Web app for planning trips:
how I researched the market, designed the app, and got it live
Web app for planning trips:
how I researched the market, designed the app, and got it live
Web app for planning trips:
how I researched the market, designed the app, and got it live
Planner opens in a new tab.
No account needed
Opens in a new tab. No account needed
Underhype's homepage
Idea
The app helps you travel around Sweden and stay on budget.
You enter travel dates and see the trip plan: from getting out of the airport to heading home.
It shows prices for eve-ry-thing and filters out overhyped places made for tourists.
Competitors
AI
AI assistants — game changers, but only if you know exactly what to ask (people don't) — otherwise, they just give you the most generic tips.
Youtube + Instagram
It’s hard to find someone you can trust. Bloggers charge 20–30 € for a guide.
Google Maps
There are way too many options, even with a high rating filter — still hundreds of places.
Paper guides
Bad in almost every way, but becomes the best one when there's no internet (like on a plane or train).
Idea
The app helps you travel around Sweden and stay on budget.
You enter travel dates and see the trip plan: from getting out of the airport to heading home.
It shows prices for eve-ry-thing and filters out overhyped places made for tourists.
Competitors
AI
AI assistants — game changers, but only if you know exactly what to ask (people don't) — otherwise, they just give you the most generic tips.
Youtube + Instagram
It’s hard to find someone you can trust. Bloggers charge 20–30 € for a guide.
Google Maps
There are way too many options, even with a high rating filter — still hundreds of places.
Paper guides
Bad in almost every way, but becomes the best one when there's no internet (like on a plane or train).
Idea
The app helps you travel around Sweden and stay on budget.
You enter travel dates and see the trip plan: from getting out of the airport to heading home.
It shows prices for eve-ry-thing and filters out overhyped places made for tourists.
Competitors
AI
AI assistants — game changers, but only if you know exactly what to ask (people don't) — otherwise, they just give you the most generic tips.
Youtube + Instagram
It’s hard to find someone you can trust. Bloggers charge 20–30 € for a guide.
Google Maps
There are way too many options, even with a high rating filter — still hundreds of places.
Paper guides
Bad in almost every way, but becomes the best one when there's no internet (like on a plane or train).
Idea
The app helps you travel around Sweden and stay on budget.
You enter travel dates and see the trip plan: from getting out of the airport to heading home.
It shows prices for eve-ry-thing and filters out overhyped places made for tourists.
Competitors
AI
AI assistants — game changers, but only if you know exactly what to ask (people don't) — otherwise, they just give you the most generic tips.
Youtube + Instagram
It’s hard to find someone you can trust. Bloggers charge 20–30 € for a guide.
Google Maps
There are way too many options, even with a high rating filter — still hundreds of places.
Paper guides
Bad in almost every way, but becomes the best one when there's no internet (like on a plane or train).
Story in the center of the design
CONTEXT
Story in the center of the design
Story in the center of the design
The idea of Underhype — cut the noise and avoid mainstream. This idea rules everything in the product.
instead of being universal app
AI is involved only as a proofreader
instead of generic visuals
Users get lifetime access
can pay for being mentioned
instead of being universal app
AI is involved only as a proofreader
instead of generic visuals
Users get lifetime access
can pay for being mentioned
instead of being universal app
AI is involved only as a proofreader
instead of generic visuals
Users get lifetime access
can pay for being mentioned
Dynamic content
CONTEXT
Dynamic content
Dynamic content
Dynamic sidebar. On search results, it shrinks and gives more control options
Adaptation to mobile browser
CONTEXT
Adaptation to mobile browser
Adaptation to mobile browser
While laptops are great for planning, the phone is still the obvious king once you're on the trip.
Homepage for logged-out users
Airport transfer options
Map tab for logged-out users
Homepage for logged-out users
Airport transfer options
Map tab for logged-out users
Homepage for logged-out users
Airport transfer options
Map tab for logged-out users
Production cycle
with AI
01
CLAUDE DESIGN
03
CLAUDE CODE
04
LOCALHOST
05
PRE-PRODUCTION
06
PRODUCTION
02
FIGMA
Since I was the only human on the project, it was all about art direction, handovers, and documentation for agents.
CLAUDE DESIGN
Generated ideas and kept everything on a design system level, using only color tokens, components, etc.
FIGMA + CLAUDE CODE
I refined things in Figma, handed them back to Claude Design, then to Claude Code to build on localhost.
PRE-PRODUCTION ENVIRONMENT
Features behind the paywall got tested in pre-production. I also used it for usability tests.
Production cycle
with AI
01
CLAUDE DESIGN
03
CLAUDE CODE
04
LOCALHOST
05
PRE-PRODUCTION
06
PRODUCTION
02
FIGMA
Since I was the only human on the project, it was all about art direction, handovers, and documentation for agents.
CLAUDE DESIGN
Generated ideas and kept everything on a design system level, using only color tokens, components, etc.
FIGMA + CLAUDE CODE
I refined things in Figma, handed them back to Claude Design, then to Claude Code to build on localhost.
PRE-PRODUCTION ENVIRONMENT
Features behind the paywall got tested in pre-production. I also used it for usability tests.
01 CLAUDE DESIGN
02 FIGMA
03 CLAUDE CODE
04 LOCALHOST
05 PRE-PRODUCTION
06 PRODUCTION
Since I was the only human on the project, it was all about art direction, handovers, and documentation for agents.
CLAUDE DESIGN
Generated ideas and kept everything on a design system level, using only color tokens, components, etc.
FIGMA + CLAUDE CODE
I refined things in Figma, handed them back to Claude Design, then to Claude Code to build on localhost.
PRE-PRODUCTION ENVIRONMENT
Features behind the paywall got tested in pre-production. I also used it for usability tests.
Production cycle with AI
Production cycle
with AI
01
CLAUDE DESIGN
03
CLAUDE CODE
04
LOCALHOST
05
PRE-PRODUCTION
06
PRODUCTION
02
FIGMA
Since I was the only human on the project, it was all about art direction, handovers, and documentation for agents.
CLAUDE DESIGN
Generated ideas and kept everything on a design system level, using only color tokens, components, etc.
FIGMA + CLAUDE CODE
I refined things in Figma, handed them back to Claude Design, then to Claude Code to build on localhost.
PRE-PRODUCTION ENVIRONMENT
Features behind the paywall got tested in pre-production. I also used it for usability tests.
Documenting the logic
CONTEXT
Documenting the logic
Documenting the logic
To "vibe-code" something that actually works, you have to give the AI clear instructions. I used what I learned back at Yandex — an enterprise-level tech company — and documented every step from both the user's and system's perspectives. At the end of the day, it was a lot like a PM job: sending detailed specs to an engineering team.
Shipping on time
CONTEXT
Shipping on time
Shipping on time
I follow the Basecamp principle: Fix Time and Budget, Flex Scope. So instead of launching everything at once, I release features one by one to hit deadlines.
In the pre-MVP version of the app, I did not have the visuals. So the app works without them — but with Danish paintings.
Made to pay for itself
Made to pay for itself
Underhype is not a pet project. It's designed to be profitable. The app can generate around 612 € in profit per month. Here is a simplified financial plan for a pessimistic scenario.
MONTHLY COSTS
Claude
22 €
Vercel
20 €
Domain
1 €
Supabase
25 €
Marketing
100 €
Total
168 €
MARKET EXPECTATIONS — PER MONTH
International visitors in all cities
112,000
Swedish domestic travelers
700,000
Who find the app, 0.5%
3,248
Pay for the app, 10%
195
Revenue
1,755 €
Profit
1,587 €
TO BE PROFITABLE
Full access price
5.99 €
Paying users
min. 19
Free users
~ 190
MONTHLY COSTS
Claude
22 €
Vercel
20 €
Domain
1 €
Supabase
25 €
Marketing
100 €
Total
168 €
MARKET EXPECTATIONS — PER MONTH
International visitors in all cities
112,000
Swedish domestic travelers
700,000
Who find the app, 0.5%
3,248
Pay for the app, 10%
195
Revenue
1,755 €
Profit
1,587 €
TO BE PROFITABLE
Full access price
5.99 €
Paying users
min. 19
Free users
~ 190
MONTHLY COSTS
Claude
22 €
Vercel
20 €
Domain
1 €
Supabase
25 €
Marketing
100 €
Total
168 €
MARKET EXPECTATIONS — PER MONTH
International visitors in all cities
112,000
Swedish domestic travelers
700,000
Who find the app, 0.5%
3,248
Pay for the app, 10%
195
Revenue
1,755 €
Profit
1,587 €
TO BE PROFITABLE
Full access price
5.99 €
Paying users
min. 19
Free users
~ 190
What's next
What's next
Since I’m solo, I have a plan for a year to make sure I stay on track and keep shipping.
Q1
Q2
Q3
Q4
Research & validation
Q2
Building: Claude Design + Claude Code
Q3 – Q4
Release MVP — September
Q3
Building iOS version
Q4
Today
DROP ME A LINE
Hugo Löfquist
2022 — 2026
Legal name
Evgenii Lefkvist
Based in Berlin
Work worldwide
DROP ME A LINE
Hugo Löfquist
2022 — 2026
Legal name
Evgenii Lefkvist
Based in Berlin
Work worldwide
DROP ME A LINE
Hugo Löfquist
2022 — 2026
Legal name
Evgenii Lefkvist
Based in Berlin
Work worldwide