<?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/2ff33d9f0bec404ba01a813b99fda78d&quot; frameborder=&quot;0&quot; width=&quot;1920&quot; height=&quot;1440&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1440</height><width>1920</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1440</thumbnail_height><thumbnail_width>1920</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/2ff33d9f0bec404ba01a813b99fda78d-263a832087c9896c.gif</thumbnail_url><duration>1328.585</duration><title>Building a Data Science Agent 🚀</title><description>In this video, I walk you through my project where I created a data science agent designed to tackle machine learning challenges. I demonstrate how this agent interacts with a Kaggle competition, specifically the Space Titanic challenge, and how it performs dynamic web searches to generate a research report. I also discuss the steps involved in defining agent states and executing Python code for analysis. Please make sure to use the tool for analysis and train at least one model based on the results.</description></oembed>