The Artefact Trap: Why Digital Agriculture Research Keeps Missing the Field

Digital agriculture (sensors, Internet of Things, machine learning, robotics, digital twins) has for fifteen years been sustained by massive investment promising more productive, precise, and sustainable agriculture, yet adoption remains heterogeneous and systemic impact limited despite intense scientific output. The dominant explanation treats this as a diffusion deficit and calls for more farmer training, advisory support, and subsidy; this reading leaves the structure of research itself unexamined and does not, on its own, explain why the gap between announced and delivered performance persists across technology generations. We argue that, alongside diffusion-side and demand-side factors, the paradox has a further, under-recognised upstream component: research design oriented towards technological artefacts rather than guaranteed functions. We develop the case for this complementary reading using Stahel’s performance economy framework and the Product-Service Systems literature. Four contributions follow: a tripartite typology of function (service-, specification-, and process-function) articulated hierarchically explains why research centred on specification-function alone cannot guarantee a service-function; current research is characterised, on the reading developed here, by three cumulative biases and three blind spots, including data governance and the under-representation of the social sciences; a four-axis reorientation agenda is proposed; and the framework is distinguished from Agricultural Innovation Systems, Responsible Research and Innovation, and mission-oriented research by specifying the functional level these leave indeterminate.