Hi HN,

I'm a backend developer who recently started building full-stack apps, mostly using Next.js + shadcn-ui. Given how capable AI coding tools have become lately, I've been relying on them to help me bridge the gap in my frontend skills.

For the most part, this has been working great — especially when I can just compose existing shadcn-ui components. I describe the layout and functionality I want, and AI helps me glue things together.

However, I'm running into trouble when:

The components don’t look quite the way I want and need customization;

The component I need doesn’t exist in the library;

I need to fine-tune the CSS/styling;

In those cases, things get a lot harder. I'm not very fluent with CSS or frontend design systems, and sometimes AI-generated code doesn't fully match what I had in mind. Then I end up spending too much time debugging styles or trying to explain better what I want — often unsuccessfully.

So now I’m wondering:

Is this a signal that I need to invest more time into deeply learning frontend development (especially styling and layout)?

Or am I just not collaborating with AI in the right way — e.g., are my prompts poorly written, or am I missing some tools or techniques that make this process smoother?