Hero image

Designing Around the Model

I joined NYU Langone's HiBRID Lab in June 2026. In the months since, I've worked across four projects that share nothing on the surface — a chatbot proposal for cardiology, a decision-support tool for statins, a behavioral-nudge system for primary care, a content pipeline for the lab itself.

What actually connected them wasn't the clinical subject matter. It was three questions nobody wanted to spend real design time on: what can this model do, what can it not do, and how long does it take to find out? Every interface decision I made traced back to one of those three — which is what this case study is actually about. It's still in motion; so is the thinking.

Role
UX Design
UX Research
Prototyping
Service Design
Tools
Figma
Claude API
Airtable
Netlify
Epic
Team
HiBRID Lab
SoDEC
MCIT
Nudge Unit
CPCVD
Timeline
June 2026 – Present
The Problem

Clinical AI gets graded on whether it's right. In practice, that was rarely what decided whether it actually worked. A correct recommendation that arrives after the patient has already left, or one hedged behind data nobody knew was missing, changes nothing.

8
phases of care where information could go missing
15 min
after a visit ends before the score is ready
5
behavioral themes explaining when a nudge changes behavior
The Challenge

How might we design clinical AI around what the model can't do, rather than around what it can?

My Role
  • Designed a statin decision-support tool alongside a physician lead and a second UX designer
  • Ran and coded usability sessions with prescribers, with a second observer for reliability
  • Built a journey-mapping tool coordinators use to flag exactly where information disappears
  • Built an automated content pipeline on the Anthropic API — intake form to review queue, no manual drafting
  • Turned research findings into placement and content decisions across four Epic surfaces
Chatbot Proposal
Before I designed anything, I needed proof a chatbot could do something the portal couldn't.

So instead of pitching a chatbot, I built a journey tool. Coordinators used it to mark exactly where information disappears across eight phases of care. The capability question got answered with evidence instead of enthusiasm — and the proposal is still waiting on what it found.

Finding
A capability question answered with evidence beats one answered with enthusiasm.
Content Pipeline
A bounded capability is a usable one. An open one is a demo.

The pipeline drafts captions and fill sheets for the lab from one intake form. It could have been an open text box. Instead it runs on eight fixed formats, each with its own layout and prompt — constrained enough to hand to a reviewer instead of a rewriter.

Model calls are slow enough that a synchronous "generate" button would've felt broken, so it runs on background functions with an approval queue instead. Nobody waits on the model.

8 formats, 1 reviewer
01
Publication
02
Event Recap
03
Guest Speaker
04
Podcast
05
Staff Spotlight
06
Project Spotlight
07
Milestone
08
Job Posting
Finding
The design work was deciding what the model should not be allowed to attempt.
Statin Decision-Support Tool
Marking what the system can't see is what makes clinicians trust what it can.

The tool automates risk stratification across a risk score, guideline enhancers, and imaging signals. What mattered most wasn't the recommendation — it was the negative space: which biomarkers were never measured, which imaging was never ordered. So it states its recommendation, attaches the guideline class, and weights Order and Decline equally. It never places the order itself.

Risk panel
0 gaps shown
4.1%
10-year risk · Borderline
Contributing factors
Elevated LDL-C, 138 mg/dL
Lipoprotein(a) — never measured
Reduced kidney function
hs-CRP — never measured
Hypertensive pregnancy history
Coronary artery calcium — not available
Higher-risk ancestry
Carotid plaque — not available
Consider starting a moderate-intensity statin
Shared decision-making · Class IIa
ConfidentShow what's missing
Finding
Confidence without visible gaps reads as a system hiding something.
Behavioral Nudge System
Latency isn't a performance problem. It decides who's in the room when the answer arrives.

In usability sessions, prescribers noticed nudges, agreed with them, and moved on anyway — past the moment it could matter. The gap between agreeing and acting was almost entirely timing. It got sharper in the data: a behavioral health score takes about fifteen minutes to finish computing after a visit ends. The patient's already gone. A number that could have been a conversation becomes a PDF instead.

Visit timeline
Visit starts
Visit ends
+15 min
+1 day
+2 weeks
PatientIn the room
ScoreNot computed
the gap
Finding
Fifteen minutes is the difference between a conversation and a PDF.
Where Things Stand

Three months in, most of this is still moving. The content pipeline is live — the lab is using it to draft real posts, not test data. The statin tool is in usability testing with prescribers, with a phased pilot planned for later this year. The cardiology chatbot is still a proposal, waiting on the capability question the journey tool was built to answer. The nudge research is feeding directly into how the behavioral health score gets redesigned next.

That's not a tidy ending. It's a status update from inside a project that isn't finished — which is the honest way to write about work you're still in the middle of.

Reflections
Constraint is the feature
Eight fixed formats beat an open text box. Bounding what the model could attempt is what made its output reviewable instead of rewritable. The most useful thing I did on this project was narrow the job, not expand it.
Say what the system can't see
Marking never-measured labs and unavailable imaging made the tool look less certain and more trustworthy at the same time. Clinicians can work with a stated gap. They can't work with a confident answer that's quietly incomplete.
Latency decides who's in the room
Fifteen minutes turned a conversation into a PDF. Timing shaped these experiences more than accuracy ever did, and it's the variable I have the least habit of treating as a design problem.
Correcting is faster than generating
The journey tool worked because it showed up with an opinion instead of a blank field. Stating my assumption and asking to be corrected got sharper answers than an open question ever did — the disagreements were the findings.
Related works
Related Works component slot — paste the existing Related Works code component here in Framer