From the course: AI Coding Agents with GitHub Copilot and Cursor

Unlock this course with a free trial

Join today to access over 25,300 courses taught by industry experts.

Defining agent scope

Defining agent scope

From the course: AI Coding Agents with GitHub Copilot and Cursor

Start my 1-month free trial Buy for my team

Defining agent scope

“

- [Instructor] When you work with any generative AI tool, context is key to quality. The more context you provide, the better the generation that comes out of the AI tool will be and the more aligned with your project it will be. And this is 10, 100, 1000 times true when you work with AI coding agents, you are working inside a project where you've made a bunch of decisions about the framework, about the code style, about the language. All of these things are important context for the AI to be able to match when it starts working with your code. And the more code you can provide as reference, the better the output will be. In both GitHub Copilot and Cursor, you can provide context, but your features are a little bit different between them, so let me show you both. In both of them, you can add files as context. If you click on the Attach button, you can attach the open editors, in the editor, you can attach the entire code base, a specific set of folders, and you can also pull out other…

Contents