Beyond Tools: Generative AI as Epistemic Infrastructure in Education

TL;DR

This paper conceptualizes AI in education as epistemic infrastructure that influences human knowledge practices, highlighting how AI systems can support or hinder the development of epistemic agency and professional judgment.

Contribution

It introduces a novel framework analyzing AI as epistemic infrastructure, emphasizing conditions that support or undermine epistemic agency in educational contexts.

Findings

AI tools often perform cognitive operations without fostering epistemic sensitivity.

Current AI systems tend to substitute tasks rather than support skilled epistemic actions.

Design principles are proposed to help AI sustain human epistemic agency.

Abstract

AI systems are increasingly embedded in practices where humans have traditionally exercised epistemic agency, the capacity to actively engage in knowledge formation and validation. This paper argues that understanding AI's impact on epistemic agency requires analyzing these systems as epistemic infrastructures rather than as neutral tools. Drawing on theories of technological mediation and distributed cognition, I advance a framework that foregrounds how AI systems reconfigure the conditions under which epistemic agency can be exercised. The framework specifies three analytical conditions: affordances for skilled epistemic actions, support for epistemic sensitivity, and implications for habit formation. I apply this framework to AI systems deployed in education, a domain where epistemic agency is both professionally essential and ethically significant. Analysis of AI lesson planning and feedback tools reveals patterns of epistemic substitution: while useful for efficiently handling teaching tasks, these systems perform cognitive operations without sustaining skilled epistemic actions, epistemic sensitivity, or virtuous habit formation, potentially preventing the cultivation of professional judgment that relies on these practices. The findings contribute to philosophical debates about AI and human agency by specifying mechanisms through which infrastructural embedding shapes epistemic possibilities, and offer design principles for AI systems that sustain rather than supplant human epistemic agency.