Visual Studio Code

GitHub Copilot is an AI assistant that lives inside the code editor, and the code editor is just the app where you write and save your code.

If you've ever opened Visual Studio Code, you've already seen the window it plugs into.

Picture it less like a robot that replaces you and more like a very fast junior teammate who has read a huge amount of code and is happy to guess what you want next.

That teammate is genuinely useful.

So I can do anything I need to.

VS Code, Visual Studio, Develop AL, Develop PTEs, AppSource Apps.

run quad, run quad extension, you name it.

I've had no limitations.

So I got this document and I'm like, okay, the content is reconstructed from the recorded chats.

To obtain the exact wording, open the session using the link provided and read the original text directly.

So in the case of quad code VS Code extension, those are saved to disk, but you have to go back and do some archaeology to dig them up.

So I was like, huh.

And so you can start there.

And I've just kind of gone from like Cloud Chat to then Cloud Code to I use something called VS Code so I can now see all my file structure and everything and have a bunch of different windows open doing a bunch of different things.

And I'll have five or six junior devs essentially building stuff simultaneously for me.

And they'll be like, oh, I found that your main code branch moved.

do use Kiro and we see, as I mentioned, we see these results when they are using Kiro for Spectre-driven development.

In this, in sort of digging into it a little bit, it's built on VS Code.

It effectively has a built-in workflow for walking you through what it looks like to build something using Spectre-driven development.

And the thing that's really cool about it is, similar to plan mode that you may be familiar with in IDs, it helps you build the specification.

Yeah.

And so when we first actually built out this tool, originally it was just managed by myself within VS Code.

And then we started to go, how do we allow our sales team to just self-serve as well?

And did you, so when you say that, did you, you were running the tool and you were just kind of, you were testing this yourself or you were running the tool in VS Code and then how did that work in the early stages?

Yeah, so we basically built out the workflow.

So we had to build out the full Legentic workflow.

versions.

And so where are they creating these dashboards from? Is that directly from your marketing hub as well? Yeah.

The prompt you see me do in the episode is what I did.

I opened up Visual Studio Code, I created a home folder, and I told it to go get busy, and it did.

So I did not...

In fact, I'm watching it work, and then I see this thing pop up for Java.

Dave, have you tried installing the Claude command line interface and having Codex use it as a reviewer?

I have.

And I actually prefer doing most of my AI inside of coding or inside of Visual Studio Code for coding.

It's just the environment that I prefer to work in.

And compilable on top of Linux, whether that would be considered AI as well.

And I mean, I hate to tell these authors, but like even, you know, many text editors like, you know, NeoVim and VS Code and everything else have like autocompletes in it that are all AI driven.

And...

I mean, yeah, you could turn them all off and never use them, but productivity is probably a higher gain than typing out each individual letter.

mean, it is insane.

And, like, now if you use stuff like anti-gravity or if you, like, I was testing something for a blog site with anti-gravity, which is Google's, like, AI IDE, like, Visual Studio Code.

It's called an IDE.

And so, which I know you know, Mario.