Thermal comfort, luminosity, and air quality are factors that directly impact the health, wellbeing, and cognitive performance of occupants in an indoor environment. It is crucial that ergonomic parameters such as temperature, humidity, light levels, and carbon dioxide concentration in these spaces adhere to criteria established by Brazilian standards. Addressing this issue, this study presents a methodology for developing a Wireless Sensor Network (WSN) with the objective of intelligently monitoring and classifying the environmental quality of study spaces. The WSN nodes comprise signal acquisition sensors, a microcontroller for processing, classification, and communication, and a multiplexer serving as an analog input expander for the microcontroller. The software components encompass signal processing, communication, and classification algorithms leveraging machine learning techniques. To enable remote monitoring, the collected signals and classifications are transmitted and stored in a cloud infrastructure utilizing Internet of Things (IoT) and cloud computing techniques.