Inspiration : Urban environments face increasing climate and routing challenges. We wanted to combine spatial data with modern AI tools to build an accessible, data-driven decision support engine.
What it does: This application stitches together real-world OpenStreetMap spatial data, statistical analytics, and AI-driven insights into an interactive dashboard.
How we built it: Built under the Frankenstein category using Kiro (Specs, Steering Docs, and Agent Hooks), Python spatial libraries, cloud infrastructure, and Streamlit for the user interface.
Challenges we ran into: Integrating heterogeneous spatial datasets with real-time AI retrieval workflows while keeping the pipeline lightweight and responsive.
Accomplishments that we're proud of: Designing a modular architecture that seamlessly connects geospatial analytics, cloud data engineering, and interactive visualization.
What we learned: Structuring AI-assisted development workflows using Kiro Specs and Steering Docs to accelerate spatial data pipeline prototyping.
What's next for Urban Climate & Heat Vulnerability RAG Engine: Finalizing the data pipeline, deploying the live interactive dashboard, and recording the full demo walkthrough.
