<?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/f9e0152e67de40aeaf99886c8d6e3a11&quot; frameborder=&quot;0&quot; width=&quot;1858&quot; height=&quot;1393&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1393</height><width>1858</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1393</thumbnail_height><thumbnail_width>1858</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/f9e0152e67de40aeaf99886c8d6e3a11-1b8d5754e0bb034f.gif</thumbnail_url><duration>775.427</duration><title>ai-agent-tools</title><description>In this video, I present my project on AI agent tools, specifically an AI research assistant built on LangChain and OpenAI LLM. The assistant features a web search tool via DuckDuckGo, a Wikipedia tool, and custom tools for saving outputs to a text file and fetching random dad jokes. I walk through the code, explaining the output schema and the system prompt that guides the AI&apos;s responses. During the demo, I show how to research a topic, such as explaining how electric cars work, and save the findings to a file. I encourage viewers to explore the capabilities of this AI assistant and consider how it might be useful in their own projects.</description></oembed>