[mjomaa]

Because AI is not there yet. Boilerplates are the better option until AI generation catches up. Here is what I do:

1. Explore an idea, research what competitors do, etc.

2. Use my own boilerplate for a greenfield project https://achromatic.dev (sorry for self-promo)

3. Write down what I actually want and paste the text and screenshot to v0 to see if it can generate something useful.

4. Improve/write the initial code by hand.

5. Paste the code into Claude and improve it more manually in an iterative fashion.

6. Make sure it is consistent with the rest of the codebase.

PS: I'm deep into developer tools now. Have forked the original drawIO/mxGraph, resolved all monkey patches, translated everything to TypeScript, added Multiplayer and more (~250k slocs) - ready as a base to explore some tools like one that solves your described problem. Here is a screenshot: https://i.imgur.com/opiu7z4.png I do envision Achromatic as a dev/design tool company.

[CatDivers]

+1 for v0. Good for creating starting base design. I then ask Claude to organise codebase, then take it to Cursor.

Should mention I'm non-technical and building a scrappy mvp this way. It could end up super scrappy...

[mjomaa]

It's good to not have an empty canvas. Like a writer and an empty page. But the output is not that good yet imo.

[CatDivers]

I think it depends what you ask for. Notion style webpages, fine. Yesterday I asked for gauge charts and it didn't perform well at all, I'll need to get better at prompting.