Healthcare · Care coordination · Caregiver web app · Governed AI
Day One Home
Home from surgery, the family becomes the only link between every doctor
The recovery plan leaves the hospital on paper. At home, the family patches it together across notes, phones and shared docs.
I’m designing Evantis, a web app where the patient keeps one plan and one history. Day One Home is its first feature: the weeks after a hospital stay. I interviewed 7 people: 4 caregivers and 3 care professionals. I also reviewed 77 health tech companies.
Of the 77 companies, none has more than 2 of the 9 features I’m designing. In Evantis, the patient decides who sees the plan: family members who become caregivers, or care professionals. Each person sees only what they’ve been given. The AI answers routine questions from the patient’s own records, declines what it isn’t allowed to answer, and hands anything clinical to a clinician. It acts only with approval, like a refill or a booking.
How I’ll know it works
Senior Product Designer · End-to-end · Self-initiated · Research done ·
The UX research is mine: the theming, the triangulation and the findings. So is every UX decision. I set the art direction in Figma, and I built the design system, working in Claude Design.
With participants’ consent, Google Meet transcribed the interviews and Claude Cowork anonymized them. I checked the anonymization and corrected it where needed. I built this page with Claude Code and wrote parts of it by hand.
From what families told me, to where the plan breaks, to the trade-offs I made
I changed direction twice: from another portal, to a standalone web app, to state funding. Each sprint is told in full below these cards.
Caregivers kept their own notes and logs, then waited for answers. So I chose a standalone web app over another portal.
I mapped everyone who touches the plan after discharge. Each needs a different part, and only the patient can let them in.
One hospital holds only its own records. The state holds them across providers. I checked feasibility with my engineering advisors. It can be built.
1 in 7
adult hospital stays lead to another admission within 30 days.
AHRQ HCUP, 2024 report ↗ (opens in a new tab)
Industry data, not from this study.
Framing the hypothesis
I started by assuming the recovery plan was there, just scattered across portals that don’t talk to each other
It came from close to home: family, friends, and once my own household, coming home from the hospital. So I reviewed 4 patient portals. None held a patient’s full history across every provider they see, from the hospital to the dentist to the MRI center.
Each portal worked differently. Some sent alerts by phone or email, others kept messages inside the portal. Then I looked wider, with a of 77 health tech companies. None of them did this across every provider.
Can families tell what comes next after leaving the hospital, and who’s responsible for it?
If families see the whole recovery plan in one place, they can tell what comes next and act on it.
I chose not to build another portal. I’d design one place where families see the whole plan and act on it.
Listening to families
After the hospital, families kept track of everything themselves
- A paper medication log, kept by the recliner.
- A notes app shared with siblings.
- A Google Doc of research, and a list of questions for the surgeon.
Each family used its own mix of paper, apps, portals and messages. None of it lived in one place.
Who I talked to: 4 family caregivers and 3 care professionals, all from my own network. The caregivers looked after a parent, a spouse or a child, and their experiences ran from 2021 to 2026.
Access to medical records split the group. Parents had their children’s records by default. For adults, it depended on the patient: one handed access over when leaving the hospital, another managed their own care. That’s what turned Sprint 2 toward access.
“You need to wait. You need to call many times. You’re waiting for that phone call back. Meanwhile, [they’re] in pain.
“I had the feeling I’m the only connection between [all of their doctors].
Mapping the handoffs
Many people touch the recovery plan,
and each needs a different part of it
I mapped who handles the plan after the hospital. Family and outside care professionals needed an adult patient’s permission to see it.
Families and care professionals walked me through each handoff: the surgeon, the nurse, the pharmacy, the family at home. To see the record, family needed the adult patient’s consent, or their login and password. A home care agency told me it has no access to hospital records at all.
Sharing became its own step, and the patient controls it.
Who else can share for the patient, how much each person sees, and for how long. Sprint 3 picks that up.
Service blueprint
Evantis gives the family one recovery plan. Behind it, the state, the providers and a nurse each play a part.
Task flows
Six flows for the weeks after the hospital: steps and decisions, not screens.
Nothing sensitive is typed. The member ID is on the card.
Answers come only from the patient’s records, the plan and a library vetted by healthcare organizations.
The notification never carries health details.
Only the patient grants access, or a legal proxy for an incapacitated patient.
No action from the user.
Making the trade-offs
I chose state funding over a quicker start with one hospital
Starting with one hospital would be faster, but a hospital only holds its own records. The state holds them across providers. I checked feasibility with my engineering advisors. It can be built.
- Ruled outBuilding inside the hospital’s record system
Every hospital would need its own connection, and it would still miss the dentist, the therapist and the pharmacy.
- LaterCare professionals editing the plan
They only view it in the first version. Editing from their own software comes later.
- Can’t solveWhat an app can’t reach
Some families have no one well enough to help and no way to pay. An app can’t change that.
Turning research into direction
I’m presenting the state-funded direction to a CEO and a CPO from my network
I walk them through the research, the hospital direction I ruled out, and why the state should fund it. Their answers to the first 2 questions below decide what I define in Sprint 5.
What remains unproven
Whether the state would fund it. If not, the direction changes.
Who answers when the AI hands a question to a nurse.
How a patient shares access: with whom, how much, and for how long.
Most hip and knee patients are covered by Medicare, the federal plan, not the state’s, so the first patient group needs rethinking.
Defining what gets built
I’ll decide what the first version does, and what it leaves out
If the CEO and CPO say go, three things get settled before any design work.
- 1Planned
Product scope
Recovery after a hospital stay: the recovery plan, the AI and sharing. The rest of Evantis comes later.
- 2
Success metrics
I’m setting the for task success, AI safety and AI quality, then testing against them.
- 3
Design system
I’ll extend the Evantis design system in code, so prototypes come together fast.
Prototyping toward a build decision
I’ll prototype and test until the evidence says build, iterate or stop
Once the first version is defined, each round tests a coded prototype with real users.
- 1Planned
Prototype fast
I’ll prototype in code on the Evantis design system, from rough to final.
- 2
Build together
I’ll check with my engineering advisors that each prototype can be built.
- 3
Test often
Each round: 4 caregivers, 2 patients, 3 care professionals and 2 nurses, starting with the AI’s answers and sharing.
- 4
Build decision
I’ll recommend build, iterate or stop to the CEO and CPO, based on the in Success Metrics.
What I learned
I was sure the answer was a better portal, then sure a hospital should fund it. Research proved me wrong both times, and showed me the family member running care isn’t always in the room. Some coordinate from another state.