<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Context Engineering on Diego Rodrigo</title><link>https://diegorodrigo.dev/en/tags/context-engineering/</link><description>Recent content in Context Engineering on Diego Rodrigo</description><image><title>Diego Rodrigo</title><url>https://diegorodrigo.dev/blog-image.png</url><link>https://diegorodrigo.dev/blog-image.png</link></image><generator>Hugo</generator><language>en</language><copyright>Copyright © 2022 - Diego Rodrigo. All rights reserved.</copyright><lastBuildDate>Tue, 21 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://diegorodrigo.dev/en/tags/context-engineering/index.xml" rel="self" type="application/rss+xml"/><item><title>How to give agents context without turning everything into a giant prompt</title><link>https://diegorodrigo.dev/en/2026/04/21/how-to-give-agents-context-without-a-giant-prompt/</link><pubDate>Tue, 21 Apr 2026 00:00:00 -0300</pubDate><guid>https://diegorodrigo.dev/en/2026/04/21/how-to-give-agents-context-without-a-giant-prompt/</guid><description>A practical model for treating agent context as a budget instead of a pile: what to load, what to summarize, what to link, and what to keep out of the prompt.</description></item></channel></rss>