BizChat: Scaffolding AI-Powered Business Planning for Small Business Owners Across Digital Skill Levels
Quentin Romero Lauro, Aakash Gautam, Yasmine Kotturi
TL;DR
Small business owners face barriers to adopting generative AI due to diverse digital skills and tacit knowledge. The authors introduce BizChat, an LLM-powered web application that scaffolds business-plan drafting across skill levels, guided by three design principles—low-floor-high-ceiling, just-in-time learning, and contextualized technology—derived from workshop series and interviews. The paper details an implementation using a multi-model chatbot architecture and an end-to-end drafting workflow that integrates voice-to-text, in-editor prompts, SBA example references, and expert feedback. This work demonstrates a practical path to democratize AI-enabled entrepreneurship and informs HCI research on inclusive adoption of emerging technologies when user skill diversity is high.
Abstract
Generative AI can help small business owners automate tasks, increase efficiency, and improve their bottom line. However, despite the seemingly intuitive design of systems like ChatGPT, significant barriers remain for those less comfortable with technology. To address these disparities, prior work highlights accessory skills -- beyond prompt engineering -- users must master to successfully adopt generative AI including keyboard shortcuts, editing skills, file conversions, and browser literacy. Building on a design workshop series and 15 interviews with small businesses, we introduce BizChat, a large language model (LLM)-powered web application that helps business owners across digital skills levels write their business plan -- an essential but often neglected document. To do so, BizChat's interface embodies three design considerations inspired by learning sciences: ensuring accessibility to users with less digital skills while maintaining extensibility to power users ("low-floor-high-ceiling"), providing in situ micro-learning to support entrepreneurial education ("just-in-time learning"), and framing interaction around business activities ("contextualized technology introduction"). We conclude with plans for a future BizChat deployment.
