From the course: GitHub Copilot Cert Prep by Microsoft Press

Unlock this course with a free trial

Join today to access over 25,500 courses taught by industry experts.

Learn how GitHub Copilot gathers context and builds a prompt

Learn how GitHub Copilot gathers context and builds a prompt - Github Copilot Tutorial

From the course: GitHub Copilot Cert Prep by Microsoft Press

Start my 1-month free trial Buy for my team

Learn how GitHub Copilot gathers context and builds a prompt

“

- [Instructor] Well, optimized AI assistance takes place in three ways. The multi-source input. For example, in VS Code, we have the open editor tabs as context. You have where the cursor is in the current file. If you're using that workspace, then you've got the workspace context. The idea with multimodal AI is that it's looking for context in many different ways. And we've also seen that depending on your IDE, and where your chat extension is in its development lifecycle, you have various ways for instance, using the pound sign in VS Code to make various pre-selection. It's very interesting. I also want to get on my horse here, and keep talking about relevance and priority. Now, Copilot is constantly evaluating, and reevaluating what you're telling it, what you're adding into context, what you're taking out of context. So you play a part in this, and you're trying to help the AI to think better, if that makes sense. And then lastly, the notion of user intent, right. Well, literally…

Contents