<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Function-Calling on EnRedAndo Me - Carlos Prados</title><link>https://carlos.enredando.me/tags/function-calling/</link><description>Recent content in Function-Calling on EnRedAndo Me - Carlos Prados</description><generator>Hugo -- gohugo.io</generator><language>en</language><managingEditor>mail@carlosprados.com (Carlos Prados)</managingEditor><webMaster>mail@carlosprados.com (Carlos Prados)</webMaster><copyright>© 2026 Carlos Prados</copyright><lastBuildDate>Tue, 09 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://carlos.enredando.me/tags/function-calling/index.xml" rel="self" type="application/rss+xml"/><item><title>Mastering Agentic AI: The Tool Use Pattern</title><link>https://carlos.enredando.me/posts/agentic-ai-tool-use/</link><pubDate>Tue, 09 Jun 2026 00:00:00 +0000</pubDate><author>mail@carlosprados.com (Carlos Prados)</author><guid>https://carlos.enredando.me/posts/agentic-ai-tool-use/</guid><description>&lt;p&gt;In the &lt;a href="https://carlos.enredando.me/posts/agentic-ai-reflection/" &gt;previous post&lt;/a&gt;, we taught our agents to look in the mirror — Reflection, the Producer-Critic loop that lifts output quality. Quality is good. But there&amp;rsquo;s still something missing: every pattern we&amp;rsquo;ve seen so far operates inside the LLM&amp;rsquo;s closed world. It thinks, it routes, it parallelizes, it critiques itself, but at no point does it actually &lt;em&gt;do&lt;/em&gt; anything that touches reality.&lt;/p&gt;
&lt;p&gt;That ends here. &lt;strong&gt;Tool Use&lt;/strong&gt; is the pattern where an LLM stops being a text generator and becomes an agent in the literal sense: something that can perceive, decide, and act.&lt;/p&gt;</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://carlos.enredando.me/posts/agentic-ai-tool-use/featured.jpg"/></item></channel></rss>