some surprisingly good Chinese models, I&amp;rsquo;m going to focus on what I&amp;rsquo;ve actually been experimenting with. The results speak for themselves.&lt;/p&gt;</description></item><item><title>Pipelines de IA: Cómo Construí Sistemas Que Trabajan Mientras Yo Duermo</title><link>https://www.fernandoux.com/blog/es/ai-pipelines-claude/</link><pubDate>Mon, 11 May 2026 00:00:00 +0000</pubDate><guid>https://www.fernandoux.com/blog/es/ai-pipelines-claude/</guid><description>&lt;p&gt;La mayoría de la gente usa IA para generar código, escribir copy o arreglarse la vida de mil formas. Le das de comer algo y te devuelve algo mejor o más estructurado. Eso está bien. Ese es el uso obvio. Pero una de las aplicaciones de mayor valor que he encontrado para la IA es construir &lt;strong&gt;pipelines&lt;/strong&gt;, específicamente con Claude.&lt;/p&gt;
&lt;p&gt;Claude está construido para esto. El modelo tiene una fuerte orientación hacia flujos de trabajo de múltiples pasos, uso de herramientas y contexto persistente. Y aunque hay otros modelos capaces ahí afuera, incluyendo algunos modelos chinos sorprendentemente buenos, voy a enfocarme en lo que he estado experimentando. Los resultados hablan por sí mismos.&lt;/p&gt;</description></item><item><title>Designing in Words: How AI Turned UX Designers Into Their Own Frontend Engineers</title><link>https://www.fernandoux.com/blog/en/designing-in-words-vibe-coding-for-ux-designers/</link><pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate><guid>https://www.fernandoux.com/blog/en/designing-in-words-vibe-coding-for-ux-designers/</guid><description>&lt;p&gt;The design review went perfectly. You handed off a Figma file that was pixel-perfect: the right spacing, the right micro-interactions, the hover states, all of it. Three weeks later, the thing that shipped looked like it was built from memory by someone who saw your design once in a dream. Sound familiar?&lt;/p&gt;
&lt;p&gt;That story has been playing on loop for the entire history of digital product design. The designer creates. The developer interprets. Something gets lost, always. Sometimes a lot. And the designer files it under &amp;ldquo;developer error&amp;rdquo; and moves on to the next project.&lt;/p&gt;</description></item><item><title>Diseñar en Palabras: Cómo la IA Convirtió a los Diseñadores UX en Sus Propios Frontend Engineers</title><link>https://www.fernandoux.com/blog/es/designing-in-words-vibe-coding-for-ux-designers/</link><pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate><guid>https://www.fernandoux.com/blog/es/designing-in-words-vibe-coding-for-ux-designers/</guid><description>&lt;p&gt;El design review salió perfecto. Entregaste un archivo de Figma impoluto, el espaciado correcto, las micro-interacciones correctas, los hover states, todo. Tres semanas después, lo que se publicó parecía construido de memoria por alguien que vio tu diseño una vez en un sueño. ¿Te suena familiar?&lt;/p&gt;
&lt;p&gt;Esa historia lleva reproduciéndose en bucle durante toda la historia del diseño de productos digitales. El diseñador crea. El desarrollador interpreta. Algo se pierde&amp;hellip; siempre. A veces mucho. Y el diseñador lo archiva bajo &amp;ldquo;error del developer&amp;rdquo; y pasa al siguiente proyecto.&lt;/p&gt;</description></item><item><title>Vibe Coding: Lo que la IA No te Va a Decir Antes de Construir tu Primera App</title><link>https://www.fernandoux.com/blog/es/vibe-coding-what-ai-wont-tell-you-before-building-your-first-app/</link><pubDate>Sun, 15 Mar 2026 00:00:00 +0000</pubDate><guid>https://www.fernandoux.com/blog/es/vibe-coding-what-ai-wont-tell-you-before-building-your-first-app/</guid><description>&lt;p&gt;Hay una conversación que ocurre miles de veces al día alrededor del mundo. Va más o menos así:&lt;/p&gt;
&lt;blockquote&gt;
&lt;p&gt;&lt;em&gt;&amp;ldquo;Hola Claude, necesito que me hagas una aplicación tipo YouTube pero sin errores.&amp;rdquo;&lt;/em&gt;&lt;/p&gt;
&lt;/blockquote&gt;
&lt;p&gt;Y la [[IA]] responde feliz, genera código, y el usuario piensa que acaba de contratar un equipo de ingenieros por 20 dólares al mes. Tres semanas después, la aplicación tiene 47 bugs, nadie sabe por qué el login falla los martes y el creador no puede cambiar el color de un botón sin romper el sistema de pagos.&lt;/p&gt;</description></item><item><title>Vibe Coding: What AI Won't Tell You Before Building Your First App</title><link>https://www.fernandoux.com/blog/en/vibe-coding-what-ai-wont-tell-you-before-building-your-first-app/</link><pubDate>Sun, 15 Mar 2026 00:00:00 +0000</pubDate><guid>https://www.fernandoux.com/blog/en/vibe-coding-what-ai-wont-tell-you-before-building-your-first-app/</guid><description>&lt;p&gt;There&amp;rsquo;s a conversation happening thousands of times a day around the world. It goes something like this:&lt;/p&gt;
&lt;blockquote&gt;
&lt;p&gt;&lt;em&gt;&amp;ldquo;Hey Claude, I need you to build me a YouTube-like application but without bugs.&amp;rdquo;&lt;/em&gt;&lt;/p&gt;
&lt;/blockquote&gt;
&lt;p&gt;And the [[AI]] responds happily, generates code, and the user thinks they&amp;rsquo;ve just hired an engineering team for $20 a month. Three weeks later, the application has 47 bugs, nobody knows why login fails on Tuesdays, and the creator can&amp;rsquo;t change a button color without breaking the payment system.&lt;/p&gt;</description></item><item><title>Spec-Driven Development: El fin del Vibe Coding amateur y el inicio de la ingeniería de sistemas para UX</title><link>https://www.fernandoux.com/blog/es/spec-driven-development-the-end-of-amateur-vibe-coding-and-the-beginning-of-systems-engineering-for-ux/</link><pubDate>Tue, 10 Mar 2026 00:00:00 +0000</pubDate><guid>https://www.fernandoux.com/blog/es/spec-driven-development-the-end-of-amateur-vibe-coding-and-the-beginning-of-systems-engineering-for-ux/</guid><description>&lt;p&gt;El concepto de [[Vibe Coding]] es atractivo. Escribes en lenguaje natural, la IA escupe código, y en minutos tienes un prototipo. Funciona perfecto si estás haciendo un script de 100 líneas. Si intentas escalar eso a un producto real, el sistema colapsa.&lt;/p&gt;
&lt;p&gt;Me reuní con &lt;a href="https://dot.cards/ryanedge"&gt;Ryan Edge&lt;/a&gt; para desglosar exactamente cómo está utilizando agentes de [[IA]] para construir software complejo. El consenso es claro: depender de interfaces de chat para programar tiene un techo de cristal. Pierdes el contexto, la IA alucina, sobrescribe lógica existente y terminas haciendo trabajo manual para corregir a un robot.&lt;/p&gt;</description></item><item><title>Spec-Driven Development: The End of Amateur Vibe Coding and the Dawn of Systems Engineering for UX</title><link>https://www.fernandoux.com/blog/en/spec-driven-development-the-end-of-amateur-vibe-coding-and-the-beginning-of-systems-engineering-for-ux/</link><pubDate>Tue, 10 Mar 2026 00:00:00 +0000</pubDate><guid>https://www.fernandoux.com/blog/en/spec-driven-development-the-end-of-amateur-vibe-coding-and-the-beginning-of-systems-engineering-for-ux/</guid><description>&lt;p&gt;The concept of [[Vibe Coding]] is appealing. You write in natural language, AI spits out code, and you have a prototype in minutes. It works perfectly for a 100-line script. Try scaling that to a real product, and the system collapses.&lt;/p&gt;
&lt;p&gt;I sat down with &lt;a href="https://dot.cards/ryanedge"&gt;Ryan Edge&lt;/a&gt; to break down exactly how he&amp;rsquo;s using [[AI]] agents to build complex software. The consensus is clear: relying on chat interfaces to code has a glass ceiling. You lose context, the AI hallucinates, overwrites existing logic, and you end up doing manual work to correct a robot.&lt;/p&gt;</description></item></channel></rss>