WayFinder

Experimental assistive technology

Ask what is ahead.

WayFinder takes one photo when asked, describes visible objects, and speaks a cautious response. It is designed around audio, large controls, and fail-closed guidance.

A deliberate three-step loop

No continuous camera. Automatic start is opt-in.

01 / CAPTURE

Request one look

The app takes one photo when requested. If start-on-launch is enabled, opening navigation requests the first photo automatically.

02 / ANALYZE

Check the scene

The server asks a hosted vision model for structured scene facts, then applies deterministic safety rules.

03 / SPEAK

Hear the result

Hazards and STOP responses take priority. Old, raced, uncertain, or failed results are not presented as clear paths.

Current status

Private pilot preparation

WayFinder is not a validated mobility aid and is not available for unsupervised use. Real-device accessibility and supervised safety evaluation remain required before a public release.