<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/529e2fdd85c94517b9b422f27e2166af&quot; frameborder=&quot;0&quot; width=&quot;1902&quot; height=&quot;1426&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1426</height><width>1902</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1426</thumbnail_height><thumbnail_width>1902</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/529e2fdd85c94517b9b422f27e2166af-26c84049d0f5f465.gif</thumbnail_url><duration>293.639</duration><title>Introducing Few-Shot Prompting Feature 🚀</title><description>Hey everyone, I&apos;m Jake from the Langsmith engineering team, and I&apos;m excited to share our newest beta feature on few-shot prompting. Few-shot prompting allows you to enhance your application&apos;s performance without complex prompt engineering by leveraging Langsmith datasets. Join me as I demonstrate how to set up and utilize this feature using a sample notebook. Let&apos;s make prompt creation easier and more effective together!</description></oembed>