Voice CMS: updating the knowledge base of a digital assistant through conversation
Grzegorz Wolny, Michał Szczerbak
TL;DR
This work presents Voice CMS, a voice-based knowledge-base update mechanism for a multi-agent LLM-enabled digital assistant, evaluated against a GUI CMS in a hotel context. The study finds that GUI generally provides higher usability and efficiency, but Voice CMS is preferred for simpler tasks and can yield comparable content quality; results suggest hybrid voice-visual interfaces to mitigate cognitive load and improve confidence. The approach demonstrates the viability of conversational interfaces for knowledge management in business settings and highlights design implications, such as the need for visual feedback to complement voice interactions. Overall, the findings point to a balanced, hybrid interaction paradigm as a practical path forward for maintaining up-to-date knowledge bases in dynamic environments.
Abstract
In this study, we propose a solution based on a multi-agent LLM architecture and a voice user interface (VUI) designed to update the knowledge base of a digital assistant. Its usability is evaluated in comparison to a more traditional graphical content management system (CMS), with a focus on understanding the relationship between user preferences and the complexity of the information being provided. The findings demonstrate that, while the overall usability of the VUI is rated lower than the graphical interface, it is already preferred by users for less complex tasks. Furthermore, the quality of content entered through the VUI is comparable to that achieved with the graphical interface, even for highly complex tasks. Obtained qualitative results suggest that a hybrid interface combining the strengths of both approaches could address the key challenges identified during the experiment, such as reducing cognitive load through graphical feedback while maintaining the intuitive nature of voice-based interactions. This work highlights the potential of conversational interfaces as a viable and effective method for knowledge management in specific business contexts.