2026
Web app for planning trips
How I researched the market, designed the app, and got it live — all by myself
2026
Web app for planning trips
How I researched the market, designed the app, and got it live — all by myself
2026
Web app for planning trips
How I researched the market, designed the app, and got it live — all by myself
Planner opens in a new tab.
No account needed
Opens in a new tab. No account needed
Idea of the app
It's a very niche trip planner — for UK and US travellers in Sweden. Knowing travel dates and transport, it gives precise tips on what to see and buy. For 12 €, it unlocks better filters, the ability to save trips, and a trip budget planner.
Research
I did JTBD research. Here are two main "jobs" people can hire the app for.
JOB № 1 — SAVE TIME
When a traveller already on my way,
they want to see the whole shape of day one — what's happening, when, in what order,
so that they land already knowing the day.
JOB №2 — SAVE MONEY
When a traveller in expensive country,
they want to know upfront what stuff actually costs,
so that they are not worrying about overspending.
Methodology
I used Ivan Zamesin's version of JTBD framework
Competitors
AI
AI assistances — 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 for a guide 20–30 €.
Google Maps
There are way too many options, even with a high rating filter — still hundreds of places.
Paper guides
Bad almost in all ways, but becomes the best one when there no internet (like on plane or train).
Idea of the app
It's a very niche trip planner — for UK and US travellers in Sweden. Knowing travel dates and transport, it gives precise tips on what to see and buy. For 12 €, it unlocks better filters, the ability to save trips, and a trip budget planner.
Research
I did JTBD research. Here are two main "jobs" people can hire the app for.
JOB № 1 — SAVE TIME
When a traveller already on my way,
they want to see the whole shape of day one — what's happening, when, in what order,
so that they land already knowing the day.
JOB №2 — SAVE MONEY
When a traveller in expensive country,
they want to know upfront what stuff actually costs,
so that they are not worrying about overspending.
Methodology
I used Ivan Zamesin's version of JTBD framework
Competitors
AI
AI assistances — 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 for a guide 20–30 €.
Google Maps
There are way too many options, even with a high rating filter — still hundreds of places.
Paper guides
Bad almost in all ways, but becomes the best one when there no internet (like on plane or train).
Idea of the app
It's a very niche trip planner — for UK and US travellers in Sweden. Knowing travel dates and transport, it gives precise tips on what to see and buy. For 12 €, it unlocks better filters, the ability to save trips, and a trip budget planner.
Research
I did JTBD research. Here are two main "jobs" people can hire the app for.
JOB № 1 — SAVE TIME
When a traveller already on my way,
they want to see the whole shape of day one — what's happening, when, in what order,
so that they land already knowing the day.
JOB №2 — SAVE MONEY
When a traveller in expensive country,
they want to know upfront what stuff actually costs,
so that they are not worrying about overspending.
Methodology
I used Ivan Zamesin's version of JTBD framework
Competitors
AI
AI assistances — 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 for a guide 20–30 €.
Google Maps
There are way too many options, even with a high rating filter — still hundreds of places.
Paper guides
Bad almost in all ways, but becomes the best one when there no internet (like on plane or train).
Idea of the app
It's a very niche trip planner — for UK and US travellers in Sweden. Knowing travel dates and transport, it gives precise tips on what to see and buy. For 12 €, it unlocks better filters, the ability to save trips, and a trip budget planner.
Research
I did JTBD research. Here are two main "jobs" people can hire the app for.
JOB № 1 — SAVE TIME
When a traveller already on my way,
they want to see the whole shape of day one — what's happening, when, in what order,
so that they land already knowing the day.
JOB №2 — SAVE MONEY
When a traveller in expensive country,
they want to know upfront what stuff actually costs,
so that they are not worrying about overspending.
Methodology
I used Ivan Zamesin's version of JTBD framework
Competitors
AI
AI assistances — 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 for a guide 20–30 €.
Google Maps
There are way too many options, even with a high rating filter — still hundreds of places.
Paper guides
Bad almost in all ways, but becomes the best one when there no internet (like on 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 proof-reader
instead of generic visuals
Users get lifetime access
can pay for being mentioned
instead of being universal app
AI is involved only as a proof-reader
instead of generic visuals
Users get lifetime access
can pay for being mentioned
instead of being universal app
AI is involved only as a proof-reader
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 unlogged users
Airport transfer options
Places to visit
Homepage for unlogged users
Airport transfer options
Places to visit
Homepage for unlogged users
Airport transfer options
Places to visit
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 paywall got tested on pre-production. I also used it for usability tests, since it could be a shareable link.
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 paywall got tested on pre-production. I also used it for usability tests, since it could be a shareable link.
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 paywall got tested on pre-production. I also used it for usability tests, since it could be a shareable link.
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 paywall got tested on pre-production. I also used it for usability tests, since it could be a shareable link.
Documenting the logic of the app
CONTEXT
Documenting the logic of the app
Documenting the logic of the app
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 and system perspective. 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 — 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 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 € profit per month. Here is a simplified financial plan for pessimistic scenario.
MONTHLY COSTS
Claude
22 €
Vercel
20 €
Domain
1 €
Supabase
25 €
Marketing
100 €
Total
168 €
MARKET EXPECTATIONS — PER MONTH
Swedes are excluded:
paid features aren't relevant for locals
International visitors in all cities
112,000
Who find the app, 0.5%
560
Become free users, 60%
336
Pay for the app, 10%
34
Revenue
408 €
Profit
240 €
TO BE PROFITABLE
Full access price
12 €
Paying users
min. 14
Free users
~ 140
MONTHLY COSTS
Claude
22 €
Vercel
20 €
Domain
1 €
Supabase
25 €
Marketing
100 €
Total
168 €
MARKET EXPECTATIONS — PER MONTH
Swedes are excluded:
paid features aren't relevant for locals
International visitors in all cities
112,000
Who find the app, 0.5%
560
Become free users, 60%
336
Pay for the app, 10%
34
Revenue
408 €
Profit
240 €
TO BE PROFITABLE
Full access price
12 €
Paying users
min. 14
Free users
~ 140
MONTHLY COSTS
Claude
22 €
Vercel
20 €
Domain
1 €
Supabase
25 €
Marketing
100 €
Total
168 €
MARKET EXPECTATIONS — PER MONTH
Swedes are excluded:
paid features aren't relevant for locals
International visitors in all cities
112,000
Who find the app, 0.5%
560
Become free users, 60%
336
Pay for the app, 10%
34
Revenue
408 €
Profit
240 €
TO BE PROFITABLE
Full access price
12 €
Paying users
min. 14
Free users
~ 140
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
Q1
Building: Claude Design + Claude Code
Q1 – Q2
Release MVP on June 1
Q2
Testing paid features
Q3
Run paywall — taking 12 € one-time payment
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