From Bloom’s 2-Sigma to AI Tutoring: The UPDAIT Framework for Pedagogically Grounded Prompt Design

Corrado Petrucco

doi:10.3280/exioa1-2026oa23979

Rethinking the University in the Age of Artificial Intelligence a cura di Marina De Rossi, Ettore Bolisani, Carlo Mariconda

N. 1 (2026): Special Issue. Rethinking the University in the Age of Artificial Intelligence

From Bloom’s 2-Sigma to AI Tutoring: The UPDAIT Framework for Pedagogically Grounded Prompt Design

Corrado Petrucco^▸^▾

DOWNLOAD PDF (English)

DOI: https://doi.org/10.3280/exioa1-2026oa23979
Inviata: 12 ottobre 2026
Pubblicato: 04-11-2026

Abstract

Bloom’s 2-sigma problem demonstrated the effectiveness of one-to-one tutoring. Generative AI seems to solve its scalability, but without adequate pedagogical design an AI tutor can generate cognitive offloading and a gap between immediate performance and durable learning. The problem, then, is no longer personalized access to an AI tutor, but the pedagogical intentionality written into its configuration. UPDAIT (Università di Padova AI Tutor Generator) is a wizard that guides instructors in building customized tutors, with prompts grounded in pedagogical theories and in the instructor's own teaching strategies.

Riferimenti bibliografici

Aamir A., Munir S., Hafsa H., & Khalid W. (2026). Neural parasitism: Could adaptive artificial intelligence systems incrementally reconfigure human neural plasticity and challenge the foundations of cognitive autonomy?. Annals of Medicine and Surgery, 88(3): 2240-2244. Doi: 10.1097/MS9.0000000000004677.
Akhtar N., Mazhar U., Shehzadi N., Dildar H., Waseem M., & Zafar I. (2026). AI dependency and cognitive offloading: Effects of generative artificial intelligence on memory retention, critical thinking, and decision-making among university students. ACADEMIA International Journal for Social Sciences, 5(3, Suppl. 4): 159-177. Doi: 10.63056/academia.5.3(s4).2026.1921.
Anderson L. W., & Krathwohl D. R. (2001). A taxonomy for learning, teaching, and assessing. Longman.
Bastani H., Bastani O., Sungu A., Ge H., Kabakcı Ö., & Mariman R. (2024). Generative AI can harm learning (SSRN Scholarly Paper No. 4895486). Social Science Research Network. Doi: 10.2139/ssrn.4895486.
Bjork E. L., & Bjork R. A. (2011). Making things hard on yourself, but in a good way: Creating desirable difficulties to enhance learning. In: M. A. Gernsbacher, R. W. Pew, L. M. Hough, & J. R. Pomerantz (Eds.). Psychology and the real world: Essays illustrating fundamental contributions to society (pp. 56-64). Worth Publishers.
Bloom B. S. (1984). The 2 sigma problem: The search for methods of group instruction as effective as one-to-one tutoring. Educational Researcher, 13(6): 4-16. Doi: 10.3102/0013189X013006004.
Chen S., Molnar I., Hua T., Li P., Khiem L. H., Ambrose G. A., Lang J., Metoyer R., & Chawla N. V. (2025). Building scaffolding dialogue data with LLM-simulated novices [Preprint]. arXiv. Doi: 10.48550/arXiv.2508.04428.
Collins A., Brown J. S., & Newman S. E. (1989). Cognitive apprenticeship: Teaching the crafts of reading, writing, and mathematics. In: L. B. Resnick (Ed.). Knowing, learning, and instruction: Essays in honor of Robert Glaser (pp. 453-494). Lawrence Erlbaum Associates.
Córdova-Esparza D.-M. (2025). AI-powered educational agents: Opportunities, innovations, and ethical challenges. Information, 16(6), 469. Doi: 10.3390/info16060469.
Degen P., & Asanov I. (2025). Beyond automation: Socratic AI, epistemic agency, and the implications of the emergence of orchestrated multi-agent learning architectures [Preprint]. arXiv. Doi: 10.48550/arXiv.2508.05116.
Foschi L. C., & Petrucco C. (2026). Delegators or self-regulators? Exploring university students’ self-regulated learning with AI. Research Trends in Humanities Education & Philosophy, 13(1): 1-14. Doi: 10.6093/2284-0184/12914.
Hattie J., & Timperley H. (2007). The power of feedback. Review of Educational Research, 77(1): 81-112. Doi: 10.3102/003465430298487.
Hong H., Vate-U-Lan P., & Viriyavejakul C. (2025). Cognitive offload instruction with generative AI: A quasi-experimental study on critical thinking gains in English writing. Forum for Linguistic Studies, 7(7): 325-334. Doi: 10.30564/fls.v7i7.10072.
Jose B., Joseph D., Mohan V., Alexander E., Varghese S. K., & Roy A. (2025). Outsourcing cognition: The psychological costs of AI-era convenience. Frontiers in Psychology, 16, 1645237. Doi: 10.3389/fpsyg.2025.1645237.
Khosravi H., Gasevic D., Sadiq S., Yan L., & Baker R. S. (2026). Building AI companions that prioritise learning over performance [Preprint]. arXiv. Doi: 10.48550/arXiv.2605.04816.
Ma N., & Zhong Z. (2025). A meta-analysis of the impact of generative artificial intelligence on learning outcomes. Journal of Computer Assisted Learning, 41(5), e70117. Doi: 10.1111/jcal.70117.
Melanou C., & Beege M. (2026). Scaffolding generative AI as a tutor: A quasi-experimental study of learning outcomes and motivational, cognitive and metacognitive processes. Education Sciences, 16(4), 651. Doi: 10.3390/educsci16040651.
Rotter J., Benazet i Montobbio P., & Hernández-Leo D. (2026). Access timing as scaffolding: A reinforcement learning approach to GenAI in education [Preprint]. arXiv. Doi: 10.48550/arXiv.2605.15850.
Schell J., Ford K., & Markman A. B. (2025). Building responsible AI chatbot platforms in higher education: An evidence-based framework from design to implementation. Frontiers in Education, 10, 1604934. Doi: 10.3389/feduc.2025.1604934.
Tufino E., & Gregorcic B. (2025). Creating a customisable Socratic AI physics tutor. Physics Education, 60. Doi: 10.1088/1361-6552/ae0d23.
Wood D., Bruner J. S., & Ross G. (1976). The role of tutoring in problem solving. Journal of Child Psychology and Psychiatry, 17(2): 89-100. Doi: 10.1111/j.1469-7610.1976.tb00381.x.
Zhai C., Wibowo S., & Li L. D. (2024). The effects of over-reliance on AI dialogue systems on students’ cognitive abilities: A systematic review. Smart Learning Environments, 11(1), 28. Doi: 10.1186/s40561-024-00316-7.
Zilberman N. (2026). Generative AI in higher education: Conditions for supporting students’ metacognitive regulation. Open Education, 30(1): 15-22. Doi: 10.21686/1818-4243-2026-1-15-22.
Zimmerman B. J. (2000). Attaining self-regulation: A social cognitive perspective. In: M. Boekaerts, P. R. Pintrich, & M. Zeidner (Eds.). Handbook of self-regulation (pp. 13-39). Academic Press. Doi: 10.1016/B978-012109890-2/50031-7.

Parole chiave

AI tutoring
higher education
UPDAIT
pedagogical design
self-regulated learning

Come citare

Petrucco, C. (2026). From Bloom’s 2-Sigma to AI Tutoring: The UPDAIT Framework for Pedagogically Grounded Prompt Design. Excellence and Innovation in Learning and Teaching - Open Access, (1). https://doi.org/10.3280/exioa1-2026oa23979

Informativa sui diritti

[1] Aamir A., Munir S., Hafsa H., & Khalid W. (2026). Neural parasitism: Could adaptive artificial intelligence systems incrementally reconfigure human neural plasticity and challenge the foundations of cognitive autonomy?. Annals of Medicine and Surgery, 88(3): 2240-2244. Doi: 10.1097/MS9.0000000000004677.

[2] Akhtar N., Mazhar U., Shehzadi N., Dildar H., Waseem M., & Zafar I. (2026). AI dependency and cognitive offloading: Effects of generative artificial intelligence on memory retention, critical thinking, and decision-making among university students. ACADEMIA International Journal for Social Sciences, 5(3, Suppl. 4): 159-177. Doi: 10.63056/academia.5.3(s4).2026.1921.

[3] Anderson L. W., & Krathwohl D. R. (2001). A taxonomy for learning, teaching, and assessing. Longman.

[4] Bastani H., Bastani O., Sungu A., Ge H., Kabakcı Ö., & Mariman R. (2024). Generative AI can harm learning (SSRN Scholarly Paper No. 4895486). Social Science Research Network. Doi: 10.2139/ssrn.4895486.

[5] Bjork E. L., & Bjork R. A. (2011). Making things hard on yourself, but in a good way: Creating desirable difficulties to enhance learning. In: M. A. Gernsbacher, R. W. Pew, L. M. Hough, & J. R. Pomerantz (Eds.). Psychology and the real world: Essays illustrating fundamental contributions to society (pp. 56-64). Worth Publishers.

[6] Bloom B. S. (1984). The 2 sigma problem: The search for methods of group instruction as effective as one-to-one tutoring. Educational Researcher, 13(6): 4-16. Doi: 10.3102/0013189X013006004.

[7] Chen S., Molnar I., Hua T., Li P., Khiem L. H., Ambrose G. A., Lang J., Metoyer R., & Chawla N. V. (2025). Building scaffolding dialogue data with LLM-simulated novices [Preprint]. arXiv. Doi: 10.48550/arXiv.2508.04428.

[8] Collins A., Brown J. S., & Newman S. E. (1989). Cognitive apprenticeship: Teaching the crafts of reading, writing, and mathematics. In: L. B. Resnick (Ed.). Knowing, learning, and instruction: Essays in honor of Robert Glaser (pp. 453-494). Lawrence Erlbaum Associates.

[9] Córdova-Esparza D.-M. (2025). AI-powered educational agents: Opportunities, innovations, and ethical challenges. Information, 16(6), 469. Doi: 10.3390/info16060469.

[10] Degen P., & Asanov I. (2025). Beyond automation: Socratic AI, epistemic agency, and the implications of the emergence of orchestrated multi-agent learning architectures [Preprint]. arXiv. Doi: 10.48550/arXiv.2508.05116.

[11] Foschi L. C., & Petrucco C. (2026). Delegators or self-regulators? Exploring university students’ self-regulated learning with AI. Research Trends in Humanities Education & Philosophy, 13(1): 1-14. Doi: 10.6093/2284-0184/12914.

[12] Hattie J., & Timperley H. (2007). The power of feedback. Review of Educational Research, 77(1): 81-112. Doi: 10.3102/003465430298487.

[13] Hong H., Vate-U-Lan P., & Viriyavejakul C. (2025). Cognitive offload instruction with generative AI: A quasi-experimental study on critical thinking gains in English writing. Forum for Linguistic Studies, 7(7): 325-334. Doi: 10.30564/fls.v7i7.10072.

[14] Jose B., Joseph D., Mohan V., Alexander E., Varghese S. K., & Roy A. (2025). Outsourcing cognition: The psychological costs of AI-era convenience. Frontiers in Psychology, 16, 1645237. Doi: 10.3389/fpsyg.2025.1645237.

[15] Khosravi H., Gasevic D., Sadiq S., Yan L., & Baker R. S. (2026). Building AI companions that prioritise learning over performance [Preprint]. arXiv. Doi: 10.48550/arXiv.2605.04816.

[16] Ma N., & Zhong Z. (2025). A meta-analysis of the impact of generative artificial intelligence on learning outcomes. Journal of Computer Assisted Learning, 41(5), e70117. Doi: 10.1111/jcal.70117.

[17] Melanou C., & Beege M. (2026). Scaffolding generative AI as a tutor: A quasi-experimental study of learning outcomes and motivational, cognitive and metacognitive processes. Education Sciences, 16(4), 651. Doi: 10.3390/educsci16040651.

[18] Rotter J., Benazet i Montobbio P., & Hernández-Leo D. (2026). Access timing as scaffolding: A reinforcement learning approach to GenAI in education [Preprint]. arXiv. Doi: 10.48550/arXiv.2605.15850.

[19] Schell J., Ford K., & Markman A. B. (2025). Building responsible AI chatbot platforms in higher education: An evidence-based framework from design to implementation. Frontiers in Education, 10, 1604934. Doi: 10.3389/feduc.2025.1604934.

[20] Tufino E., & Gregorcic B. (2025). Creating a customisable Socratic AI physics tutor. Physics Education, 60. Doi: 10.1088/1361-6552/ae0d23.

[21] Wood D., Bruner J. S., & Ross G. (1976). The role of tutoring in problem solving. Journal of Child Psychology and Psychiatry, 17(2): 89-100. Doi: 10.1111/j.1469-7610.1976.tb00381.x.

[22] Zhai C., Wibowo S., & Li L. D. (2024). The effects of over-reliance on AI dialogue systems on students’ cognitive abilities: A systematic review. Smart Learning Environments, 11(1), 28. Doi: 10.1186/s40561-024-00316-7.

[23] Zilberman N. (2026). Generative AI in higher education: Conditions for supporting students’ metacognitive regulation. Open Education, 30(1): 15-22. Doi: 10.21686/1818-4243-2026-1-15-22.

[24] Zimmerman B. J. (2000). Attaining self-regulation: A social cognitive perspective. In: M. Boekaerts, P. R. Pintrich, & M. Zeidner (Eds.). Handbook of self-regulation (pp. 13-39). Academic Press. Doi: 10.1016/B978-012109890-2/50031-7.