Agentrolux

Cet exemple est en cours de mise à jour. Le texte ci-dessous est encore en anglais.

Example · Physiotherapy and therapy clinicsRebooking and adherence agent

The course of treatment that quietly stops

An agent that reminds the patient, rebooks the session, checks in between visits and flags a drop-off to the clinician — without ever advising on exercise, pain or progress.

Illustrative scenario — not a real client result

Course tracker · 16:20

Simulated example
  • 18 reminders sent

    16:21 · Next session, time, what to bring

    Answered
  • 4 sessions rebooked

    16:24 · Same clinician, inside the plan's window

    Answered
  • “The pain is worse this week”

    16:26 · Clinical · with the physiotherapist

    Person

No exercise or pain advice, ever

Rebooking and adherence agent · Physiotherapy and therapy clinics

  • Sourced facts
  • A clinician decides
  • Drop-offs are flagged
01 — A typical day

Three small failures that add up.

What physiotherapy and therapy clinics owners tell us goes wrong in an ordinary week.

One missed session becomes three

A patient misses week two. Nobody calls, and the plan that depends on weekly progression quietly stops.

See the attendance data

A booking line that cannot be reached

Patients who want to change an appointment cannot get through, so they simply do not come.

See the clinic study

A pain question in a reminder thread

“Should I keep doing the exercises?” is a clinical question, and a friendly answer from an assistant is a risk.

See the boundary
01 — A typical day · the evidence

What the numbers actually say.

Each figure opens its source, year, sample and limits. Click a badge to check it.

01
Source

PLOS ONE, missed appointments across US outpatient physiotherapy

2021

Method and sample are recorded in the source registry.

Read the source for its scope and limits.

Open the source

73%

of patients missed at least one appointment in a course of physiotherapy

Retrospective cohort of 444,995 patients across 697 US clinics, records from 2016–17. Share of patients, not of appointments.

PLOS ONE · 2021
02
Source

International Journal of Physiotherapy, no-shows at a private clinic

2021

Method and sample are recorded in the source registry.

Read the source for its scope and limits.

Open the source

20.6%

of appointments were no-shows or cancellations at one clinic

6,162 appointments at a Calgary clinic, 2017 records. Combined figure, not no-shows alone.

International Journal of Physiotherapy · 2021
03
Source

International Journal of Physiotherapy, no-shows at a private clinic

2021

Method and sample are recorded in the source registry.

Read the source for its scope and limits.

Open the source

C$114,506

estimated annual cost of those missed appointments

The same single-clinic study. An estimate for one clinic, not a sector figure.

International Journal of Physiotherapy · 2021
02 — What the helper does

From your records to a decision you own.

The agent works from the plan the clinician wrote: how many sessions, how far apart, and which one is next. It reminders the patient, rebooks within that window, and keeps the record current.

Between sessions it sends the check-in the clinic has approved — a short question about attendance, not about symptoms — and passes any answer that mentions pain, swelling or a change in condition straight to the clinician.

It never prescribes, progresses or adjusts an exercise, never says a symptom is normal, and never discharges a patient from a plan.

6 steps · 2 decisions you own

Text version of the flow
  1. 1. Read the plan — Sessions left, spacing.
  2. 2. Remind and rebook — Same clinician, same window.
  3. 3. Check in between — Attendance, not symptoms. Human checkpoint: Two misses reaches a person.
  4. 4. Flag the drop-off — Two missed, one message. Human checkpoint: A clinician owns the plan.
  5. 5. Route anything clinical — Pain, swelling, new symptoms.
  6. 6. Close the plan — Completed or discharged.
02 — What the helper does · a simulated example

One simulated example, step by step.

Use the buttons or the left and right arrow keys. Nothing here is a real customer.

Simulated example

North Quay Physio, five clinicians

SMS · 16:20

1 / 6

A five-clinician outpatient clinic. The agent manages reminders and rebooking for active plans. Every message is simulated; no real patient data is used.

  1. North Quay Physio's assistant. I can confirm or rebook your session and pass messages to your physiotherapist. I can't advise on exercises or symptoms. Reply HUMAN for a person.

03 — What you decide

The helper prepares. You decide.

The agent keeps the appointments. The clinician owns the treatment.

  • The plan is read-only

    Session count, interval and exercises come from the clinician's record; the agent cannot change any of them.

  • Symptoms stop the script

    Pain, swelling or a change in condition goes to the clinician with the plan, and the patient is told who will reply.

  • Drop-offs are clinical events

    Two consecutive misses flag the plan instead of generating another reminder.

  • You can pause it

    Pause for a clinician, a patient or the whole clinic; messages fall back to reception.

Without your approval · No exercise prescription, no progression, no reassurance about pain, and no discharge. Two missed sessions always reach a person.

04 — What changes when a safeguard is missing

Documented cases, not scare stories.

Three documented cases with their sources: a booking system that patients could not use, a falsified timesheet, and a fraud that relied on unchecked records.

2017

East London MSK service

Letters late, phone line busy, patients absent

A quality-improvement review found patients complaining that appointment letters arrived too late and that a busy reception line stopped them changing appointments. Baseline DNA was 23.76% for new referrals and 23.74% for follow-ups; after booking changes and SMS reminders, 13.46% and 13.26%.

What the helper would do differently

Rebooking is self-service and always reachable, and the reminder carries the change route in the same message. The clinic measures its own DNA rate before and after rather than assuming the effect.

23.8%

DNA rate for new referrals at baseline

2019

HCPC case study

Timesheets signed for hours not worked

A physiotherapist repeatedly claimed pay for hours not worked, submitted timesheets purporting to carry a colleague's signature, and claimed travel expenses improperly, including after leaving employment. The panel found misconduct and imposed a striking-off order.

What the helper would do differently

Session attendance and completion come from the clinic's own record, never from a self-report the agent collects. What the agent records is evidence, not an approval.

Struck off

misconduct found by the regulator

2026

US DOJ, physical-therapy fraud

Treatment recorded for therapists who were not there

A clinic office manager falsified medical records to say physical therapists who were not at the clinic had treated patients; Medicare paid the clinics more than $8 million over 2018–2020. A federal jury convicted her of health-care fraud and false statements.

What the helper would do differently

The agent cannot mark a session as delivered. Attendance is matched to the clinician's identity and the appointment record, and an anomaly is investigated rather than absorbed.

$8M

Medicare paid to the clinics in the scheme

04 — What changes · the evidence

The rest of the evidence.

Every figure resolves to a source with its sample and limits. No figure without one.

  • 73%

    of patients missed at least one physiotherapy appointment

    444,995 patients, 697 US clinics, 2016–17 records. Share of patients, not appointments.

    Source

    PLOS ONE, missed appointments across US outpatient physiotherapy

    2021

    Method and sample are recorded in the source registry.

    Read the source for its scope and limits.

    Open the source
  • 20.6%

    no-shows and cancellations at one outpatient clinic

    6,162 appointments, Calgary, 2017. Combined figure; single clinic.

    Source

    International Journal of Physiotherapy, no-shows at a private clinic

    2021

    Method and sample are recorded in the source registry.

    Read the source for its scope and limits.

    Open the source
  • C$114,506

    estimated annual cost of missed appointments at that clinic

    The study's own estimate for one clinic. Not a sector-wide cost.

    Source

    International Journal of Physiotherapy, no-shows at a private clinic

    2021

    Method and sample are recorded in the source registry.

    Read the source for its scope and limits.

    Open the source
04 — What changes · your week

The same week, two ways.

Drag the handle, or use the left and right arrow keys when it is focused.

Typical week, beforeTypical week, after
  • Mon

    Two patients miss their session; nobody calls them.

  • Tue

    A patient cannot reach reception to move an appointment, so does not attend.

  • Wed

    A pain question is answered by whoever picks up the phone.

  • Thu

    A plan stalls at session three and stays on the books.

  • Mon 16:21

    Reminders sent; changes handled in the same thread.

  • Tue

    Sessions rebooked inside the plan's window, with the same clinician.

  • Wed

    Pain reports reach the clinician the same day.

  • Thu

    Two consecutive misses flag the plan for clinical review.

Illustrative example · not a measured result

05 — Your version

Four questions about your own week.

Keep your answers. They are the brief for the first version we would build for you.

  1. How many sessions does the clinic run in a week, and how many are missed?

  2. How often should a check-in happen between visits?

  3. What counts as a drop-off that a clinician should hear about?

  4. Which questions must never be answered by an agent: exercise, pain, progress?

Next

Put your own figures into the calculator below. It runs in your browser, and nothing is sent or stored.

Put your week into the calculator

Bring the four answers to the free one-hour call. We will use them to sketch the first version, and you keep the written plan either way.

Talk about your business
05 — Your version · your numbers

Put your own week into it.

An estimate, not a promise. The model and its assumptions are printed below.

Your inputs

All clinicians.

count

Reminders, changes, call-backs.

min

Your own no-show and late-cancel rate.

%

What a missed session costs you.

per hour

Reception time.

per hour

Example defaults are typical for a small business. Replace them with yours. Nothing is stored, sent or shared.

Estimated result

Illustrative

Reception hours back each month

0–0

Time released at your rate
£0–£0
Reminders sent after hours
0–0%
Time to a rebooked session
Already immediate
How we calculated this

Routine work handled by the helper: 70% of the share you marked routine.

Time saved per item: 80% of the minutes you entered.

Monthly volume: weekly figures × 4.33; monthly figures used as entered.

Cost: hours saved × your staff cost per hour, in pounds as an illustration.

Reply time: routine items move within the hour while the helper runs. Complex work still waits for a person.

Questions

The things people ask next.

No. Exercises, progression, frequency and stopping are the clinician's decisions. The agent routes any such question with the plan attached.

Start here

Show us a month of missed sessions.

One hour with your attendance data and one treatment plan. We will show you where the course stalls, and what the agent would send — and never send.