This project aims to replicate the Apple Watch double-tap feature using on-device machine learning with an Arduino Nano BLE Sense 33. The device leverages its built-in accelerometer, gyroscope, and an externally attached MAX30102 oximeter sensor 1 to detect gestures such as double-tap, clench, and rotate. The hardware is housed in a 3D-printed wearable enclosure, mimicking a smartwatch form factor. This system has the potential to improve accessibility, especially for individuals with disabilities or those needing single-handed operation. The final system achieves a gesture detection accuracy of 94%, with robust classification performance across five gesture classes (including idle and other).