Leading the technology for SmartSustain, an Innovate UK funded planning platform used across five West Yorkshire councils — from geospatial pipelines and search to an AI agent and the map on top.
5
West Yorkshire councils
700+
sites scored 0–100
Millions
records through ETL
- 01Led the technology for SmartSustain, working with technical colleagues, planning officers and council stakeholders to turn loosely defined planning requirements into working features and explain trade-offs in plain terms.
- 02Designed and built the FastAPI backend on PostgreSQL and SQLAlchemy, with async endpoints for site search, assessment, scoring, map data and the AI assistant.
- 03Wrote ETL pipelines that clean, normalise and load millions of records from inconsistent government and open-data sources, and designed the data model and indexes to keep queries responsive at that size.
- 04Built geospatial queries over flood risk, road noise, air quality and other environmental layers, with Redis caching and bounds-based queries so the map only loads data for the area in view.
- 05Built an AI agent workflow with Python, LangChain and OpenAI models, letting planning officers ask natural-language questions that invoke backend tools, retrieve site-specific information and synthesise actionable insights.
- 06Built the assistant's RAG pipeline on pgvector, combining vector search with location and metadata filters so answers are grounded in the data for that specific site.
- 07Built Elasticsearch site search by address, postcode, council or developer, with typo-tolerant matching and faceted filters by sustainability score, developability and site size.
- 08Implemented a deterministic, weighted scoring engine that rates 700+ candidate sites from 0 to 100 across environmental, economic, social and regulatory pillars.
Stack
Python / FastAPI / PostgreSQL / pgvector / Elasticsearch / Redis / LangChain / React / MapLibre / AWS
Built here