MISCON: A Mission-Driven Conversational Consultant for Pre-Venture Entrepreneurs in Food Deserts
This addresses the problem of supporting pre-venture entrepreneurs in food deserts, but it is a work-in-progress report with no results yet.
The paper introduces MISCON, a conversational consultant designed to help aspiring small business owners and advisors in food-insecure regions get information and analysis for setting up food businesses, using a state machine model with a knowledge graph and LLMs.
This work-in-progress report describes MISCON, a conversational consultant being developed for a public mission project called NOURISH. With MISCON, aspiring small business owners in a food-insecure region and their advisors in Community-based organizations would be able to get information, recommendation and analysis regarding setting up food businesses. MISCON conversations are modeled as state machine that uses a heterogeneous knowledge graph as well as several analytical tools and services including a variety of LLMs. In this short report, we present the functional architecture and some design considerations behind MISCON.