Technological advancements in the recent years has seen an unparalleled rise. Today, technologies like big data, machine learning, robotics, deep learning, and many other AI enabled softwares have eased the ways to develop and implement many disease detecting and monitoring systems and applications. And one such disease is Diabetes. It is vital to develop efficient methods for the diabetes diagnosis and treatment due to the life-long and extensive harm that comes with diabetes. Systems that have been previously proposed suffer from networking and intelligence issues. The goal of this work is to develop a customised, intelligent, and cost-effective diabetes diagnosis solution using machine learning techniques including random forest, SVM, ANN, XgBoost, and AdaBoost. One of the main benefits of cloud-based diagnosis is that it enables real-time monitoring and analysis of a patient's health data, allowing medical personnel to spot patterns and trends that may not be obvious using conventional diagnostic techniques.