I study the welfare effect of automation on workers in a setting where technology is complementary but imperfect. Using a modified task-based framework, I argue that imperfect complementary automation can impose non-pecuniary costs on workers via a behavioral channel. The theoretical model suggests that a critical factor determining the welfare effect of imperfect complementary automation is the automatability of the production process. I confirm the model’s predictions in an experiment that elicits subjects’ revealed preference for automation. Increasing automatability leads to a significant increase in the demand for automation. I explore additional drivers of the demand for automation using machine learning analysis and textual analysis of choice reasons. The analysis reveals that task enjoyment, performance, and cognitive flexibility are the most important predictors of subjects’ choices. There is significant heterogeneity in how subjects evaluate imperfect complementary automation. I discuss the implications of my results for workers’ welfare, technology adoption, and inequality.