AI Intake, Notes, and Billing Busywork Removal for a Physiotherapy Clinic

A physiotherapy clinic runs on hands-on hours: assessment, treatment, progress. Around every one of those hours sits a second, invisible shift. The front desk re-types paper intake forms into a desktop practice management system while the phone rings. Clinicians stay late writing SOAP notes from memory. Someone spends Friday afternoon keying claims into insurer portals, then re-keying the ones that bounce. And every new location the group opens adds another copy of the same busywork.

This is the transformation we would run for that group. It is presented as a concept, built on the same method we use in client engagements, so you can see exactly what the before, the after, and the path between them look like.

The busywork, quantified

Follow one new patient through the flow. She fills out a paper form on a clipboard in the waiting room: history, medications, injury, insurer, consent. The front desk re-types that form into the PMS, field by field, between phone calls. In the treatment room the physiotherapist asks her the same questions again, because the clipboard never made it that far, then spends ten minutes after the session writing the SOAP note from memory. At day’s end, someone reads that note, picks a billing code, and types the claim into the insurer’s portal by hand. One visit, one story: told twice, typed three times.

The clinic is not disorganized. It is faithful to how clinic software was designed: a person translates what the patient said into fields, one keystroke at a time. The clinical judgment, the treatment plan, the billing rules underneath are all still right. The waste lives entirely in the translation layer.

Before and after: the intake-to-billing flow

Drag the handle. The before is the recreated legacy intake screen; the after is the intelligent flow designed in its place.

The sentence the patient says in the waiting room becomes the start of the record. The old form does not disappear; it becomes the review surface, where the clinician confirms what the system drafted instead of typing it from scratch.

What we built

The concept above is not a mockup exercise. It is the output of the same engagement steps we run in client work:

• We map the intake-to-billing workflow first: it touches every patient at every location, and its time cost is easy to measure at the front desk.
• We design the data path as private by design: patient information stays in the clinic’s environment, the AI reads through the same permissions staff already have, and processing runs with zero data retention.
• We build the drafting layer as grounded: the structured intake, the SOAP note, and the claim line are drafted from the patient’s own words plus the clinic’s records and fee schedules, never from thin air, and every draft shows what it used.
• We design the approval gates before the automation: the clinician confirms the note, the biller confirms the claim, every field visible and editable, with an undo and an audit trail.
• We wire evals from day one: drafts are scored against real historical visits, and every correction a clinician makes becomes a test case.

How it works

The PMS stays the source of truth, which is what makes this safe for a clinic with real patients and real insurers. Before the visit, the patient describes the problem once, in their own words, on their phone or a clinic tablet. The system turns that into a structured intake, checks the policy details, and drafts the SOAP note the clinician refines in the treatment room. The confirmed note pre-fills the claim, and a person approves it before anything is sent. The AI never posts to the chart or to an insurer on its own.

Because patient information stays inside the clinic’s environment and processing runs with zero data retention, the design lines up with what PIPEDA expects of a private healthcare business: collect once, with consent, use it for the purpose the patient gave it, and let no copy wander.

Why this pays back

For a clinic group the return shows up three times. The front desk stops being a transcription service and gets back to the patients on the phone. Clinicians finish notes in the room instead of after hours, which is the difference between a sustainable caseload and a burned-out one. And claims go out the same day with fewer bounces, because each claim is drafted from the confirmed note instead of retyped from it. Time-and-motion research on clinical documentation shows the stakes: when desk work eats nearly two hours for every hour of care, removing the re-typing is not a convenience, it is capacity.