Poultry farming is a critical sector for food security and rural livelihoods, yet traditional practices remain highly labor-intensive and vulnerable to environmental stressors and disease outbreaks. This project presents the design and implementation of a Smart Poultry Farm system that integrates Internet of Things (IoT)-based automation with deep learning (DL)-enabled disease detection. The system leverages an IoT32 microcontroller and multiple low-cost sensors, including DHT22 for temperature and humidity, MQ135 for gas concentration, ultrasonic and water-level sensors for feed and water monitoring, and a flame sensor for fire detection. Actuators such as servo motors, a water pump, a fan, a heating bulb, and a buzzer were programed to respond automatically to sensor thresholds, ensuring consistent environmental management and chicken welfare. In parallel, an ESP32-CAM module was deployed to capture fecal images of poultry, which were classified by a DL pipeline trained on four categories: coccidiosis, Newcastle disease, salmonella, and healthy. A total of seven state-of-the-art architectures were benchmarked, and EfficientNet-B0 was settled on as the final model with a test accuracy of 99.19% on a held-out test set of a public fecal image dataset and 95.62% on a separate real-world dataset of local commercial poultry farms. The model’s lightweight design and high accuracy make it suitable for integration with ESP32-CAM in real farm conditions. A Fast Application Programming Interface (FastAPI)-based backend and web dashboard were developed as a cloud server to unify the system, enabling farmers to log in, visualize sensor data, monitor actuator status, and view disease detection results in real time. System evaluation confirmed reliable automation with response times under 2 s and robust disease detection performance. The proposed system represents a cost-effective, scalable, and sustainable solution for small-scale poultry farms. By reducing manual labor, improving environmental stability, and enabling early disease detection, it contributes to both improved farm productivity and enhanced poultry welfare.