Glass is an AI desktop assistant and screen-to-LLM interface that processes visual and auditory context from a computer to automate tasks. It functions as a tool for screen analysis, bridging real-time desktop captures with large language models to extract semantic meaning and data insights.
The system enables AI-assisted desktop interaction by recording live screen and audio data to provide a persistent digital memory for processing. This allows the application to analyze visible screen information and trigger automation workflows through global keyboard shortcuts.