To explain persistent gender gaps in market outcomes, a lab experimental literature explores whether women and men have innate differences in ability (or attitudes or preferences), and a separate field-based literature studies discrimination against women in market settings. This paper posits that even if women have comparable innate ability, their relative performance may suffer in the market if the task requires them to interact with others in society, and they are subject to discrimination in those interactions. The paper tests these ideas using a large-scale field experiment in 142 Malawian villages where men or women were randomly assigned the task of learning about a new agricultural technology, and then communicating it to others to convince them to adopt it. Although female communicators learn and retain the new information just as well, and those taught by women experience higher farm yields, the women are not as successful at teaching or convincing others to adopt the new technology. Micro-data on individual interactions from 4,000 farmers in these villages suggest that other farmers perceive female communicators to be less able, and are less receptive to the women's messages. Relatively small incentives for rewards undo the disparity in performance by encouraging added interactions, improving farmers' accuracy about female communicators' relative skill.