MISCON: A Mission-Driven Conversational Consultant for Pre-Venture Entrepreneurs in Food Deserts

TL;DR

MISCON is a conversational system designed to assist pre-venture entrepreneurs in food deserts by providing tailored information and analysis through a state machine model utilizing knowledge graphs and LLMs.

Contribution

This work introduces MISCON, a novel conversational consultant architecture integrating knowledge graphs and analytical tools for supporting food-insecure entrepreneurs.

Findings

Designed a state machine-based conversational architecture

Integrated heterogeneous knowledge graphs and LLMs for tailored advice

Presented initial functional architecture and design considerations

Abstract

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.