<?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/bcde36f3fa424b2f80c860def0b3f164&quot; frameborder=&quot;0&quot; width=&quot;1280&quot; height=&quot;960&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>960</height><width>1280</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>960</thumbnail_height><thumbnail_width>1280</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/bcde36f3fa424b2f80c860def0b3f164-1711288002684.gif</thumbnail_url><duration>327.841</duration><title>Slate: A Seamless Integration of LLM Prompts in Traditional Code Notebooks</title><description>Hey folks, in this quick demo, I&apos;ll show you Slate, a tool I&apos;ve been working on. Slate takes inspiratiion from traditional code notebooks like Jupyter Notebooks, but adds a seamless integration with LLMs. You can work on your data set, apply transformations, and visualise it throughout your notebook. With Slate, you can easily code and transform your data when you want, and write natural language prompts that transform your data in the context of your notebook. Check out this example where I group popular science fiction books by publication year and decade. It&apos;s all executed locally in the browser. Let&apos;s see what happens!

Try it here: https://try-slate.com</description></oembed>