Build Story · Planner · Experiment
Five-Year Planner: five years down to this week
A planner that turns a five-year vision into three priorities for this week.
In one look
The problem
A five-year vision is easy to write and easy to forget. Nothing links it to what you do on Monday.
What we built
Write the vision once. The app breaks it into year goals, up to three rocks a quarter and dated milestones. Each week a check-in of 15 minutes or less sets up to three if-then priorities, each linked back to the vision. An AI coach helps in setup and check-ins, and the plain forms always work.
Where it is now
An early experiment on a lovable.app address, with sign-in by email link or Google. The whole loop is built: setup, weekly check-in, a five-level calendar, a quarterly rethink and a private calendar feed. It is a prototype, not a launched product, and it was last changed on 12 October.
What this would have cost in 2024
About $10k and 4–6 weeks
2024 team: 2 people: a full-stack developer, and a designer part-time. Built here by one founder working with AI in 3 days.
| Piece | 2024 hours |
|---|---|
| Plan cascade, email and Google sign-in, 12-table database with per-user access, setup flow, weekly check-in, countdowns | ~105 |
| AI coach in setup and check-ins, with a form fallback | ~42 |
| Five-level calendar and private calendar feed | ~63 |
| Chase-then-rethink layer, quarterly rethink, database tests, bug fixes | ~63 |
| Total (PERT) | ~273 |
Method: PERT (O+4M+P)/6 per piece; low = O × $25, likely = PERT × $37.5, high = P × $50 (Accelerance 2024 Eastern-Europe band). These are estimates of what a team would have needed in 2024, not invoices.
How it was built
From first commit to current build in 3 days
- Vision, rocks and the weekly check-in
One brief produced email sign-in, a six-step setup, a plan tree from vision to year goals to quarter rocks to milestones, a This week page and a check-in. A fix pass the same morning made check-in and quarterly saves safe to retry.
- Coach, calendar, rethink, calendar feed
An AI coach joined setup and the check-in, with a switch back to plain forms. One calendar got five levels on real calendar quarters. Goals became hypotheses with a line on what would change your mind, and the quarterly rethink now starts from evidence. A read-only calendar link for Google or Apple closed the day.
7 edits on 10 October - Tested as fake users
The real save functions ran as two signed-in test users and one visitor inside a transaction that rolled back. Retries, caps and the rethink worked, and no user could see or change another's plan.
21/21 checks passed · 0 rows left behind - Google sign-in and bug fixes
Google sign-in was added next to the email link. Onboarding bugs were fixed, and what you type in setup now survives a reload.
Who did what
The founder decided
- Three rocks a quarter and three priorities a week, no more.
- Goals are hypotheses: each one says what would change its mind.
- No streaks and no daily ticks. Habits show up from repeated actions.
- The calendar link is read-only, so the app writes nothing into your own calendar.
AI built and checked
- The web app, built in Lovable from nine briefs, eight of them written with Claude.
- A research brief on 127 sources before any code, and the database test, both done in Claude chat.
- The in-app coach runs on a Claude model.
Stack
Want something like this for your team?
From one call to something live. The same method is in the Claude Operator Pack.
From the founder
You might also like
Shares TanStack Start · Lovable
Shares TanStack Start · Lovable
Shares TanStack Start · Lovable