Dukawalla: Voice Interfaces for Small Businesses in Africa
Elizabeth Ankrah, Stephanie Nyairo, Mercy Muchai, Kagonya Awori, Millicent Ochieng, Mark Kariuki, Jacki O'Neill
TL;DR
Addressing the challenge that SMBs in Africa lack accessible analytics, the paper presents Dukawalla, a voice-enabled LLM assistant that translates spoken data into actionable insights. It reports a two-week, field-based deployment with seven Nairobi SMBs to study how voice interfaces can support data collection and decision-making. Contributions include a mobile-first architecture combining voice capture, LLM-driven structuring to CSV, and bite-sized visualizations, along with qualitative findings on sociocultural and linguistic barriers. The work highlights practical potential and the need for improved multilingual ASR, language-aware prompting, and workflow integration to realize scalable adoption.
Abstract
Small and medium sized businesses often struggle with data driven decision making do to a lack of advanced analytics tools, especially in African countries where they make up a majority of the workforce. Though many tools exist they are not designed to fit into the ways of working of SMB workers who are mobile first, have limited time to learn new workflows, and for whom social and business are tightly coupled. To address this, the Dukawalla prototype was created. This intelligent assistant bridges the gap between raw business data, and actionable insights by leveraging voice interaction and the power of generative AI. Dukawalla provides an intuitive way for business owners to interact with their data, aiding in informed decision making. This paper examines Dukawalla's deployment across SMBs in Nairobi, focusing on their experiences using this voice based assistant to streamline data collection and provide business insights