Answers are grounded in this paper and cite their sources.
Conversational AI chatbots are emerging as scalable mental health tools, but little is known about real world engagement or its relationship to clinical outcomes. To characterize engagement phenotypes among users of Ash, a purpose-built AI mental health chatbot, and examine associations with clinical change and working alliance. K-means clustering across eight behavioral features identified engagement phenotypes among 102,684 users. Subsamples completed the PHQ-9 ( n = 298), GAD-7 ( n = 298), and MSPSS (social support; n = 194) at baseline and 3 weeks; 11,437 users completed baseline Working Alliance Inventory (WAI). Five engagement phenotypes emerged: Early Dropouts (52.2%), Power Users (1.6%), Intensive Users (4.1%), Weekly Users (25.3%), and a novel Concentrated User pattern (16.8%); across users, 66.9% had at least one overnight session (9pm-5am). Significant pre-post improvements occurred in depression ( d = -0.51), anxiety ( d = -0.57), and social support ( d = 0.22). An observed dose-response gradient in self-reported depression improvement was replicated in a larger sample using model-predicted PHQ-9 ( n = 23,813), with the largest improvements among high-engagement Power and Intensive Users ( d = -0.57 and -0.50) and the smallest among Early Dropouts ( d = -0.22). Higher working alliance predicted depression improvement and moderated the engagement-social support relationship. Engagement with AI mental health tools is multidimensional, and different clinical outcomes respond to different dimensions of use. Findings caution against treating session counts as a primary engagement metric and offer naturalistic, correlational evidence consistent with clinical benefit of purpose-built conversational AI, pending confirmation in controlled designs.
No takes yet. Share an insight, caveat, or question.
Wolfe et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: