[Video] Explaining Agentic AI Through Automated Bug Fixing

Hey Community!

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

⏯  Explaining Agentic AI Through Automated Bug Fixing

https://www.youtube.com/embed/K8XhU27b5Po
[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, the presenter introduces the concept of agentic AI using the example of automated bug fixing. He explains how such a system operates by creating a loop between an application, a large language model (such as OpenAI, Claude, or Gemini), and a set of predefined tools. The LLM iteratively selects tools, such as listing, reading, editing, or executing program files, while the framework carries out these actions and returns the results. This process repeats until the model delivers a final fix. Rather than relying on a developer to outline every step, the LLM generates its own sequence of actions, making the approach more flexible and adaptive as language models continue to advance.

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

Enjoy watching, and subscribe for more videos! 👍