Should a city document chatbot use Agentic RAG?
A municipal document chatbot prototype aims to help citizens and local politicians search and understand meeting minutes, budgets, motions, reports, and similar public records. The project is and has a live demo.
It already runs as a prototype, but it fails when people ask questions in unexpected ways, mix several topics, or use words that do not closely match the documents. The main problem is that real users will not always ask questions in the neat, AI-friendly style that demos often assume.
is being considered because it could rewrite questions, run several searches, and take multiple steps before giving an answer. The key decision is whether that added process really helps messy questions enough to justify the extra build and work compared with simple RAG.
Key points
- The chatbot is for searching and understanding municipal documents.
- It covers records such as meeting minutes, budgets, motions, and reports.
- The current prototype struggles with unexpected wording, mixed topics, and questions that do not match document wording.
- could rewrite questions, search more than once, and answer through several steps.
- The tradeoff is better handling of messy questions versus , speed, and work.