<?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 Pythonflow</title>
		<link>https://pythonflow.com/tags/agents/</link>
		<description>Recent content in Agents on Pythonflow</description>
		<generator>Hugo</generator>
		<language>en-us</language>
		
			<managingEditor>alicandonmez90@gmail.com (flowfelis)</managingEditor>
		
		
			<webMaster>alicandonmez90@gmail.com (flowfelis)</webMaster>
		
		
		
			<lastBuildDate>Sat, 27 Jun 2026 07:00:00 +0100</lastBuildDate>
		
			<atom:link href="https://pythonflow.com/tags/agents/index.xml" rel="self" type="application/rss+xml" />
			<item>
				<title>LangBot Day 10: Agents and Tool Calling — Let the LLM Decide What to Do</title>
				<link>https://pythonflow.com/posts/langbot-day-10-agents/</link>
				<pubDate>Sat, 27 Jun 2026 07:00:00 +0100</pubDate><author>alicandonmez90@gmail.com (flowfelis)</author>
				<guid>https://pythonflow.com/posts/langbot-day-10-agents/</guid>
				<description>&lt;p&gt;&lt;strong&gt;Recap:&lt;/strong&gt; On Day 9, LangBot became a full RAG pipeline — every chat message retrieves relevant documents and the LLM answers from them. The &lt;code&gt;/search&lt;/code&gt; command, list-mode routing, and regular chat all coexist. But there is a problem hiding in plain sight: the routing logic is hand-coded in &lt;code&gt;if&lt;/code&gt;/&lt;code&gt;elif&lt;/code&gt; blocks. LangBot doesn&amp;rsquo;t &lt;em&gt;decide&lt;/em&gt; anything — it follows a script. Today we replace that script with an &lt;strong&gt;agent&lt;/strong&gt;: an LLM that reasons about which tool to use, calls it, and responds — autonomously.&lt;/p&gt;</description>
			</item>
	</channel>
</rss>
