{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/f9e0152e67de40aeaf99886c8d6e3a11\" frameborder=\"0\" width=\"1858\" height=\"1393\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1393,"width":1858,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1393,"thumbnail_width":1858,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/f9e0152e67de40aeaf99886c8d6e3a11-1b8d5754e0bb034f.gif","duration":775.427,"title":"ai-agent-tools","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'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."}