To make Aki truly useful on iOS, it needs the ability to recognize text within images and act on it—specifically by creating tasks from that text. I frequently receive notifications (e.g., from a doorbell camera app) that require follow-up actions, but I can't copy the text directly. If I could simply take a screenshot and have Aki extract the actionable content to create a task, it would streamline my workflow significantly. OCR (Optical Character Recognition) support for image-based input would solve this and make task creation much more intuitive on mobile.
