Skip to main content

Case study · A multi-site general practice · Voice AI

Two rings, then a voice agent picks up.

Result

+38%

growth in patient bookings over 90 days, reported as bookings recovered

Measured
Baseline
The prior quarter’s missed-call rate
Window
90 days
Checked by
The Practice Manager

Around 240 inbound calls a day, and roughly 60% answered inside two rings. A voice agent now picks up after the second ring and books the caller in.

On a clinic front desk, threads of soft violet light run along a faint violet grid between the desk phone, the appointment book and the filing trays, while staff talk over lunch and patients wait behind.

A business like yours?

Business
A multi-site general practice
Calls
Around 240 inbound a day
Systems
Practice management system, phones, SMS

Explainer · about 20 s · silent

Read the transcript
  1. A multi-site practice takes around 240 calls a day. Roughly 60% were answered inside two rings.
  2. After the second ring, a voice agent picks up and finds the caller’s record.
  3. It offers the next three times, books one, or hands the call back to a person.
  4. Bookings recovered rose 38% in 90 days, measured by the Practice Manager.

Before · Nine months tracked

Two hundred and forty calls a day they couldn’t answer in time.

When a GP network grows past five sites, the phones become the business. Front-desk staff were fielding around 240 inbound calls a day, and not every call was answered inside two rings.

The calls missed at the front desk dropped into voicemail or disconnected, and many of those were new patients trying to book a first appointment. The clinic group was paying to acquire those calls through Google Ads.

The Practice Manager had been quietly tracking it in a spreadsheet for nine months.

60%

of around 240 daily calls answered inside two rings, before the pilot

Measured
Baseline
All inbound calls at the front desk, around 240 a day
Window
Nine months before the pilot
Checked by
The Practice Manager

Build · 18 days

A voice agent that waits two rings, then books.

The fix was not a louder phone system. It was a voice agent that picks up only after two rings, the moment a person at the front desk would otherwise drop the call.

The agent identifies the caller, pulls their record from the practice management system, offers the next three available appointments, and hands the call back to a person if anything looks unusual. Nexus, Raava’s orchestrator, coordinates the voice agent, the booking workflow and the SMS confirmation after the call.

Built in 18 days as a pilot, then eight weeks of iteration with the Practice Manager.

A call comes in. The front desk has two rings to pick it up, as before.

  1. The front desk has two rings to pick it up, as before.

  2. It identifies the caller and pulls their record from the practice management system.

  3. The next three open appointments, read back to the caller.

  4. Anything unusual goes back to a person at the front desk.

  5. The confirmation goes out once the call ends.

Voice Twilio + VapiModel Anthropic ClaudeGlue n8nRecords Practice management system APICoordination Nexus, Raava’s orchestratorPrivacy Post-call transcript redaction

Tuning · 8 weekly reviews

Eight weeks of tuning, on one question: when to hand the call back.

The eight weeks after the build went on one question: when should the agent hand the call back to a person? Too eager to defer and the front desk gets flooded; too confident and the agent books the wrong slot for a complex patient. Most of the value came from a single threshold setting, revisited four times.

A 30-minute review with the Practice Manager every week, ten transcripts read together, and a small change shipped every Friday. Eight cycles in, the hand-off rate had settled, and the agent was handling the rest in full.

7%

settled hand-off rate: calls handed back to a person

Measured, incomplete
Window
Eight weekly review cycles
Checked by
The weekly review with the Practice Manager

Earlier weeks are not on the record.

Result · 90 days

What changed in 90 days.

Numbers verified by the Practice Manager. Anonymised under our standard case-study disclosure: vertical and outcome are real; name, location, and PMS-specific identifiers are not.

+38%

growth in patient bookings over 90 days, reported as bookings recovered

Measured
Baseline
The prior quarter’s missed-call rate
Window
90 days
Checked by
The Practice Manager

92%

of after-hours calls answered by the agent, without waking a duty receptionist or routing to voicemail

Measured, incomplete
Checked by
The Practice Manager

No time frame on the record.

$1.2M AUD

in patient lifetime value

Projection

The clinic group’s own 12-month projection, from its own lifetime-value model.

“Raava helped us recover capacity we didn’t know we had. The agent isn’t replacing anyone. It’s catching what we couldn’t catch on the busiest mornings.”

Practice Manager · Victorian healthcare network (anonymised at the client’s request)

Curious whether your clinic has the same gap?

A free 45-minute audit. We look at your call volume, your practice management system, and where time is leaking. You get a written follow-up within 48 hours, whether we’d be a fit or not.