AI Voice Agent
Clinics were missing patient calls while the front desk juggled in-person care. I designed a healthcare AI voice agent that answers every call, books appointments straight into the EHR, and gives operations teams full real-time visibility.
Overview
Never miss a patient call — even when the front desk is full.
It answers inbound patient calls, handles booking, rescheduling and cancellations, and writes the outcome directly into the practice's EHR — so front-desk staff can focus on in-person care. I designed the operations product: the dashboards, monitoring, and configuration that let a team run the agent across dozens of clinics with confidence.
The hard part
Handing patient calls to an AI is a trust problem, especially in healthcare. Operations teams need confidence that the agent captures intent correctly, books the right slot, and escalates when it should. The design challenge was making an invisible, autonomous AI conversation fully observable — every intent, booking, handoff and EHR write legible, auditable, and controllable from one dashboard.
Research & insights
What the research told me
The agent detects why a patient is calling — book, reschedule, cancel — and routes each call automatically.
When intent is unclear or a caller is upset, the AI hands off to a human — those moments had to be impossible to miss.
Value only lands when a booking writes straight into the practice's EHR, so the AI-to-EHR flow had to be foolproof.
How I worked
Learn the operations job
I interviewed operations teams to understand how they would supervise an AI taking real patient calls.
Map the AI call lifecycle
I blueprinted every automated step — answer, intent detection, booking, escalation, EHR write — to define what teams must see.
Design for observability
I surfaced real-time monitoring, per-call transcripts, and an audit trail so no agent action is ever a black box.
Make onboarding safe
I designed a guided practice registration and configuration flow so each clinic goes live without misfires.
Wireframes & iterations
From rough to right
I iterated on the monitoring and configuration layouts — how to surface live call outcomes, handoffs, and usage without overwhelming an operations lead. A dedicated design system kept every screen consistent across a large, data-heavy platform.
Final UI
The shipped workspace
Guided onboarding, real-time monitoring, usage analytics and a full audit trail in one consistent, data-dense product.
Outcome
The shipped design
The platform pairs an autonomous AI voice agent with the operational controls to trust it. The agent answers calls, understands intent, books and syncs to the EHR on its own; the workspace makes all of that automation visible.
