Thinking through Prompting: Cognitive Mediation in Human-AI Interaction

8Citations
Citations of this article
14Readers
Mendeley users who have this article in their library.
Get full text

Abstract

Prompts are central to creative work with generative AI systems, yet they are often treated as simple and static interface components. This paper proposes a different view: prompts function as cognitive interfaces that mediate between user intent and algorithmic generation. Integrating theories of external cognition, interface semiotics, and pragmatist theories of situated inquiry, the paper provides a theoretical framing of prompting along three interrelated dimensions: semantic projection, compositional structuring, and interpretive negotiation. Through an empirical vignette from branding communication, I show how prompting can be seen as a dynamic representational activity, deeply embedded in cognitive processes of exploration, articulation, and iterative refinement. By reframing the prompt as a site of cognitive labor rather than as a static interface, this expands our understanding of interaction with generative AI as epistemic, semiotic, and situated.

Cite

CITATION STYLE

APA

Dalsgaard, P. (2025). Thinking through Prompting: Cognitive Mediation in Human-AI Interaction. In Proceedings of the 36th Annual Conference of the European Association of Cognitive Ergonomics, ECCE 2025. Association for Computing Machinery, Inc. https://doi.org/10.1145/3746175.3747192

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free