Just-in-Time Prompting

A prompting technique for voice and video-capable AI models where the user pre-configures the AI with a role and task description, then uses a trigger phrase (such as "check now") to initiate an on-demand visual analysis of the current camera view. Developed as a workaround for the inability of current VVLMs to continuously monitor video streams, just-in-time prompting allows blind travelers to check for specific items of interest at appropriate moments during navigation, such as when approaching a building or bus stop.