Multi-Surface
Experience System
6 coordinated surfaces · Real-time state · UE5 simulation · AI interaction
Client
Glydways
Role
Principal Design Technologist
Year
2025 — Present
Tools
Unreal Engine 5 · Figma · Swift · Arduino · Python · ElevenLabs
01
The Problem
Glydways is building a new category of autonomous transit — small, on-demand pods operating in dedicated guideways. No prior design patterns exist for how a rider should be onboarded, guided, and comforted through an experience that has no driver, no conductor, and no established behavioral script.
The brief had to be written before the work could begin. That meant defining what the experience even was — across physical space, digital surfaces, acoustic environment, and thermal comfort — before designing any of it.
“No established design patterns. The brief had to be written before the work could begin.”
02
System Architecture
Coordinating across six surfaces simultaneously — each with its own timing, fidelity, and failure mode.
Kiosk
Access point · Ticketing · Wayfinding
VMS
Variable message sign · Platform status
In-Cabin Display
Onboarding · Journey state · Egress
Lighting
Interior + exterior state signaling
Audio
AVAS · In-cabin AI interaction
UE5 Sim
Real-time validation environment
03
Hardware Prototyping
Lab prototype — kiosk & station mockup
UXSync — prototype coordination (localhost)
Physical prototyping was the only way to understand the experience. Coordinating Arduino, Linux, and iOS devices via real-time WebSocket messaging allowed full multi-modal state testing — lighting, audio, and display surfaces responding simultaneously to a single event trigger.
04
In-Cabin Intelligence
Designing an LLM-driven audio interaction system for a context where the rider may be anxious, disoriented, or non-verbal. The system needed to read journey state and respond appropriately — not just answer questions.
Multi-agent architecture with ElevenLabs TTS, tuned for acoustic comfort in a small enclosed space. Deliberation is audible — the system thinks out loud at a volume and cadence matched to the environment.
In-cabin display — journey state (Civic Center)
05
Outcomes
6
Coordinated surfaces
Kiosk · VMS · Display · Lighting · Audio · UE5 — all responding to a single state event
0→1
Zero prior patterns
No existing UX conventions for autonomous transit rider experience to reference or adapt
HW+SW
Fully integrated
Physical prototype delivery spanning Arduino, iOS, Linux, and cloud AI — not a simulation
Next project
Hyphen — Director of DesignFood automation