Clinicians back with patients, not keyboards
We set up ambient AI that drafts the note from the appointment, with consent, for the clinician to check and sign.
Our plan for a clinic group with 20 clinicians
- from kickoff to first value
- 6–8 weeks
- estimated payback*
- Month 3
- of clinician time a year, estimated*
- $140k
* Estimates from the illustrative maths in chapter 07; we confirm your real figures in a discovery call.
- Industry
- Healthcare
- Solution
- Ambient documentation
- What we build
- Speech and clinical language
- People in control
- Every decision
- First value
- 6–8 weeks
- Payback
- Month 3*
The problem
Hours of notes after every clinic
Every appointment ends with typing: history, findings, plan. Clinicians write notes at night, look at the screen instead of the patient, and burn out. Hiring more people doesn’t remove the work.
- Notes finished after hours
- Clinicians face the screen, not the patient
- Long waits between appointments
- Burnout and turnover

Why we know it works
The approach is proven at scale
We build on methods that have already worked for large companies, and size them for a growing business. The evidence we draw on, as reported by Kaiser Permanente:
The Permanente Medical Group rolled out ambient AI scribes to its physicians. In a study published in NEJM Catalyst, the tool was used more than 2.5 million times in its first year and saved an estimated 16,000 hours of documentation over 15 months. 88% of surveyed physicians reported a positive effect on their visits.
- of documentation saved in 15 months
- 0k h
- uses in the first year
- 0.0M
- of physicians reported a positive impact
- 0%
Physicians review every note: the AI sometimes recorded things that didn’t happen, and it worked only for appointments held entirely in English.
See it work
From conversation to note
An illustrative appointment with our scribe. The conversation is transcribed as it happens, and a structured draft note is ready for the clinician to check and sign.
Appointment · recording with consent
Draft note
Awaiting clinician review- Subjective
- Objective
- Assessment
- Plan
How we solve it
Your data, an AI that understands it, and people in control
The same idea, sized for a growing business: we connect to what you already have, put the AI in the middle, and keep a person in charge of every decision that matters.
- 01
Your data
- Appointment audio, with consent
- Patient record context
- Note templates
- 02
Speech and clinical language
Speech-to-text, then a language model that writes a structured note in your format.
- 03
Your workflow
A draft note appears in the patient record minutes after the appointment.
- 04
Your people
The clinician checks, edits and signs every note. Nothing is filed without them.
How we build it
First value in 6–8 weeks
One problem, a fixed scope and a clear plan. You see it working on your own data before it goes live.
DiscoverWeeks 1–2
We shadow clinics, agree consent wording and choose the note templates with you.
Set up safelyWeeks 2–4
We set up secure recording, data protection and access controls first.
PilotWeeks 4–6
We pilot with a few clinicians, review every note and measure accuracy section by section.
Go liveWeek 7
We roll out clinic by clinic, with training and support.
ImproveWeeks 8–10
We tune templates to each specialty and review accuracy monthly.
Safety and consent
Built for clinical care
Clinical AI can get things wrong, so we design every step to keep the clinician in control.
Consent first
Patients are asked before recording, and can say no without any change to their care.
Nothing filed unsigned
Every note is a draft until the clinician reviews, edits and signs it.
Private by design
Recordings are processed securely and deleted once the note is signed.
Where the savings come from
The maths, line by line
An illustrative example with stated assumptions, so you can put in your own numbers. We confirm the real figures together in a discovery call.
$140k
of clinician time a year, back with patients
A clinic group with 20 clinicians
Illustrative · assumptions- Documentation saved per clinician a day (assumption)
- 20 min
- Clinic days a month
- 22
- Hours back a month
- 147 h
- Value of a clinician hour
- $80
The J-curve
A small dip, then compounding growth
Research on new technologies finds the same pattern: value dips while you invest in data, process and training, then climbs well past where you started. We keep the dip small by starting with one problem and paying back fast.
* Shape after Brynjolfsson, Rock & Syverson (2021); the payback month is illustrative.
What comes next
Where this is heading
- 01
From note to follow-up
The same conversation drafts referrals, coding and the patient’s own summary.
- 02
Every language
Appointments in the patient’s language, notes in the clinic’s.
- 03
Safer by design
Models that flag what they’re unsure of, so review is faster and safer.
Facing the same problem?
A free consultation maps where this would pay back fastest in your business.
Sources

Next case study · Manufacturing
Machines that warn you before they break
Let's build what's next for your business.
Tell us what's slowing you down. We'll show you where AI, automation, software and data will make the biggest difference, and what to do first.
- Free consultation
- Your workflows reviewed by a specialist
- Clear next steps, no commitment
Working across time zones · Live
- ----San Francisco
- ----New York
- ----London
- ----Dubai
- ----Sydney