<?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/68966959a914492db08e8f0e82c578ca&quot; frameborder=&quot;0&quot; width=&quot;1152&quot; height=&quot;864&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>864</height><width>1152</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>864</thumbnail_height><thumbnail_width>1152</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/68966959a914492db08e8f0e82c578ca-1687432572078.gif</thumbnail_url><duration>774.319</duration><title>Prompts and completions: how to structure your AI&apos;s knowledge base 🤖</title><description>Hey there! In this video, I&apos;m going to talk about prompts and completions, which are essentially the dialogue that your AI will have with its clients. I&apos;ll explain how to provide training data to your AI so that it can use your data instead of generalized knowledge from the internet. We&apos;ll also discuss how many prompts and completions you need, depending on whether you&apos;re coaching or mentoring and how niche your areas of expertise are. I&apos;ll use a tree analogy to explain how to structure your prompts and completions, starting with the trunk (fundamentals) and branching out into areas of expertise. Finally, I&apos;ll share some tips on how to improve your AI&apos;s learning through defined tuning and feedback.</description></oembed>