Agriculture plays a vital role in the economic development and food security of a nation. However, farmers often face challenges in selecting suitable crops and identifying plant diseases at early stages, which leads to reduced productivity and financial loss. To address these issues, this paper proposes FarmAssist AI, an intelligent system that integrates crop recommendation and plant disease detection. The system utilizes machine learning techniques to recommend crops based on environmental parameters such as nitrogen, phosphorus, potassium, temperature, humidity, pH, and rainfall. Additionally, deep learning models, specifically convolutional neural networks (CNN), are used to detect plant diseases from leaf images. This approach enhances decision-making, improves crop yield, and supports smart agriculture practices.