Tomato farming plays a vital role in global agriculture, but its productivity often faces significant challenges due to various leaf diseases caused by microbes like bacteria, viruses and fungi. This infection can lead to substantial production loss and financial hardship, especially for small-scale farmers. Accurate and timely detection of these diseases are essential for preventing crop damage and ensuring sustainable farming practices. Traditional methods of identifying diseases rely on manual observation, which can be slow, subjective, and error-prone. This project aims to address this challenge by utilizing advanced machine learning techniques, specifically Convolutional Neural Networks (CNNs), to build a reliable and efficient system for tracking tomato leaf diseases. The system will analyze images of tomato leaves, classify them into disease categories, and provide valuable insights to farmers. A well-curated dataset containing depiction of tomato leaves affected by diseases such as late blight, early blight, and septoria leaf spot will be used to train the model. To improve accuracy under diverse conditions, data augmentation methods will be applied. Preliminary results indicate that CNN-based models outperform traditional methods, achieving superior results in terms of reliability and precision. This automated system has the potential to be integrated into mobile applications or IoT-based solutions, providing real-time disease detection for farmers, thereby boosting productivity and sustainability in tomato farming.