<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Agents on Enrique Goberna</title><link>https://enriquegoberna.com/tags/agents/</link><description>Recent content in Agents on Enrique Goberna</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Sun, 06 Sep 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://enriquegoberna.com/tags/agents/index.xml" rel="self" type="application/rss+xml"/><item><title>Beyond RAG: Building a Stateful AI System for Longitudinal Training Decisions</title><link>https://enriquegoberna.com/posts/beyond-rag-building-a-stateful-ai-system-for-longitudinal-training-decisions/</link><pubDate>Sun, 06 Sep 2026 00:00:00 +0000</pubDate><guid>https://enriquegoberna.com/posts/beyond-rag-building-a-stateful-ai-system-for-longitudinal-training-decisions/</guid><description>RAG still describes part of this system. It stopped describing the interesting part once retrieved context became durable state that could constrain the next decision.</description></item></channel></rss>