Physiotherapy clinic scheduling app with double-booking rules, no-show tracking, recall list, and utilization
clinic-scheduling · 3600 s per turn · source
The ask
We're Northshore Physiotherapy, six therapists, and we're moving our appointment book off paper. Our patient list, the therapist roster through September, and our appointments are attached; a few patients registered twice, and some different patients happen to share a name. Nobody should ever be double-booked, therapist or patient, and I want no-shows tracked with anyone who has missed two appointments flagged. Patients who aren't discharged, have been in before, and have nothing booked should land on a recall list so the front desk can call them. Therapists should only see their own schedule, our accountant needs to see everything without changing anything, and I want a dashboard with bookings, no-shows, the recall list, and each month's utilization (time in completed appointments as a share of rostered hours); send me an admin login and one for Lena Fischer.
Seed files the agent must import: patients.csv</code>, <code>roster.csv</code>, <code>appointments.csv. The agent must leave a RESULT.json with a reachable URL, an admin login, and the named restricted login.
Acceptance checklist
26 binary items. The first 14 are the enterprise baseline shared by every build task (delivery, invitations, roles, server-side authorization, scoped live dashboard, exact lists and exports, audit metadata, validation, persistence); the rest are application-specific. Core items, which together define "first usable": 1, 3, 5, 6, 8, 14, 15, 22.
| Tag | Items |
|---|---|
| Exact | 9 |
| Permission | 3 |
| Rule | 3 |
| Automation | 2 |
| Dashboard | 2 |
| Delivery | 2 |
| Sharing | 2 |
| API | 1 |
| Audit | 1 |
| Persistence | 1 |
The full checklist with per-item "how to check" instructions and expected figures is in checklist.md. Testers see it; the agent never does.
Change requests
Each change is a new one-shot turn on the carried-forward workspace. Only the owner's text below is sent; the tester items are withheld. After each change the full checklist is rerun, so regressions count.
Change 1 · 3 new checklist items
Show each therapist's utilization week by week on the dashboard, and give me a no-show report by patient for any month I pick.
Change 2 · 3 new checklist items
Appointment length should come from the type (initial assessment 60 minutes, follow-up 45, short follow-up 30), and nobody should be able to book a therapist outside their rostered hours.
Change 3 · 3 new checklist items
Add a front desk login that can book and move appointments for every therapist but never sees the clinical notes. And therapists should only be able to open patients who are on their own schedule.
No published score. Build runs need a human acceptance pass on a live URL, and no arm has completed one for the full set. Automated probes generate a tester sheet; they do not substitute for it. Results will be published as a separately labeled release when an arm completes.