When and What Conversational AI Should Ask: Extending the Persuasion Knowledge Model to Explain User Engagement and Purchase Intention

Conversational AI is rapidly expanding in e-commerce, where chatbot questions critically shape users’ cognition and engagement. Yet, the effects of question timing and type on persuasion remain underexplored. Building on the persuasion knowledge model, this study examines how question timing (in-conversation vs. follow-up) and type (informational vs. experience-evoking) influence users’ knowledge structures, flow experience, and purchase intention. We developed a retrieval-augmented generation-based recommendation chatbot and conducted an online experiment with 335 participants. The analysis showed that informational questions presented during the conversation and experience-evoking questions presented as follow-up prompts strengthened topic knowledge. Persuasion knowledge was most strongly activated when experience-evoking questions appeared during the conversation, whereas agent knowledge varied depending on the timing–type combination. Topic knowledge positively predicted flow components and purchase intention, whereas persuasion knowledge negatively predicted these outcomes. Agent knowledge was activated under certain question configurations but did not directly predict flow experience or purchase intention.