The idea of Underhype — cut the noise and avoid mainstream. This idea rules everything in the product.
instead of being universal app
No AI suggestions
less typical for interfaces
Users pay for features only (saving, budgeting)
can pay for being mentioned
for the easiest and most secure UX
Dynamic sidebar. On search results, it shrinks and gives more control options
On homepage, when content does not require that much space, sidebar goes wider. It works as a place for marketing — either presenting the app to a guest or promoting Premium for users who already registered but did not pay yet.
Since I was working solo and had limited time, I built everything directly in Claude Design and Claude Code. It allowed to move fast and focus on adapting the components to my needs, rather than building from scratch.
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.
In pre-MVP version of the app I did not have final visuals. So the app works without it — but with Swedish paintings. Like this one with Thor
Since I’m solo, I have a plan for a year to make sure I stay on track and keep shipping.