---
title: 'UCLA Health: Randomized deployment of DAX and Nabla ambient AI scribes'
slug: ucla-ambient-scribe-rct
stable_id: 868ad97f92d5e208
company: UCLA Health
function_code: healthcare_screening
pattern_codes:
  - creator_to_judge
evidence_strength: verified
publication_tier: showcase
freshness: current
reviewed_at: '2026-08-23'
updated_at: '2026-08-22'
source_quality_summary: 1 peer reviewed; publication outcomes are verified.
caveat_summary: >-
  DAX did not significantly improve time versus control. Requires continuing physician
  vigilance; product performance was not uniform.
collections:
  - human-still-decides
  - regulated-autonomy
  - negative-results
bundle_version: 1.0.0
bundle_fingerprint: sha256:c23c6cc2b88153d008ea8fda928f632ce0011fc2d4c5036672a16e5d895bab93
canonical_url: https://brianletort.ai/transformations/ucla-ambient-scribe-rct
---

# UCLA Health: Randomized deployment of DAX and Nabla ambient AI scribes

Ambient tools can draft notes in practice, but vendor-specific efficiency and error results require comparison.

Function: Healthcare screening. Patterns: Creator to judge. Evidence: verified.

Freshness: current. Reviewed: 2026-08-23. Updated: 2026-08-22.


Source quality: 1 peer reviewed; publication outcomes are verified.

## Before

1. **Outpatient physician** — Conducts the visit and writes the note in the EHR. (control: Physician signature.)
2. **Physician** — Completes and reviews documentation. (control: Clinical accountability.)

## After

1. **Ambient AI scribe** — Records the conversation and generates a draft note. (control: Two-month randomized clinical deployment.)
2. **Physician** — Reviews, corrects, and signs the draft. (control: Physician vigilance for clinically significant inaccuracies.)

## Decision rights

Physicians decide whether any generated content enters the record.

## Exception path

Inaccurate output is corrected or discarded and documented manually; adverse events follow clinical safety reporting.

## Outcomes

- **Time writing each note** (verified): Control arm fell from 4:22 to 4:04 per note. → Nabla arm fell from 4:30 to 3:49; a 9.5% greater reduction than control.. DAX did not significantly improve time versus control.
- **Safety and accuracy** (verified): Usual physician-authored documentation. → One mild adverse event; clinically significant inaccuracies were reported occasionally for both products.. Requires continuing physician vigilance; product performance was not uniform.

## Executive lesson

Treat ambient scribes as distinct products with measurable differences, not as one uniform category.

## Anti-pattern

Scaling a category-wide claim when one tested product did not beat control.

## Questions for leaders

- Which product-specific metric matters?
- How are inaccuracies sampled?
- Do savings persist at scale?

## Sources

- [Ambient AI Scribes in Clinical Practice: A Randomized Trial](https://doi.org/10.1056/AIoa2501000) — NEJM AI, Massachusetts Medical Society