ProtoChat: Supporting the Conversation Design Process with Crowd Feedback

Yoonseo Choi, Toni-Jan Keith Monserrat, Jeongeon Park, Hyungyu Shin, Nyoungwoo Lee, Juho Kim

Abstract: Conversation designers use iterative design to create, test, and improve conversation flows. While it is possible to iterate conversation design with existing chatbot prototyping tools, challenges remain such as recruiting participants and collecting structured feedback on specific conversational components, hindering rapid iterations, and making informed design decisions. To address these limitations, we introduce ProtoChat, a crowd-powered design tool built to support the iterative process of conversation design for a chatbot. ProtoChat enables rapid testing with the crowd and guiding the crowd workers to provide granular feedback on specific points of conversation.