- Ambient scribes
Ambient AI scribes: what the evidence actually shows
A 22-page read of the published evidence on ambient AI scribes.
PDF · 22 pages · Updated 30 September 2026
- Who it is for
- Clinical leaders and medical groups deciding whether, and how, to pilot an ambient AI scribe.
- Format
- Length
- 22 pages
- Updated
- 30 September 2026
- Topic
- Ambient scribes
Three findings inside
2.58 million
patient encounters across 7,260 physicians in the largest published scribe deployment.
The Permanente Medical Group, NEJM Catalyst, 2025
9.5%
less time in notes for one scribe in a randomized trial; the other showed no significant change.
Lukac et al., NEJM AI, 2025
13 min
of EHR time saved per 8 scheduled patient hours across 8,581 clinicians in five health systems.
Rotenstein et al., JAMA, 2026
What is inside
- The burden the scribe is aimed at
- Scale is settled: the Kaiser Permanente deployment
- What the randomized and controlled evidence shows
- Time savings: the distribution, not the average
- Accuracy: how notes go wrong, and how systems catch it
- The vendor landscape: documented and marketed
- An honest return-on-investment frame
- What to measure in a pilot
Get it
A 22-page read of the published evidence on ambient AI scribes.
PDF · 22 pages. The download starts on this page and the file is also sent to your inbox.
Read the guides behind it
Questions
Is this clinical or regulatory advice?
No. It appraises published evidence and sources. Confirm anything that affects a patient or a purchase with your own governance team and counsel.
Do I have to join the briefing to download?
No. The download does not depend on the box. The box is only for the AIMOCS briefing, and nothing is sent until you confirm from the email we send you.
What do you do with my email address?
We use it to send you this file. The privacy notice says what else we do, and how to ask us to delete it.
Physicians and teams working on AI in healthcare
Meet them in the network.
Ambient AI scribes: what the evidence actually shows
Get it