How to Improve LLMs with Tools (ft. OpenAI Agents SDK)

🤝 Want your team maximizing Claude? I run 1:1 and team AI workshops for companies doing $1M+ per year: https://aibuilder.academy/yt/-BUs1CPHKfU This is the 2nd video in a series on AI agents. I discuss how LLMs can perform actions via tools and share a code example with OpenAI's Agents SDK. 📰 Blog: https://medium.com/@shawhin/how-to-improve-llms-with-tools-69cc68c804ed?sk=3ffd8308ce4905617b136a02cfa8dd83 💻 Code: https://github.com/ShawhinT/YouTube-Blog/tree/main/agents/1-tool_use ▶️ Series Playlist: https://www.youtube.com/playlist?list=PLz-ep5RbHosU02OKABBkbsQrYWmQfoZMH References [1] https://youtu.be/SEZ7j31u67A [2] https://openai.github.io/openai-agents-python/agents/ [3] https://huggingface.co/learn/agents-course/en/unit1/tools [4] https://github.com/openai/openai-agents-python/blob/main/examples/basic/stream_items.py Intro - 0:00 Traditional Software vs Agents - 0:26 How does Tool-use Work? - 3:38 Way 1: Prompting - 7:35 Way 2: Fine-tuning - 11:06 Example: YouTube Video Agent - 12:15 Demo - 22:10 What's Next? - 23:38