| Creators: |
Martinenghi, Andrea and Guidotti, Sabrina and Donabauer, Gregor and Koyuturk, Cansu and Ortiz Beltran, Ariel and Theophilou, Emily and Chimisso, Riccardo and Bink, Markus and Garzotto, Franca and Taibi, Davide and Ruskov, Martin and Kruschwitz, Udo and Hernandez-Leo, Davinia and Ognibene, Dimitri |
| Title: |
Genie Training the Wisher: Six-Dimension Task-Agnostic AI Coaching for Learning Transferable LLM Prompting Skills |
| Item Type: |
Conference or Workshop Item |
| Event Title: |
(Proceedings of the) 27th International Conference Artificial Intelligence in Education (AIED) |
| Event Location: |
Seoul, Rupublic of Korea |
| Event Dates: |
June 27 - July 3, .26 |
| Projects: |
IDI |
| Page Range: |
pp. 424-438 |
| Date: |
27 June 2026 |
| Divisions: |
Informationsmanagement |
| Abstract (ENG): |
Effective prompting has become a key skill for interacting with Large Language Models (LLMs), yet most existing support focuses on optimizing prompts for specific tasks or domains. In this work, we introduce Prompting Coach (PC), a task-agnostic prompting support tool designed to help users improve their general prompting skills, rather than performance on a single prompt or application. Grounded in a conceptual framework that defines six core dimensions of prompting, our tool captures prompt qualities and information types that recur across diverse prompting patterns and interaction paradigms. PC provides heuristic feedback on user prompts, highlighting strengths and weaknesses along these dimensions and offering actionable suggestions without relying on task-specific templates or domain knowledge. To evaluate its effectiveness, we conducted a controlled user study in which participants (N=66) interacted with PC under different configurations and across sequences of heterogeneous tasks. We measured both task outcomes and prompt quality over time. Users who received prompting feedback significantly improved their task performance and prompt quality compared to the baseline condition. Importantly, these improvements generalized beyond the immediate task: participants who used PC on earlier tasks demonstrated higher performance when approaching new, previously unseen tasks, even when feedback was absent. These findings suggest that PC, grounded in six prompting dimensions, supports transferable learning of prompting strategies rather than short-term optimization. Overall, while LLM users may improve through repeated unsupported use, automated task-agnostic support accelerates the development of transferable prompting skills. This provides insights for the design of AI literacy programs and further understanding of prompting as a learnable, generalizable interaction skill. |
| Forthcoming: |
No |
| Language: |
English |
| Uncontrolled Keywords: |
AI Literacy, Learning to Prompt, Prompting, Prompting Coach |
| Link eMedia: |
Download |
| Citation: |
Martinenghi, Andrea and Guidotti, Sabrina and Donabauer, Gregor and Koyuturk, Cansu and Ortiz Beltran, Ariel and Theophilou, Emily and Chimisso, Riccardo and Bink, Markus and Garzotto, Franca and Taibi, Davide and Ruskov, Martin and Kruschwitz, Udo and Hernandez-Leo, Davinia and Ognibene, Dimitri
(2026)
Genie Training the Wisher: Six-Dimension Task-Agnostic AI Coaching for Learning Transferable LLM Prompting Skills.
In: (Proceedings of the) 27th International Conference Artificial Intelligence in Education (AIED), June 27 - July 3, .26, Seoul, Rupublic of Korea, pp. 424-438.
(Lecture Notes in Computer Science; 16584).
ISBN 9783032297631
|
 |
View Item in edit mode (academic staff only) |
