Plant diseases is a significant threat to agriculture, leading to reduced crop yields and economic losses. Prior detection of plant diseases is important for effective management and mitigation. This research mainly focus on machine learning-based approach to detect a disease in plants using Convolutional Neural Networks (CNN). We train a model on a comprehensive dataset of plant images, encompassing various species and disease conditions, to accurately classify and diagnose diseases. The trained CNN model is then integrated into a user-friendly mobile application, enabling real-time analysis of agriculture for farmers. The app allows users to upload various images of plants, then it is analyzed by the model to detect the presence and type of disease. Additional features include disease management tips, severity indicators, and treatment suggestions to assist farmers in taking timely and appropriate action. The proposed solution aims to improve the accessibility of advanced diagnostic tools for farmers, promoting long life agricultural practices and reducing crop losses. In the beginning testing shows promising results in terms of accuracy and usability, indicating the potential for widespread adoption in agricultural communities.