Participants in this arm will utilize the ambient AI scribe tools from Abridge. They will otherwise continue their usual clinical activities, including providing care with trainees (e.g., medical students, residents) and multiple family members in the room. The tool will be used exclusively in the outpatient clinical setting and only when the participant is present. The ambient AI scribe tool integrates into the electronic health record (EHR), and the EHR's mobile app is used to collect the recording on a mobile device. The ambient AI scribe tool is transcriptional and does not provide clinical decision support.

These participants were not provided with the ambient AI scribe application on their mobile device. They still had access to documentation with dictation or existing scribe services (non-AI).

Ambient artificial intelligence (AI) scribes are a clinical documentation tool that uses automated speech recognition and large-scale language models to capture and transcribe synchronous patient-provider encounters in real time. Clinicians then review, edit, and authorize the AI-generated text before finalizing the chart, ensuring necessary human oversight and medical accuracy. In this study, participants used Ambient AI scribes on mobile devices for the recordings.

The ambient AI scribe will be available for the provider to use in the outpatient setting. They were not required to use the Ambient AI scribe, but could choose whether to use it and with which patients. Consent to use the device was documented for all patient encounters.

Change in professional fulfillment and burnout, measured using the Professional Fulfillment Index (PFI), a validated 16-item self-report questionnaire. The instrument comprises three subscales: Professional Fulfillment (6 items), Work Exhaustion (4 items), and Interpersonal Disengagement (6 items). Items are rated on a 5-point Likert scale (0 = "Not at all true" / "Not at all" to 4 = "Completely true" / "Extremely"). Subscale scores are calculated as the mean of constituent items. Unit of measure: mean subscale score (range 0-4) and overall burnout score (mean of Work Exhaustion and Interpersonal Disengagement subscales, range 0-4).

Change in perceived workload, measured using the NASA Task Load Index (NASA-TLX), a validated multidimensional self-report questionnaire. The instrument comprises six subscales: Mental Demand, Physical Demand, Temporal Demand, Performance, Effort, and Frustration. Each subscale is rated on a 0-100 scale in 5-point increments. Unit of measure: subscale score (range 0-100) and overall workload score, calculated as the unweighted mean of the six subscales (range 0-100). Higher scores indicate greater perceived task workload associated with clinical documentation.

Percentage of clinical encounters in which the provider used the Abridge ambient AI scribe, measured using Abridge platform usage logs cross-referenced with electronic health record (EHR) encounter data. Unit of measure: utilization rate, calculated as (number of encounters in which Abridge was used divided by the total number of clinical encounters during the same period). This fraction is then represented as a percentage (range 0-100%) and aggregated monthly by provider.

Time spent by the provider in the electronic health record on clinical note documentation activities, measured using EHR audit log data (e.g., Epic Signal Provider Efficiency Profile). Unit of measure: minutes per scheduled clinic day on note documentation, normalized to clinical workload (clinical Full-Time Equivalent), and aggregated in 4-week windows per provider. No patient information will be collected for this outcome measure.