AI consulting Case studies Healthcare

Case study · Healthcare

Clinical notes and letters, written during the visit

An outpatient clinic with three offices

5½ ha week back for every clinician

Client profile

Practice
Outpatient clinic, three offices; many patients are auto-accident and personal-injury cases
Modeled for
A 10-clinician multidisciplinary clinic with two staff on records and correspondence
Before
Practice-management and records software, Word letter templates, dictation, fax and email
Privacy
Recordings, transcripts and notes stay on the office computer, encrypted

The challenge

What wasn’t working.

Clinicians finished their notes after the last patient, from memory. Every injury case brought a stream of documents: narrative reports, disability and work notes, letters to attorneys and insurers, referrals, each repeating findings already said in the room. Patient privacy ruled out sending recordings to a cloud service.

The audit

What we found.

We followed visits from the treatment room to the signed note and the last letter, and counted the documents each case produced.

  • Notes were written after hours, from memory.
  • A narrative report for an injury case took well over an hour to write.
  • Letters to attorneys, employers and other clinicians repeated the same exam findings each time.
  • Missing documentation (care-plan goals, outcome measures, claim details) surfaced only when a payer denied the claim.

Clinical time went on writing about care instead of giving it.

What we built

A scribe that listens with consent, drafts everything the visit needs, and shows its working, without the recording ever leaving the room’s computer.

  1. 01

    Listens, with consent

    The clinician reads a short consent script. Recording starts only once the patient agrees, and the transcript appears as they talk.

  2. 02

    Drafts the whole visit

    In a minute or two: the visit note, a plain-language summary for the patient, and the letters mentioned in the room, on the clinic’s letterhead.

  3. 03

    Shows where each line came from

    Hover any sentence to see what was said behind it. Edit anything, then sign.

  4. 04

    Safety and codes

    Red flags are shown with the line where they were said. Suggested codes are checked against the official code set and payer rules, and gaps a reviewer would find are listed before signing.

  5. 05

    Private by design

    It runs on the office computer, encrypted, with no cloud account. The recording is deleted when the visit is signed, and a log records who did what.

What stays with a personThe clinician is always the author: every note and letter is checked and signed by them before it leaves.

Results

What it returns.

  • 1–2 min

    from the end of the visit to ready drafts

  • 5½ h

    a week back for every clinician †

  • 8

    kinds of document drafted from one visit

  • 0

    recordings sent off the office computer

  • ≈2

    full-time roles of records and correspondence †

† An estimate, modeled from the client’s own volumes and roles.

The value

$235,000–$285,000 a year

Clinician time at a blended $90 an hour, administrative staff at $28, with benefits. Extra visits from the time clinicians get back are not counted.

Value driverAmountHow it is worked out
Visit notes $108,000 10 clinicians × 2½ hours a week × 48 weeks = 1,200 hours × $90
Records and correspondence staff $101,000 2 full-time roles, 3,600 hours × $28
Narrative reports $54,000 10 × 1 a week × 75 minutes saved = 600 hours × $90
Letters $52,000 10 × 6 a week × 12 minutes saved = 576 hours × $90
Claim documentation $22,000 10 × 30 minutes a week = 240 hours × $90
Realized in year one $235,000–$285,000 $336,000 discounted to 70–85%

Value is staff time the work no longer takes, priced at a fully loaded hourly cost and discounted to 70 to 85 percent for partial realization. Revenue gains are left out. We show the arithmetic so you can test it with your own figures.

See how it looks to the team.

A two-minute demo you can click through: one piece of the work, by hand and then with the build. Made-up people, real work.

View the demo

More case studies.

Your workflow could be the next one.

A 30-minute discovery call. You leave knowing whether a build would pay for itself.