The idea of Underhype — cut the noise and avoid mainstream. This idea rules everything in the product.
rare for modern interfaces
instead of a flashy one like .app
instead of hundred options
over AI suggestions
instead of being an everything app
Since I was working solo and had limited time, I built everything directly in V0 app, that works on Claude. I used v0 design system. It allowed to move fast and focus on adapting the components to my needs, rather than building from scratch. And only then I moved results from v0 to Figma — just because sometimes it's faster and cheaper to play with design in Figma rather than in v0 directly.
To "vibe-code" something that actually works, you have to give the AI crystal-clear instructions. I used what I learned back at Yandex — an enterprise-level tech company — and documented every step from both the user and system perspective. At the end of the day, it was a lot like a PM job: sending detailed specs to an engineering team.
I follow the Basecamp principle: Fix Time and Budget, Flex Scope — instead of launching everything at once, I release features one by one to hit deadlines.
EXAMPLE
In the first version, I cut extra graphics to focus on core features. I tested and launched features before my deadline.
Since I’m solo, I’ve sized every task to make sure I stay on track and keep shipping.