This is a loader animation I made for an internal tool of which I am the sole user.
It took millions of tokens and multiple minutes of iteration (it was two prompts).
Eye Tracking + Voice + AI
No matter if we touch, point, speak, look or simply think, the interface should handle it.
Here, gaze is used as direct input, but mainly as "micro-intent" signal that provides additional context to the system. SwiftUI + ARKit.