intesol.kr
Cases / Education startup
MVP CASE 03

AI study assistant MVP — shipped in 6 weeks

One page of ideas became a product with 200 beta users in six weeks. That demo became the centrepiece of their seed round.

200
Beta users
68%
Daily active
22 min
Average session
Duration
6 weeks
Team
3 people
Started
2025 Q2
Market
Korea K-12
SITUATION

What was blocking them

ISSUE 01
Three hypotheses to test
Diagnostics, problem recommendation, or wrong-answer explanations — nobody knew which one drove retention. There was no budget to build all three.
ISSUE 02
The funding round was already booked
The first meeting was eight weeks out. Walking in without a demo was not an option.
ISSUE 03
Teacher review was the risk
An explanation that misses the curriculum loses trust instantly. Nothing could ship unreviewed.
APPROACH

The order we worked in

Each phase began from what the previous phase measured. We kept that order because without the earlier step there is no way to verify the next one's effect.

01
Cutting scope
Of the three hypotheses we kept only wrong-answer explanations, the one tied directly to retention, and dropped the rest out of the six-week scope. That decision created the schedule.
1 week
02
Building the core loop
Solve → detect error → generate a stepwise explanation, built on FastAPI and the Claude API. Every other screen was built to the bare minimum.
2 weeks
03
Teacher review tooling
We built the internal tool for teachers to approve or edit explanations alongside it. Edit history feeds back into generation quality.
2 weeks
04
Instrumented beta launch
We instrumented retention and session length, then opened the beta to 200 users. Week-three data became the investor deck.
1 week
RESULTS

Baseline at kickoff, measured after delivery

Metric
Before
After
Time to launch
Not started
→
6 weeks
Beta users
0
→
200
Daily active rate
—
→
68%
Average session
—
→
22 min

How each figure is measured is set out in the measurement notes on the cases page. Revenue and cost figures come from the client's own accounting and are published only within the scope they approved.

“They were the ones who told us to cut features first. That is why it shipped on time, and investors saw something that actually worked.”
Education startup · Co-founder · CPO
MVP Claude API FastAPI Instrumentation design Teacher review tooling
Free · 1 business day
This one started with a diagnostic too
The 6-Week MVP starts by measuring your baseline. Find out where you stand first — the diagnostic is free.