Town Councils receive a wide variety of resident feedback daily — from minor maintenance requests to urgent safety concerns. Much of the current case-handling process relies on manual review, officer judgement, and follow‑up, creating bottlenecks and inconsistency.
This project explores how a digital prototype enhanced with AI can support officers in handling resident feedback more effectively, while maintaining full accountability.
Town Councils receive a high volume of resident feedback each day, ranging from routine maintenance requests to urgent safety issues. Existing case management processes often rely on manual review and officer judgement, resulting in inconsistent handling, limited case visibility, and slower response times.
This project presents an AI-powered prototype that supports case classification, workflow guidance, and response drafting while keeping officers in control through a human-in-the-loop approach. Built with Python and Streamlit, the system combines natural language processing (NLP) and rule-based decision logic to streamline case triage, standardise workflows, and provide a consolidated view of case histories and audit trails.
While the prototype demonstrates the potential to improve efficiency, consistency, and transparency in case management, these benefits have not yet been validated in a live Town Council environment. Overall, the project showcases how AI can be responsibly integrated into public service workflows by enhancing, rather than replacing, human decision-making.
