From the course: AI-Powered Development: GitHub Copilot in Visual Studio Code
Unlock this course with a free trial
Join today to access over 25,300 courses taught by industry experts.
Prompt engineering for the agent
From the course: AI-Powered Development: GitHub Copilot in Visual Studio Code
Prompt engineering for the agent
This chapter looks at another refactoring project using agent mode. We'll be working with this word frequency web page that you've already seen in a few earlier videos. Remember this is the one where you choose a file and then once you open the file you can click on analyze and it'll give you a word count. This project originally started as a .NET demo I built years ago. Before putting this course together I converted the .NET Windows application into this simple HTML page. That's another area where Copilot really excels, helping you move a project from one format or text stack to another quickly and with a lot less manual effort. The first task I want to perform is separation of concerns. I should have a separate CSS file and a separate JavaScript file. Let's talk about prompt engineering. Let's look at three possible refactoring prompts. In modern prompt engineering, the way you phrase a request matters just as much as the request itself. Different prompt styles naturally lead an AI…
Contents
-
-
-
-
-
-
-
-
-
-
(Locked)
Prompt engineering for the agent4m 11s
-
(Locked)
Start an agent-assisted refactor2m 55s
-
(Locked)
Add blocked words to the UI2m 17s
-
(Locked)
Add additional files2m 34s
-
(Locked)
Clean up invalid charactors57s
-
(Locked)
Modernize the UI layer3m 29s
-
(Locked)
Refactor review: Outcomes and impact1m 53s
-
(Locked)
-
-
-
-
-
-
-
-
-
-
-