<p>Urban environments are increasingly complex, dynamic, and data-intensive, requiring advanced spatial intelligence to support proactive, evidence-based governance. Current smart city and urban informatics platforms are limited by static datasets, siloed architectures, and underutilised AI capabilities. This study proposes and demonstrates a novel AIoT-enabled platform architecture for built environment mapping and spatial decision support. Anchored in platform urbanism, the architecture integrates high-resolution imagery, pretrained deep learning models from the ArcGIS Living Atlas, iterative workflows in ArcGIS Pro, and interactive dissemination via ArcGIS Experience Builder. The platform is demonstrated through building footprint detection in three Brisbane suburbs using the Building Footprint Extraction Australia model. Suburb-level processing enhances computational efficiency, while analytical extensions support footprint change detection, flood exposure assessment, and land-use zoning overlays. Results indicate that the platform transforms manual, fragmented processes into automated, reproducible, and dynamic workflows directly applicable to urban planning. Although demonstrated for building footprints, the architecture is scalable to other urban features, including roads, parcels, and solar panels. Limitations include dependence on high-resolution imagery and pretrained models, highlighting opportunities for future work in multi-model integration, real-time data streams, and developing AI models tailored to diverse urban contexts. By bridging cutting-edge AI innovation with operational governance needs, the proposed platform offers a replicable pathway for embedding AI-enabled spatial intelligence into smart city management.</p>