The language skills of young children can predict their academic success in later schooling. We may be able to help more children succeed by helping them improve their early language skills: a prime time for intervention is during preschool. Furthermore, because language lives in a social, interactive, and dialogic context, ideal interventions would not only teach vocabulary, but would also engage children as active participants in meaningful dialogues. Social robots could potentially have great impact in this area. They merge the benefits of using technology -- such as accessibility, customization and easy addition of new content, and student-paced, adaptive software -- with the benefits of embodied, social agents -- such as sharing physical spaces with us, communicating in natural ways, and leveraging social presence and social cues.To this end, we developed a robotic learning/teaching companion to support children's early language development. We performed a microgenetic field study in which we took this robot to two Boston-area preschools for two months. We asked two main questions: Could a robot companion support children's long-term oral language development through play? How might children build a relationship with and construe the robot over time?