Here's roughly how my conversation with GPT4 went

Me: I want to make an svg editor, give me some suggestions. I mainly want something with mobile support.

GPT4: gives me some options

I look over the options and choose fabricjs

Me: Start by loading an svg at a predefined url

GPT4: <code>

Me: Ok now implement a save feature, send the json to this url ...

GPT4: <code>

Me: The text is loaded as an image, I want the text to be editable

GPT4: <code>

Me: I'd like to add some google fonts to the text editor

GPT4: <code>

Me: The fonts aren't loading, I think we need to load the fonts first before initializing the canvas.

GPT4: <code>

Me: Ok add a undo/redo feature

GPT4: <code>

Me: Let's add some clickable buttons instead of hotkeys, here is the html..

GPT4: <code>

I probably could have done this myself, but frankly it would have taken me a long time to figure out the fabricjs api. It probably saved me at least a week making this thing.

here's the live app: https://tinyurl.com/2dhh58cn

and the code: https://tinyurl.com/2tu4xrtn

you can tell the GPT generated sections by the (overly) verbose comments