<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Laya on Pavan Chavali</title><link>https://pchavali09.github.io/tags/laya/</link><description>Recent content in Laya on Pavan Chavali</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><lastBuildDate>Sun, 25 Oct 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://pchavali09.github.io/tags/laya/index.xml" rel="self" type="application/rss+xml"/><item><title>The Model Is the Easy Part: Einstein, Laya and Case Routing</title><link>https://pchavali09.github.io/posts/laya-decision-model/</link><pubDate>Sun, 25 Oct 2026 00:00:00 +0000</pubDate><guid>https://pchavali09.github.io/posts/laya-decision-model/</guid><description>&lt;img src="https://pchavali09.github.io/posts/laya-decision-model/cover-page-laya-decision-model" alt="The Model Is the Easy Part: Einstein, Laya and Case Routing" style="max-width: 100%; margin-bottom: 20px;" /&gt;&lt;br /&gt;&lt;p&gt;A fine-tuned model can read a customer&amp;rsquo;s angry paragraph and pick the right department in about 40 milliseconds. That&amp;rsquo;s on a single T4 GPU, with a model you can download for free. It used to mean a pile of rules. Now it feels like magic, and the instinct is to point it at the work and wait for the wonders.&lt;/p&gt;
&lt;p&gt;I&amp;rsquo;ve watched this story develop from the other end. When I work on older Service Cloud orgs — upgrades, migrations — routing lives in rules. I have seen it many times. Then Einstein arrived with a gate and a confidence score. Now there are small open decision models like Laya, which you run yourself.&lt;/p&gt;</description></item></channel></rss>