[Video] Chaining LLMs for Better Results using Agentic AI

Hey Community!

We're happy to share the next video in the "Code to Care" series on our InterSystems Developers YouTube:

⏯  Chaining LLMs for Better Results using Agentic AI

https://www.youtube.com/embed/hAtuAIihBVA
[This is an embedded link, but you cannot view embedded content directly on the site because you have declined the cookies necessary to access it. To view embedded content, you would need to accept all cookies in your Cookies Settings]

In this video, you will see a practical example of Agentic AI using a compound workflow of multiple large language models (LLMs) to improve the quality of output. The scenario involves generating a marketing plan for a new product: one LLM drafts the plan, another critiques it, and a third produces a final, improved version based on the critique. The video also walks through the process in code, demonstrating how chaining LLMs can enhance results for complex tasks. It also discusses the trade-offs - higher cost and longer execution time - for more accurate, policy-aligned, and refined outputs.

🗣 Presenter: @Don Woodlock, Head of Global Healthcare Solutions, InterSystems

Enjoy watching, and subscribe for more videos! 👍