Students' multimodal prompting practices as epistemic work in AI literacy development

Synthesis: Students' multimodal prompting practices as epistemic work in AI literacy development

Key Findings

Prompting strategies vary along a continuum from basic input-output use to strategic, iterative, and dialogic practices. Across the eight student groups, the authors mapped four prompting methods — Input-Output, Role-Play, Chain-of-Thought, and Generated Knowledge — with one group (G5) interrogating the system about the components of a good story before generating and another (G3) instructing it step-by-step through the assignment.

Prompting emerges as a central epistemic practice through which students critically interpret, refine, and negotiate AI-generated outputs — for example, one group's 16-step prompting history moved from exploring genre conventions to challenging the system's character design choices and requesting explanations of its revisions.

Multimodal engagement exposes challenges in translating abstract meaning into machine-readable prompts, fostering awareness of system limitations and bias: students concluded that "prompt literacy is different between prompting for text than it is for pictures," and that image outputs became increasingly divergent from their intended vision without a precise visual vocabulary ("We realized we don't have as much experience prompting for images").

Students develop the need to actively construct coherence across modalities when producing text and image outputs, and learn tool-specific constraints — Copilot's image generation was judged less effective than ChatGPT or DALL·E, and groups switched tools after copyright-related refusals, evaluating systems on performance and output quality.

While students demonstrate developing competence in evaluation and creation, the ethical dimensions of AI Literacy remain underdeveloped: reflections focused on functionality and alignment rather than fairness, transparency, privacy, or responsible use.

Study Design & Method

The study was conducted as an exploratory workshop with 28 postgraduate students engaged in collaborative multimodal prompting tasks, including the creation of short stories or poems and corresponding images using a university-provided GenAI tool. The participants (aged 23–44) came from diverse cultural, linguistic, and academic backgrounds spanning Europe, Asia, Africa, and the Americas, with prior GenAI experience ranging from information retrieval and summarization to image generation and coding tasks. The workshop lasted 1h 45min across two sessions of four groups each; all four groups chose short stories in the first session and the majority chose poems in the second, yielding a balanced exploration of narrative and poetic formats. The corpus comprised eight self-documented group reports (6–22 pages each, 109 pages in total) containing prompting histories, motivations, and reflections, analyzed qualitatively using reflexive thematic analysis, guided by frameworks for prompting methods and AI literacy. The design aimed to provide empirical insight into two questions: which prompting strategies students develop when interacting with open-ended GenAI tools, and how engagement in prompt engineering activities shapes their understanding of GenAI and AI Literacy more broadly.

Implications for AI in Education

The findings position prompting as an epistemic practice — a way of learning to interpret, negotiate, and guide AI-generated outputs — rather than a merely technical skill. Because students' strategies ranged from simple input-output use to iterative, dialogic refinement, the study suggests that Prompt Engineering competence develops through hands-on engagement rather than through rule-based instruction alone, with effective prompting depending on balancing specificity and openness rather than simply adding detail. Multimodal tasks proved valuable for surfacing the interpretive work behind prompt construction: text prompting yielded satisfactory results with fewer attempts than image prompting, and students discovered that coherence across modalities must be actively constructed, requiring a more precise visual vocabulary. Yet the comparatively weak development of ethical reasoning points to a gap that standard evaluation-and-creation activities do not close on their own — students evaluated tools primarily on performance and output quality, with limited engagement with fairness, transparency, or responsible use. For Higher Ed practitioners, the results highlight the value of iterative, reflective, and multimodal learning designs that foster critical, strategic, and responsible engagement with AI, and they suggest that ethical dimensions of literacy — including platform governance, copyright, bias, and responsible AI use — need to be taught explicitly across the curriculum rather than assumed to follow from technical proficiency. The findings also connect prompting to Multimodal literacy more broadly, positioning it as a situated practice requiring distinct forms of interpretation and meaning-making across text and image generation.

Limitations

The author notes that the small sample size (28 postgraduate students) limits the generalizability of the findings: although participants represented diverse disciplines, professions, and geographic regions, they were self-selected and enrolled in a course module that may have attracted students with a pre-existing interest in technology or digital innovation. The study was confined to a single workshop within a specific course context, which restricts the scope of the intervention and the depth of longitudinal insight into students' evolving AI literacy. The findings should therefore be interpreted as exploratory and context-specific, pointing to the need for broader, more sustained studies across varied educational settings and learner populations.

Connected Concepts

Automated Essay Scoring

Reducing AI Misuse

Affective Tutoring

CS Education

Connected Articles

Slidesqaqa Pedagogical Question Generation — Slide Deck Q&A Quality Assurance App: A Multi-Stage Pipeline for Pedagogical Question Generation

Same AI Different Pathways — Same AI, different pathways: Unpacking mechanisms of AI-mediated learning across discipline-institution contexts

Pchl He Framework GenAI Content Creation 2026 — From Prompts to Verified Loops: The PCHL-HE Framework for Generative AI-Assisted Educational and Research Content Creation in Higher Education

Prompt Problems Nl Programming Mistakes — Understanding Student Perceptions, Mistakes, and Debugging Approaches when Solving Natural Language Programming Tasks

Choi Anchor Aes Prompting 2025 — Anchor Is the Key: Toward Accessible Automated Essay Scoring with Large Language Models Through Prompting

Misiejuk Cognitive Offloading Prompting 2026 — Cognitive Offloading in Student–AI Collaboration: A Longitudinal Analysis of Prompting Strategies

Citation

Sofkova Hashemi, S. (2026). Students' multimodal prompting practices as epistemic work in AI literacy development.