<?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/ad9f1df8cd4849cfb8fabfb4bdf45230&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/ad9f1df8cd4849cfb8fabfb4bdf45230-186db435b10a6914.gif</thumbnail_url><duration>5175.948</duration><title>Building a Multi-Tool Agent Framework in Python 🛠️</title><description>In this video, I walk through the process of setting up a basic agent framework that includes functions for reading and writing files, as well as listing directories. I emphasize the importance of keeping sensitive information, like API keys, out of version control by using a .env file and a .gitignore. I also discuss how to structure tool definitions and handle tool calls effectively. Viewers are encouraged to implement the code examples provided and experiment with the agent&apos;s functionality. Please ensure to follow the naming conventions for folders and files as we develop this documentation agent.</description></oembed>