<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>AI Engineering on Jamal Yusuf</title><link>https://jamal.dev/categories/ai-engineering/</link><description>Recent content in AI Engineering on Jamal Yusuf</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sat, 20 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://jamal.dev/categories/ai-engineering/index.xml" rel="self" type="application/rss+xml"/><item><title>Context Engineering for Production Agentic Systems</title><link>https://jamal.dev/writing/context-engineering-production-agents/</link><pubDate>Sat, 20 Jun 2026 00:00:00 +0000</pubDate><guid>https://jamal.dev/writing/context-engineering-production-agents/</guid><description>&lt;p&gt;There is a moment in every complex AI project when the prompts stop working.&lt;/p&gt;
&lt;p&gt;You have beautiful ReAct loops. You have tool schemas. You have a vector store full of relevant documents. And yet the agent drifts. It forgets constraints three turns in. It hallucinates policy details it was explicitly told. It loses the thread between a membership eligibility check and the downstream claims adjustment it was supposed to trigger.&lt;/p&gt;</description></item></channel></rss>