The shift from browsing to AI prompting challenges web-tracking data

Abstract Digital behavioural traces have become an important source of evidence for studying population behaviour, especially as social, economic, and informational activities increasingly take place online. Web-tracking data have been particularly valuable because they capture high-frequency signals of how individuals search, navigate, compare sources, and interact with digital environments. However, this empirical foundation is being disrupted by the rapid diffusion of artificial intelligence (AI) technologies, especially large language models (LLMs), which increasingly redirect user behaviour from exploring different information sources online to requesting direct answers within chats embedded in closed platforms. This paper discusses the methodological foundations of using web-tracking data for demographic inference and examines how these data are combined with surveys, censuses, and administrative records. It then analyses how the shift from browsing to AI prompting may reduce the observability, richness, and comparability of digital behavioural traces. By assessing both the opportunities and limitations of these data, the article clarifies their role in demographic research and considers how computational social science and evidence-based social policy may need to adapt in an increasingly AI-mediated information environment.