I design the human control layer of agentic AI in clinical software.
Nine years designing for clinicians and researchers at Mayo Clinic, Verana Health and Modernizing Medicine. Trained in human factors. I prototype in code so leadership sees the idea run first. See what I shipped.
Open to new opportunities · Remote, US Eastern timeGood agents know which calls aren’t theirs to make.
This agent read a study protocol and drafted an answer. It identified a call that is yours to make.
Work where people stay in charge
Let the agents do the work. Keep people in charge.
I ran the research, proposed how AI agents fit into study startup, and designed how coordinators direct and check their work. Leadership approved the direction, and it’s now in build from my prototype.
- Direction approved by leadership
- In build from my prototype
- 4.8/5 concept score for the study overview, the top-rated among 11 specialists
- Requirements written from my prototype
Getting decades of research data back within reach
I built a working prototype of the MVP. Leadership approved the build after seeing it run, and development is underway from my prototype.
- Build approved after the prototype demo
- In development from my prototype
- Conflict flow cut from four options to one question
- Held the line: nothing reaches the catalog without validation
A Medicare quality platform clinicians would recommend
Reporting software that made a dense compliance workflow clear and trustworthy. Each rule sits next to the decision it affects, so clinicians stay in control of their own score.
- NPS of 90 from about 200 users surveyed after launch
- Used by nearly 3,000 clinicians across two specialty registries
- Shipped on time for a Medicare deadline
A crowded drug market, readable at a glance
A 0-to-1 analytics product that shows pharmaceutical brand teams how retina drugs are being used, and how that is changing, month over month. Every number carries its comparison, so the people reading it make the call.
- A product sold at $1M+ per customer each year
- 2.7M+ patients and 7,300+ clinicians in the data
- Designed 0 to 1, through alpha and beta
Chart and motion studies
The data visualizations from my dashboards, pulled out and animated on their own.
Control That Means Something
A framework for human oversight of AI that acts on its own.
- BoundaryWhere the AI must stop and a person must act.
- ControlWhat a person can do about it: confirm, edit, pause, override.
- LegibilityMaking the AI’s reasoning something a person can check.
The tools behind the work
What I use to design, prototype, build, and ship.
Trained in human factors. Working in design and code.
I design the moment an AI hands a decision back to a person: what it shows, what it asks, and what happens when the person disagrees. Trained in human factors, I work from how people actually make decisions under pressure, not how we hope they will.
Two habits shape how I work. I build accessibility into the prototype from the first version, not as a later audit. And I stay close through the build, keeping designs and code in step so what ships is what was tested.
MS, Human Factors in Information Design, Bentley University. BS, Operations and Decision Technologies, Kelley School of Business, Indiana University. Working remotely on US Eastern time.
