Humans and artificial intelligence (AI) algorithms increasingly interact on unstruc-tured managerial tasks. We propose that tailoring this human-AI interaction to align withindividuals’ cognitive preferences is essential for enhancing performance. This hypothesisis examined through a field experiment in a multinational pharmaceutical firm. In the exper-iment, we manipulated four contextual parameters of human-AI interaction—work proce-dures, decision-making authority, training, and incentives—to align with sales experts’cognitive styles, categorized as either adaptors or innovators. Our results show that tailoredinteraction significantly improves sales performance, whereas untailored interaction resultsin negative treatment effects compared with both the tailored and control conditions. Quali-tative evidence suggests that this negative outcome arises from role conflicts and ambigui-ties in untailored interaction. Exploring the mechanisms underlying these outcomes further,a mediation analysis of AI login data reveals that human-AI interaction tailoring leads salesexperts to adjust their AI utilization, which contributes to the observed performance out-comes. These findings support a human-centered approach to AI that prioritizes indivi-duals’ information-processing needs and tailors their interaction with AI accordingly.