Conversational discourse is a cognitive and social process influenced by both discourse content and pragmaticfactors, such as the participants’ prior knowledge; these factors may also affect how simulated conversations with virtual agentsunfold, with implications for design. This study explored effects of question content and perceived expertise of a virtual agenton students’ interactions with a conversation-based assessment (CBA) measuring science inquiry skills. Twenty-four middleschool students were randomly assigned to work with a High- or Low-Knowledge virtual peer to collect data and generateweather predictions. Students evaluated their own data relative to the peer’s; they could either ”Choose” which note to keep, orto ”Agree/Disagree” with the peer’s suggested choice of note. Students rated the peer as more expert in the High-Knowledgecondition, but peer expertise did not affect performance. However, the Agree/Disagree condition improved students’ accuracyin their note choice, and yielded marginally higher pre-post learning gains.