{"id":660308,"date":"2026-10-08T14:03:05","date_gmt":"2026-10-08T12:03:05","guid":{"rendered":"https:\/\/preprod.aivancity.ai\/blog\/educational-prompts-and-generative-ai-what-does-a-prompt-actually-do-pedagogically\/"},"modified":"2026-10-16T12:38:30","modified_gmt":"2026-10-16T10:38:30","slug":"educational-prompts-and-generative-ai-what-does-a-prompt-actually-do-pedagogically","status":"publish","type":"post","link":"https:\/\/preprod.aivancity.ai\/blog\/en\/educational-prompts-and-generative-ai-what-does-a-prompt-actually-do-pedagogically\/","title":{"rendered":"Educational Prompts and Generative AI: What Does a Prompt Actually Do Pedagogically?"},"content":{"rendered":"\n
\n

\n By\n <\/p>\n\n

\n\n
\n

\n \n Dr. Antoun YAACOUB\n <\/a>\n <\/p>\n

\n Associate Professor at aivancity\n Director of the MSc Intelligences Artificielles G\u00e9n\u00e9ratives & Agentiques\n <\/p>\n <\/div>\n\n

\n

\n Zainab Assaghir\n <\/p>\n

\n Full Professor\n Faculty of Sciences, Lebanese University\n <\/p>\n <\/div>\n\n <\/div>\n<\/div>\n\n

\n

\n L<\/span>ibraries of educational prompts<\/strong>\n are multiplying, but they describe what we ask\n generative AI<\/strong> to produce, rarely the\n pedagogical function<\/strong> of that request.\n Our study proposes a\n taxonomy of five pedagogical functions of prompts<\/strong>\n and shows that it can be applied reliably by\n two raters<\/strong>. It also shows that it is\n difficult to infer, from the text of a prompt alone,\n the level of cognitive complexity\n it will engage.<\/strong>\n <\/p>\n<\/div>\n\n

Generative artificial intelligence is becoming embedded in educational practice, to the point that UNESCO and the OECD now devote recommendation frameworks to it (Miao and Holmes, 2023; OECD, 2026). Teachers use it to prepare lessons, design activities or produce course materials; students use it to get explanations, practice or receive feedback on their work. In all these uses, the interaction goes through a prompt, that is, the instruction written for a generative AI model.<\/p>\n\n

Behind this diversity of uses lies a more fundamental question: what does a prompt actually do pedagogically?<\/strong><\/p>\n\n

Does it simply ask the AI to produce an answer, does it guide the learner step by step, does it require them to argue a position, or does it lead them to evaluate their own reasoning?<\/p>\n\n

This is the question addressed by our study From Engineering to Pedagogy: A Functional Taxonomy for Teacher and Student-Facing Educational Prompting<\/em>, published in the proceedings of the EC-TEL 2026 conference (Yaacoub and Assaghir, 2027). In it, we propose classifying educational prompts not only according to the task they ask to be performed, but according to the pedagogical function they seek to fulfill<\/strong>.<\/p>\n\n

After calibration, two raters applying this classification to 50 unseen prompts achieve high agreement (88%, \u03ba = 0.80). However, the text of a prompt, taken in isolation, does not reliably reveal the level of cognitive complexity it will actually engage<\/strong>. The corpora, the coding scheme and the annotation workbook are available in open access on the OSF platform.<\/p>\n\n

\n\n
\n 01\n <\/div>\n\n

\nWhy look beyond \u201cprompt engineering\u201d?\n <\/h2>\n\n<\/div>\n\n

Libraries of educational prompts are growing rapidly. Recent literature reviews highlight the rise of large language models in education, the heterogeneity of prompt-writing practices and the lack of a shared analytical framework (Chen et al., 2024; Shi et al., 2026). These libraries are most often organized around the task to be performed: preparing a lesson, generating a quiz, creating an assessment rubric, explaining a concept.<\/p>\n\n

This organization is useful in practice, but it says little about the intended pedagogical mechanism and makes it difficult to compare prompts from one context to another.<\/p>\n\n

Two prompts that appear to request the same task can in fact organize the cognitive work very differently.<\/p>\n\n

One provides an answer directly; another guides the user step by step; a third asks them to justify their reasoning, consider a counterargument or evaluate their own work.<\/p>\n\n

The question is therefore no longer only what we ask the AI to produce<\/strong>, but how the prompt organizes the cognitive activity of the teacher or the learner<\/strong>.<\/p>\n\n

This distinction matters in education, where the quality of an interaction with AI depends not only on the quality of the generated response, but also on what the user is led to do themselves.<\/p>\n\n