project · 2025
Neighbourly, AI location analyser
Hackathon prototype that turns an address into a structured neighbourhood profile using a multi-step, tool-using AI workflow.
The idea
Choosing an area involves many small questions about nearby places, accessibility, and local context. The prototype explored whether an agent could coordinate those questions into one transparent experience.
Approach
- Built a full-stack interface around structured location, routing, and place-search tools.
- Used a multi-step workflow to gather evidence before creating a concise profile.
- Kept the output explainable by showing the inputs behind each part of the result.
Outcome
The project demonstrated how tool-using agents can turn a broad location question into a useful, inspectable set of answers.