<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>AI Engineering on AgentPlix - AI &amp; Automation Hub</title>
    <link>https://agentplix.com/categories/ai-engineering/</link>
    <description>Recent content in AI Engineering on AgentPlix - AI &amp; Automation Hub</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Tue, 05 May 2026 11:05:12 +0000</lastBuildDate>
    <atom:link href="https://agentplix.com/categories/ai-engineering/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Cut Claude API Costs 50% with a Self-Modifying Agent</title>
      <link>https://agentplix.com/posts/i-cut-claude-api-costs-by-50-using-this-self-modifying/</link>
      <pubDate>Tue, 05 May 2026 11:05:12 +0000</pubDate>
      <guid>https://agentplix.com/posts/i-cut-claude-api-costs-by-50-using-this-self-modifying/</guid>
      <description>I built a self-modifying agentic system that slashed my Claude API costs by 50%. Here&amp;#39;s the exact architecture, code, and techniques to replicate it.</description>
    </item>
    <item>
      <title>RAG vs Fine-Tuning: Which AI Approach Wins?</title>
      <link>https://agentplix.com/posts/rag-vs-fine-tuning-which-ai-approach-is-right-for-your/</link>
      <pubDate>Wed, 29 Apr 2026 11:02:02 +0000</pubDate>
      <guid>https://agentplix.com/posts/rag-vs-fine-tuning-which-ai-approach-is-right-for-your/</guid>
      <description>RAG vs fine-tuning for LLMs: we break down costs, use cases, and when each approach actually wins so you build the right thing the first time.</description>
    </item>
  </channel>
</rss>
