A digital nurse navigator that helps emergency room patients understand where they are, why they’re waiting, and what happens next, in plain language.
The emergency department is disorienting. You’re anxious, often in pain, and rarely sure what’s happening or how long it will take. The information that would settle you exists, it just never reaches you: your triage level, your position in the queue, who is actually responsible for your care, what the next step is and roughly when it happens.
Active Autonomy Companion is a digital nurse navigator that meets patients there. It explains where they are, why they’re waiting, what their triage level means, who’s on their care team and what comes next, all in plain language.
The thesis: an anticipatory, AI-driven system should make people feel more in control, not less. It never hides what it’s doing. It shows its work, sets honest expectations about wait times, and keeps patients oriented from check-in to discharge.
The patient experience under high cognitive load. The ER is a high-stress moment. People are anxious, in pain, and in no state to absorb complexity. I’m designing the screens that carry patients through a visit (the waiting view, journey timeline, care team and discharge summary) to keep them calm and oriented, and A/B testing layout and navigation variations to find the clearest version.
Safe handling of patient data. Every screen touches protected health information, so I’m also writing the spec for handling it safely under HIPAA. The principle: treat the model as untrusted, and enforce anything that matters legally or clinically in code rather than in a prompt.
AI that belongs in high-stakes spaces. The bigger question underneath it all: how do we design AI for environments like the ER so it’s genuinely safe and helpful, rather than one more thing to manage?
Lorem ipsum dolor sit amet, consectetur adipiscing elit. The first version went wide before it went deep, and I built the whole thing out before testing whether the premise held.
Sed do eiusmod tempor incididunt ut labore. It tested as more work than the thing it replaced, which is the one result a redesign cannot survive.
Ut enim ad minim veniam, quis nostrud exercitation. The version I kept held on to the intent and threw out the scaffolding around it.
In progress. The three threads above are what the final screens have to resolve, and this is where they will land as they come together.
The screen a patient looks at most, and the one that has to carry honest expectations about the wait without pretending to a precision the department doesn’t have.
Where you are, what already happened, and what comes next. Orientation is the whole product, and this is the surface that delivers it.
The handoff back to the patient’s own life, which is the moment the most instructions get given and the least gets retained.
The full case study, prototype and final deliverables will land here as it comes together.