Designing a
Conversation

SuperDial's AI places automated calls to insurance companies on behalf of healthcare providers. But first, customers need to tell the AI what to ask. This is the story of designing a Script Builder that turned the complexity of human conversation into something anyone could configure.

Suzanne Jackson, Wind and Water, 1975

Company SuperDial
Role Sole Designer & Engineer
Scope UX, Front-End Dev
Shipped Fall 2023
SuperDial Script Builder

The problem

To place an automated call, customers need to define what questions they want answered. The challenge: calls vary enormously in complexity, customers are non-technical ops teams who don't have time for involved setup, and whatever we built also needed to be legible to the AI that would actually conduct the call.

Three directions, one right answer

I explored three fundamentally different approaches before converging on a solution.

Decision model exploration

The first was a node-based decision model that powerful, capable of handling highly complex branching logic, and... immediately too much. Ops teams flagged it would require dedicated support to implement, and the complex decision trees would actually constrain the AI when calls deviated from script. Verdict? Over-engineered.


Answer checklist exploration

The second flipped the approach entirely: users would only select what information they wanted captured, and the system would generate the questions internally. Cleaner for engineering, better for AI consistency — but customers hated losing visibility into what was actually being asked. Verdict? Too opaque.


Final Script Builder design

The third direction split the difference. A form-based Script Builder (familiar to anyone who's used Google Forms) that let teams define what questions to ask while keeping the interaction model simple. Enough structure for consistent data capture, flexible enough for different operational styles, and interpretable enough for the AI.

Impact

$1.8M ARR Generated from Scripts in First Year of Launch
100% Product Adoption

Reflection

We implemented v1 of our Script Builder in Fall 2023 and have continued iterating since. The Script Builder evolves as we gain greater clarity on use cases - for example, we've found that many customers want similar scripts, so we've created template "base" scripts that get you 70% of the way there. Our core design didn't box us into a corner, which has allowed us to easily adapt to changes. The Script Builder isn't some ground-breaking feature, but it manages to suit the complex needs of our customers while being easy to understand, and I'm quite happy with that.

← Architecting for Different Users Next: New User Comprehension →