For Indian clinics, 1–5 doctors
Your day book records what came in.
Not what should have.
A five-doctor OPD practice does not have a claims problem. It has four leaks that never produce a transaction — so nothing in a cash book shows them, and they persist for years.
48
₹62,400
31
₹1,84,000
31Advised follow-up, never booked₹18,600 potential
₹62kPatient balances over 30 dayscollectable
22%No-show rate, Tue evening slots6 slots
9Procedure in notes, not on bill₹7,200
4Duplicate patient recordsmerge
The four leaks
None of them produce a transaction.
That is why they survive.
A consultation is ₹600. The patient pays ₹500 and says they will bring the rest. In a paper system that intention survives about four hours. Most of this money is collectable — it is simply forgotten by both sides.
“Come back in two weeks.” The patient nods and leaves. Nothing records that a follow-up was intended, so there is nothing to chase. This is the largest of the four and the least visible.
Commonly 15–30%, higher for follow-ups. A slot that goes unused displaced a patient who would have attended. What matters is notice, not politeness — a cancellation 24 hours out is refillable.
A dressing or an injection during a consultation that was already being paid for. Trivial individually. Not across a year — and only visible if the clinical record and the bill are the same record.
The product
Twenty-seven modules and an assistant.
Named after what the work is called, not after where it sits in an org chart.
What you run it on
The whole practice, in one record.
Getting started
Live the same week.
Records migrated from spreadsheets or your current system, doctors and staff set up, prescriptions and billing running. A single-doctor practice can be live the same week.
Outstanding balances over 30 days. No-show rate by doctor and slot. Advised follow-ups against booked follow-ups — a number most clinics cannot produce at all.
The clinic tier runs the same platform as the hospital tiers. Adding beds or branches changes the plan, not the software.
Deployments
Clinics running this today
Anonymised by agreement — no names, no logos. What is shown is the mechanism that was put in place.
- Patient balance persists against the record
- Advised follow-ups tracked against booked ones
- Procedure recorded in notes reconciled to the bill
- Recall schedule generated from the record
- Reminders timed for notice, not politeness
- No-show rate reported by slot and doctor
- Indian clinical shorthand resolved offline
- Clinic-specific phrases learned after two uses
- Unspecified catch-all codes flagged
Built to standards, not to a demo
What a day book records, and what it misses
The day book
- Who came in
- What they paid
- Nothing about who did not come
- Nothing about who should have
What you also need
- Who cancelled and was never replaced
- Who was told to come back and did not
- Which slot has stood empty three weeks running
- Which patient has not been seen since March
What we will never do
Things we have promised not to do
- Take a cut of a consultation fee
- Charge per appointment
- Sell a position in the directory
- Host star ratings
- Move a free thing behind the paywall
How we are actually paid
- Hospitals, for revenue integrity
- Companies, for corporate health
- Labs and pharmacies, for their modules
- Implementation, because it is somebody’s week
- Nothing from a patient, ever
One room or two hundred beds.
What runs without being asked
Improved most weeksA cancellation is offered to the next person in order, with a window, until somebody takes it.
Raised when the prescription is written, chased twice, then it stops. It does not nag.
An abnormal value escalates after thirty minutes if nobody named has acknowledged it.
Twenty-four rules, scored before submission and sorted by exposure rather than raw risk.
Ctrl-K from any screen. These are database queries, so they work offline and cost nothing.
Ask in your own words. Bring your own Anthropic or OpenAI key, or run Ollama on your hardware and nothing leaves the building.
We are deliberate about which is which. Most of what runs here is rules, not a model — because a rule is auditable, works when the connection drops, and cannot invent a figure. We build and improve both every week, and we will always tell you which one answered you.
Prescriptions a patient can actually read
Four live, four in clinical review| Language | Status | |
|---|---|---|
| English | Live | Reviewed |
| Hindi — हिन्दी | Live | Reviewed |
| Marathi — मराठी | Live | Reviewed |
| Tamil — தமிழ் | Live | Reviewed |
| Bengali — বাংলা | In review | Awaiting a clinician |
| Telugu — తెలుగు | In review | Awaiting a clinician |
| Gujarati — ગુજરાતી | In review | Awaiting a clinician |
| Kannada — ಕನ್ನಡ | In review | Awaiting a clinician |
We do not machine-translate a dose. A model asked to render “one tablet twice daily after food” will usually be right, and usually is not a standard that applies to a dose instruction — a dropped negation reaches a patient with no clinician present to catch it. So every phrase is a fixed table, translated once, and it is not offered to a clinic until a doctor who speaks that language has read all twenty-three. Anything outside the table stays in English: a phrase somebody must ask about is far safer than a confident mistranslation they act on.
The booking page is free, permanently.
No cap, no commission, and it does not move behind the paywall later.