Prapatti AI Uses Google Gemini to Help Disabled Users Navigate Inaccessible Websites
A developer has built Prapatti AI, a desktop tool designed to restore digital independence for people with visual, motor, or cognitive disabilities. The tool was created in the spirit of International Day of Charity, addressing the fact that 95–98% of top websites still fail basic web accessibility standards. Prapatti AI uses Google Gemini's multimodal vision-language model to visually interpret desktop interfaces, allowing users to control navigation through adaptive hardware sensors such as eye-trackers or switch controls. The system operates on a local Sense-Reason-Act loop, where Gemini analyzes screenshots and returns precise coordinate commands that automate clicks, form-filling, and popup dismissal. By relying on visual inspection rather than DOM parsing, the tool works across inaccessible websites, legacy software, and apps that lack proper accessibility tags.
This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)
Log in to join the discussion and vote.
Log in