Accessibility-First AI: Building Glucolily for the Eli Lilly Hackathon
A diabetes companion that listens, reads photos of plates, and never assumes the user can see the screen clearly.
Glucolily started as a 48-hour build and ended as an Eli Lilly Code for All semi-finalist. The brief I gave myself: design as if the primary user has low vision and shaky hands, then make the AI keep up.
Multi-modal input, by necessity
Text, audio, photo. A user logging lunch should be able to snap the plate, dictate the carbs, or type — whichever is easiest in the moment. The fine-tuned agent unifies all three into the same structured log.
Accessibility is a feature set, not a checkbox
Adaptive font sizing tied to system preferences
Contrast modes designed for diabetic retinopathy
One-tap doctor report generator
Emergency alerts that bypass the chat UI entirely
Designing for the edge of the user base usually makes the centre of it happier too.