Selected Work
Lead product designer building consequential systems across healthcare operations, enterprise workflows, and AI agents.
Experiments
Can a research report stay honest after it ships?
Where does an always-on agent actually spend its money?
Does giving an agent the design system beat pasting a screenshot?
Interface work
Everyday interactions across banking, investing, and patient booking.
Everyday banking, with control close at hand.
Understand what changed in your portfolio.
Change your visit without losing your place.
Each was the reasonable default. The work showed what it cost.
A continuous score left the lawyer setting a threshold with no basis for choosing one. The concept replaced it with draft / reviewed, where review stays an explicit human act.
See the review statesThe mapping surfaced two different jobs. About a third of sites had a patient-experience team whose mandate was rounding; the rest had service-line leaders fitting it around everything else they owned. One needed depth, the other speed.
See the operating modelsA request that had changed hands still read as one status, so nobody could tell a stalled approval from a reassignment. The record now carries lifecycle and custody as separate tracks, and its own event log shows the state holding while responsibility moved twice.
See the custody ledgerWorking notes
Underneath the buzzword sits a real design craft: shaping the boundary between what a system does on its own and what it checks with a person first.
Human oversight is a design choice that varies by context, and interfaces should let people understand, dismiss, or correct AI behavior.
Inside
What changes the answer
The design work is deciding where a feature sits on this line, and making that legible to the person on the other side.
Rescheduling an internal focus block is not the same design problem as changing a patient priority or approving access to financial data. The interaction may look similar. The authority is not.
The design work isn't making the agent capable. It's making the boundary visible.
Covers autonomy, approval, reversibility, escalation and auditability.
Most of the design work that matters happens before any pixel exists. The decks come later. The brief is the deliverable.
Established design frameworks put problem discovery and definition before solution development, so teams gather evidence about what to build first.
On patient rounding, the critical decision was not the eventual screen. It was recognizing that the proposed product boundary did not match how rounding actually happened on the floor. Once that changed, the interface problem changed with it.
The brief is the deliverable
Brief fragment
The earlier the ambiguity, the more expensive it is to carry forward.
A good brief doesn't remove the design work. It makes sure the team is solving the right problem.
Enterprise AI is won in the workflow around the model: who reviews what, where the system pauses, what it can access, and what happens when it gets one wrong.
Research finds that AI value varies with workflow redesign, task fit, and how assistance is embedded in real work.
The model is one dependency
Enterprise products also have permissions, policy, exceptions, queues, ownership, audit requirements, and existing systems of record. A better model does not make those disappear.
Model quality determines what is possible. Workflow design determines what is safe and useful enough to deploy.
Fig. 03 · Workflow anatomy
Swap the model and the product barely moves. Fix the workflow and it ships something people trust.
Around the action: EXCEPTIONS, RECOVERY. On the action: PERMISSIONS, APPROVAL. Under the action: PROVENANCE, AUDITABILITY.
Fig. 04 · Three layers of control
The model determines what the system can do. The workflow determines when it should.
