“About 3 minutes”
Patients wanted to know what they were signing up for. So the intro leads with a time estimate, before the first question.
Problem
Nearly half of patients quit the chat
Previsit.ai’s intake chat runs before a doctor’s appointment. When patients dropped out, doctors started the visit without the basics.
My role
Solo product designer
Read 30 conversations and ran 6 patient interviews, then redesigned the flow, UI and copy. Also designed the dashboard doctors use to review answers.
Outcome
57% → 77%
Chat completion in the first 47 live conversations after launch. Doctors rated answer quality 4 of 5, up from 3.
The chat only works if people finish it. Nearly half of them didn’t.
Before & after
The insight
I assumed the chat asked too much. 30 conversations and 6 patient interviews said otherwise.
People stayed when they could see the end coming. Drop-off clustered at question 6 whether the questions were easy or hard. The finish line mattered more than the length.
Constraint
So the brief became: 6 questions from the doctor, plus AI follow-ups whenever an answer is too vague to use. That breaks the obvious progress indicator. You can’t show “3 of 8” when the total keeps changing.
Three fixes that only work together
Patients wanted to know what they were signing up for. So the intro leads with a time estimate, before the first question.
“3 of 8” breaks the moment the AI adds a follow-up. Now it’s 3 of 9 and the finish line just moved, and trust goes with it. The bar only moves forward, however many questions get asked.
“I smoke” is useless without the frequency. The AI asks until the answer is usable, and the bar keeps moving. The patient never sees the goalposts shift.
How the AI asks
Then there was the AI itself. I worked out how it behaves with our prompt engineer, by going through the conversations that had already happened.
Follow-ups fire on habits. Daily medication, smoking, alcohol: answers where a doctor needs the how much and the how often. There’s no hard cap. If an answer still isn’t usable, the AI asks again.
“I don’t know” is a fine answer. The AI suggests finding out before the visit and moves on, with no pressure.
No medical language. The AI talks the way these doctors’ patients talk. A lot of that call was intuition, built from reading how those patients actually wrote.
Decisions
Four calls, what each replaced, and what it cost.
Keeping the AI follow-ups
cost · Some chats got longer
instead of Cutting them to shorten the chat
A bar that only moves forward
cost · An exact question count
instead of A “3 of 8” count
One question per message
cost · More taps for the same answers
instead of Every question in one message
A time estimate set against the long case
cost · Short chats look longer than they are
instead of A shorter, optimistic estimate
The people who used to quit at the wall were reaching the end.
Before: one month of live conversations before the redesign. Each doctor rated at least 4 answers.
Mostly a story about restraint: taking things off the screen until the patient felt sure about what was left. If you’re building patient-facing AI and fighting drop-off, say hi.
More work