This study presents an updated approach to accurately monitor the growth stages of tomatoes and predict optimal harvest intervals using the YOLO11 deep learning model. Tomatoes are a valuable agricultural crop, essential for food security, and rich in micronutrients, making their timely harvest crucial to maximising yield quality. Manual assessment of ripeness stages is labour-intensive and susceptible to error as it increases the likelihood of post-harvest losses and reduces overall efficiency. We leverage the YOLO11 model's object detection capabilities to address these challenges, optimised for precisely identifying tomato maturity stages under diverse agricultural conditions. Our model was trained and evaluated using the Laboro Tomato dataset, which includes high-resolution images across various ripeness stages, achieving significant performance improvements over previous YOLO versions. The YOLO11 model demonstrated enhanced accuracy and computational efficiency, with a mean Average Precision (mAP) of 89.4%, improving the precision and recall rates compared to baseline models. The system allows farmers to make timely decisions about harvest intervals helps minimise waste and improves irrigation based on stages of growth. Our findings underscore the potential of deploying advanced deep learning models like YOLO11 in agricultural applications, offering a scalable solution for real-time, and accurate crop monitoring. This study contributes to the field by providing an effective framework for automated harvest scheduling, which could be extended to other crops and adapted to diverse environmental conditions.