ADGScribe.ai
Physicians spend more time documenting than caring
For every hour of patient care, physicians spend an average of two hours on documentation. That imbalance doesn't just create burnout, it erodes the quality of care itself. Manual note-taking during consultations reduces eye contact and patient trust, while post-visit documentation stretches into personal time.
Existing tools either required full manual transcription or generated notes so rough they needed heavy editing before meeting clinical standards. Neither respected how physicians actually work.
An AI scribe built for the flow of clinical work
ADGScribe.ai automatically transcribes patient encounters, generates structured notes, and surfaces the right patient context at the right time. My role focused on shaping the experience so it felt intuitive in motion. I worked across UX strategy, information architecture, and content design to make sure the system supported physicians without asking them to adapt to it.
Structuring the information architecture
One of my primary contributions was defining the navigational structure and content hierarchy. The challenge: surface enough context to be useful at a glance, without overwhelming a physician mid-workflow.
Recording a session became the homepage. The most urgent, active work should have zero navigation cost.
The structure follows how clinicians actually think and move through their day: active work first, everything else within reach. By aligning each section to a real task, the system reduces context-switching and keeps attention on the patient, where it matters most.
Clinical software written for clinicians, not administrators
Clinical software is often written for the teams who manage it, not the people who use it daily. Our content approach was the inverse: plain language, action-oriented, with system state surfaced proactively so physicians aren't caught off guard mid-session.
A workflow tool that disappears into the work
Although the product wasn't fully launched by the time I left, we completed and handed off a full design iteration to engineering, while continuing to iterate on future versions. More importantly, we were able to ground the work in real feedback from physicians, doctors, and medical billers, validating that the system made sense within actual clinical workflows, not just in theory.
Working on this project really shifted how I see an entirely different profession, not just what physicians do, but how their workflows are structured, how medical coding actually functions behind the scenes, and how much clarity matters in fast-paced clinical environments. It made me think a lot more intentionally about IA, especially in how CTAs are organized to make something complex feel immediately graspable and usable in the moment.
Something as "small" as a mislabeled section or buried action isn't just a usability issue, it can mean a delayed note, a missed detail, or a physician staying late to finish documentation that should've happened in the room.