I want an app that scans the phone’s camera roll, recognises the same person across different shots, and then lets me decide exactly which images to forward. The core flow is simple: • First, the app analyses every photo, clusters faces that it believes belong to the same individual and shows me those groupings. • From there, I can pick pictures one-by-one or bulk-select them in three distinct ways: individually, by date range, or by geolocation. This mirrors the way I already think about my library, so the interface needs to surface those three filters prominently and let me combine them if I wish. • Once I have a final selection, the app should open the standard share sheet so I can send the chosen files through any installed channel (Messages, WhatsApp, AirDrop, e-mail, etc.). Accuracy is key: false positives in face grouping must be minimal, and whenever the algorithm is unsure, it should simply place the photo in an “Unsorted” bucket so I can manually move it. I’m happy for you to use Apple’s Vision/Core ML, Google ML Kit, OpenCV or another proven face-clustering library—whatever offers reliable on-device processing and keeps users’ photos private. Deliverables 1. A fully functional mobile app (native or cross-platform) that runs on at least one major platform. 2. Automatic face clustering with an easy way to correct mistakes. 3. Filters that let me select photos individually, by date range, or by geolocation. 4. Share-out workflow that passes the selected images to the system share sheet. 5. Source code and setup instructions so I can compile and test on my own device. If you already have experience implementing face detection and efficient photo filtering, this should be a straightforward build. Let me know the tech stack you’d prefer and any similar work you’ve completed.