<?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 Jennifer Reif</title><link>https://jmhreif.com/tags/agents/</link><description>Recent content in agents on Jennifer Reif</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><lastBuildDate>Thu, 23 Apr 2026 09:00:00 -0600</lastBuildDate><atom:link href="https://jmhreif.com/tags/agents/index.xml" rel="self" type="application/rss+xml"/><item><title>Agents, Tools, and MCP: A Mental Model That Actually Helps</title><link>https://jmhreif.com/blog/2026/agents-mcp-thinking/</link><pubDate>Thu, 23 Apr 2026 09:00:00 -0600</pubDate><guid>https://jmhreif.com/blog/2026/agents-mcp-thinking/</guid><description>Photo credit AI feels magical right now, and it is moving fast with new frameworks every week, new patterns every month. And there is a lot of noise about agents specifically, including some mixed signals. From &amp;#34;agents are just LLM wrappers&amp;#34;, to &amp;#34;agents are fully autonomous,&amp;#34; and &amp;#34;agents will replace everything&amp;#34;, none of it is particularly useful when you are trying to build something real. The magic looks good on paper until it meets real systems.</description></item></channel></rss>