This study focuses on the “IoT-Integrated Micro Particulate Matter (PM) Sensing System,” combining expertise in electrical and electronic engineering with Internet of Things (IoT) technology to develop a multi-device air-quality monitoring platform featuring real-time detection, cloud transmission, and intelligent data analysis. The research motivation stems from the Ministry of Environment’s “Air Quality Improvement Action Plan,” aiming to create a low-cost, highly scalable solution that helps schools and communities establish real-time monitoring mechanisms—making invisible pollution quantifiable and rapidly recorded. The system adopts a PMS5003 sensor module and an ESP32 microcontroller, with a Flask-based server architecture supporting data uploads from multiple sensors to the cloud, simultaneously displaying results on a web interface. Integrated with Google AI models, the platform analyzes air-quality data to provide pollution trends and health recommendations. A 3D-printed enclosure was also designed, offering dust protection, heat dissipation, and ease of maintenance. Experimental results show that the system can accurately capture pollution fluctuations in real time and stably upload data to the cloud. Through concise AI-generated summaries, it provides reliable analytical feedback, demonstrating strong sensitivity, stability, and practical intelligence. The system can be applied to campus, household, and community air-quality monitoring, and also serves as an educational model for environmental awareness and sustainable development, the concept of safeguarding health through technology.