Agricultural reproduction functions as a primary foundation for numerous countries including India to provide stable income for multiple families who work within it, although they experience problems because of plant illnesses and climate pattern changes. The research has resulted in developing a web application that delivers immediate crop recommendations utilizing soil nutrient environmental information together with temperature and humidity and pH values and precipitation information. Artificial intelligence together with machine learning technologies has developed effective data-based decision platforms to modify traditional agricultural decision-making procedures. These implemented technologies allow for improved crop yield predictions and appropriate disease detection to enhance agricultural practice operations. A research assessment included training seven predictive tools: Decision tree, Naive Bayes, Support Vector Machine (SVM), Logistic Regression, Random Forest, XGBoost, and K-Nearest Neighbor (KNN). The use of Random Forest as the crop forecasting tool makes sense since it delivers the highest level of prediction accuracy. The web application performs crop recommendations through its Plant Disease Identification system that applies convolutional neural network (CNN) technology. Leaf image analysis enabled by CNN produces exact diagnoses of plant health problems that enable farmers to prevent potential losses of their crops. The research objective provides farmers with technology solutions that help them make improved crop decisions and plant disease diagnosis. The combination of crop recommendation and disease detection features in intelligent systems promotes sustainable farming practices that strengthen economic stability and food security operations within India and other regions.