Anyone else finding AI design tools skip the actual product thinking?
I've been talking to dozens of PMs over the last few weeks who prototype with Lovable, Bolt, Figma Make, V0, etc. Same frustrations keep surfacing.
Output looks a bit generic: looks like a demo, not your actual product
Context loss: explain your product in ChatGPT/Claude, then re-explain in Lovable, then again somewhere else
No edge case thinking: AI executes prompts literally, doesn't challenge or expand on them
The core issue I keep seeing: these tools are interface builders. They're great when you already know exactly what to build. But the hard part, thinking through the flows, the states, the edge cases, where users will actually get stuck, that's still entirely on you.
Building something at Figr AI to tackle exactly this.
Curious: are PMs who prototype regularly hitting the same walls? Or is there a bigger pain point I'm missing entirely?
Replies
I’ve noticed the same pattern. @moksh_garg
Most of these tools are amazing at turning a clear spec into pixels fast. But they don’t really help you find the spec. They don’t question assumptions, model edge cases, or pressure-test the flow.
So you end up with something that looks polished but hasn’t been deeply thought through.
The context switching is also real. You explain the product three times across tools and still lose nuance.
I think the gap isn’t UI generation. It’s product reasoning. If you’re building around that layer, you’re probably closer to the real bottleneck than most design tools right now.
Figr AI
@alpertayfurr Exactly, really well put Alper :)
i'm trying to solve something similar at Figr AI which is much closer to product reasoning. The main bottleneck is to very deeply understand your existing product. That's why, Figr is built to understand whole context around your product and build a custom RAG for you. If you're facing a similar issue with other AI design tools, I think you can probably check out @Figr AI