An end-to-end platform for dental practices.
Front desk, clinical charting, insurance and checkout, reporting and access on one standards-based record. Built by a small team directing AI coding agents inside governed foundations that keep the work consistent.
What it is
- Who it is for
- Independent and small-group dental practices that run the front desk, the operatory and billing as one operation rather than three systems.
- What it covers
- Scheduling and front-desk operations, clinical charting and treatment planning, coordination of benefits and checkout, reporting, and role-based access for the whole practice team.
- What it is built on
- A FHIR-based clinical record. The standard defines the data model, which means no page gets to reinterpret it.
- How it is built
- A small team directing AI coding agents, who work inside a design system and backend standards they consume but do not change. An independent QA reviewer who has worked with Michael for years tests the result.
Why the way it is built is worth reading about
Most writing about AI agents is about speed. The interesting part of Pixie is what had to hold still so that speed did not turn into drift.
Early pages were styled locally. Every agent made reasonable choices on its own, and the pages stopped looking like one product. The fix was not better prompting. It was deciding which foundations agents would consume rather than reinvent, and making those foundations good enough that nobody needed to.
Design system
- Defined in Figma
- Built as an atomic component library on shadcn
- Documented in Storybook
Agents import it rather than restyle locally.
Pages, flows and wiring
- Screens composed from library components
- Forms, tables and navigation
- Calls to the record through its standard interfaces
Picked up in phases from a backlog that lives in the repository.
Standards-based record
- FHIR resources and profiles
- Validation at the boundary
- One data model for every page
The standard decides the shape of the data. A page does not.
Case studies
Short, specific, and each one built around a single question a product or engineering leader would actually ask.
Need a leader who can
build with AI?
Let's talk about the product challenge, the team, and the outcomes you need—whether you're improving how your business runs or building something new.