Reimagining clinical documentation for WebPT’s Gen 3 EMR.
WebPT wanted clinicians talking to patients, not typing. I owned the clinical workstream inside a five-workstream transformation and proposed the AI-scribe direction from observed clinical behavior.
.jpg)
The product and operating context
WebPT was replacing its old system with a Gen3 clinical platform. Documentation remained mandatory, and SOAP-note accuracy was non-negotiable.
The problem behind the request
Clinicians spent two to four hours a day documenting care. The fields could not disappear, but the workload around capturing them had to.
Design the system to listen - not wait to be told.
I proposed a live scribe that captures the visit and drafts a structured SOAP note while the therapist stays focused on the patient. A working prototype changed stakeholder skepticism into product direction.
From decision to shipped system
- Observed the clinical workflow and reframed the brief from organizing documentation to reducing it.
- Built and compared multiple concepts, including AI-only, manual fallback, single-patient, and multi-patient directions.
- Worked with clinical SMEs to define the required data behind first and repeat visits.
- Resolved dependencies with patient, front-office, and back-office workstreams and used the client’s design system as the shared standard.
The work, in context
Selected full-product views establish the system. Focused frames show the decisions and interactions that made the direction real.
.jpg)







What changed
The split-screen AI-assistance and structured-note pattern shipped and became the model other workstream pods used. Therapists responded positively before the client completed its own validation round.
Sensing what users need and getting a client ready to validate and sign off are different jobs. Complex consulting work requires both.