With advancements in AI’s vision and conversation capabilities, I wanted to build an interface embedded in a physical space to see how it converses and reacts to you. Instead of confining AI to digital interfaces, I explored how it could respond to objects, sounds, and human movements.

Coda combines object recognition, textual understanding, movement, audio, and speech to create an intuitive, multimodal interface that enhances how we interact with our environment. By recognizing objects and interpreting their context, Coda enables hands-free assistance, real-time guidance, and interactive feedback.