<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Spring AI on PG Blog</title><link>https://pg-blogs.netlify.app/tags/spring-ai/</link><description>Recent content in Spring AI on PG Blog</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sat, 04 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://pg-blogs.netlify.app/tags/spring-ai/index.xml" rel="self" type="application/rss+xml"/><item><title>LLM Frameworks vs. the Raw SDK in Java</title><link>https://pg-blogs.netlify.app/posts/26-llm-frameworks-vs-the-raw-sdk-in-java/</link><pubDate>Sat, 04 Jul 2026 00:00:00 +0000</pubDate><guid>https://pg-blogs.netlify.app/posts/26-llm-frameworks-vs-the-raw-sdk-in-java/</guid><description>&lt;h2 id="introduction"&gt;Introduction&lt;/h2&gt;
&lt;p&gt;Every LLM ecosystem now has at least one framework promising to make agents easier to build, and every framework post either oversells the abstraction or dismisses it outright. Neither is useful. The only honest way to evaluate a framework is to build the same thing twice — once on the vendor&amp;rsquo;s raw SDK, once on the framework — and compare what each version actually cost you and actually gave you back.&lt;/p&gt;</description></item></channel></rss>