We investigated whether fine-grained coordination in a screen-based puzzle task with a (virtual) partner would influence on-line perspective-taking. Participants played a screen-based puzzle game with a computer player. In the high-coordination condition, the player presented participants with puzzle pieces that could be placed near their partner’s last piece. In the low-coordination condition, pieces could only be placed further away from their partner’s last piece. Participant’s eye movements were then measured in a referential communication task, with the partner giving the instructions, and whether possible competitor referents were in shared or privileged ground. The results demonstrate clear effects of ground and coordination. Participants in both coordination groups were sensitive to the perspective of the interlocutor. In addition, participants in the high-level coordination condition were more sensitive to statistical regularities in the input and their comprehension was more time-locked to the utterance of the speaker.