["Psychology &Marketing, EarlyView. ", "\nABSTRACT\nFirms often seek to replace human agents (HAs) with automated agents (AAs) for customer service, but customers still tend to react more negatively to AAs than to HAs. This meta‐analysis examines agent‐related perceptions (i.e., humanlikeness, warmth, and competence), which represent the key upstream customer reactions shaping downstream responses. Specifically, it clarifies the hierarchy of these perceptions and examines the moderating effect of task‐related risks (i.e., functional, psychological, and social) on these perceptions. Meta‐analytic path modeling with subgroup analyses, including 1191 effect sizes, provides novel insights. First, there is indication that perceived humanlikeness is not a prerequisite for perceived warmth and competence; all three perceptions emerge in parallel. Second, tasks entailing functional or psychological risk largely weaken the negative perceptions of AAs (vs. HAs). For psychologically risky tasks, AAs are not perceived as less competent than HAs. Tasks entailing social risk largely strengthen the negative perceptions of AAs (vs. HAs). These findings challenge two prevailing assumptions in the services marketing literature: that customers favor humans over AAs simply because they are not humanlike and that risk generally discourages AA usage. The results have important managerial and future research implications.\n"]