<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Blog on Abbas Sharifitabar</title><link>https://sharifitabar.ir/blog/</link><description>Recent content in Blog on Abbas Sharifitabar</description><generator>Hugo</generator><language>en</language><lastBuildDate>Mon, 02 Nov 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://sharifitabar.ir/blog/index.xml" rel="self" type="application/rss+xml"/><item><title>Your Agent Doesn’t Need to Leave the JVM (Mostly)</title><link>https://sharifitabar.ir/blog/agents-on-the-jvm/</link><pubDate>Mon, 02 Nov 2026 00:00:00 +0000</pubDate><guid>https://sharifitabar.ir/blog/agents-on-the-jvm/</guid><description>&lt;p&gt;When a Spring team is asked to “add AI”, the first design move is usually the same. Stand up a Python service next to the backend and build the agent there. Python earned that default. I build agents in Python against the Anthropic API myself, and I will keep doing so for part of the work.&lt;/p&gt;&#10;&lt;p&gt;The default still deserves a second look. Spring AI 2.1.0-RC1 shipped on 23 October, a day after Spring Boot 4.2.0-RC1 and Spring Framework 7.1.0-RC1. These are release candidates, not final releases, and I will say where that matters. Even so, they make a different layout easy to justify: the agent lives inside the Spring service that already owns your domain.&lt;/p&gt;</description></item></channel></rss>