Urban centers in tropical developing nations face severe air pollution crises, yet a critical policy inertia gap persists between real-time sensor data acquisition and dynamic municipal enforcement. This study aims to develop and evaluate the Smart Air Quality Governance (SAQG) framework, an automated, artificial intelligence (AI)-enhanced Environmental Decision-Support System (EDSS) designed to bridge passive monitoring with legally binding administrative action. Employing a qualitative policy gap analysis and semi-structured key informant interviews (n = 12) with municipal environmental, transportation, and public health authorities in a tropical metropolitan area (Jakarta, Indonesia), this paper examines the institutional bottlenecks delaying emergency responses. Unlike traditional passive monitoring platforms, the novelty of the SAQG framework lies in its active execution engine, which directly links real-time PM2.5 sensor networks to a three-tiered automated policy matrix, enforcing immediate interventions such as adaptive signal timing, industrial emission caps, and mandatory work-from-home orders. The results demonstrate that embedding AI-driven predictive triggers into local government regulatory architectures significantly reduces administrative response latency during atmospheric crises. This study provides local authorities with a practical blueprint to transition from reactive observation to proactive urban resilience, directly advancing UN Sustainable Development Goals (SDG 3: Good Health and Well-Being, SDG 11: Sustainable Cities and Communities, and SDG 13: Climate Action).