PÉRO: a specialized RAG system for mobilizing knowledge on school retention and success
DOI:
https://doi.org/10.51657/v3tvrg25Keywords:
Generative AI, Retrieval-Augmented Generation (RAG) systems, knowledge mobilization, research network, academic perseverance, academic and school successAbstract
This article presents the iterative co-design of PÉRO, a conversational robot (chatbot) based on retrieval-augmented generation (RAG) and powered by a corpus of more than 8,000 publications from the PÉRISCOPE network on academic perseverance and success (PRS). The codesigners aimed to support educators' epistemic agency while providing reliable and relevant responses and ensuring the transparency, traceability, and verifiability of sources. An analysis of 416 user feedback responses indicates that 90.4% were deemed relevant or highly relevant. The analysis also points to the richness of the corpus relative to the questions asked, despite limitations in sustaining exchanges. Grounded in a specific and clearly delimited scientific corpus, PÉRO differs from both generic GenAI systems and conversational AI (cAI), which allows for more sustained exchanges. As an intervention instrument, PÉRO’s contribution remains to be documented. As a component of a research infrastructure, PÉRO offers a replicable and adaptable model that could support exchanges and the circulation of knowledge between researchers and practitioners.
References
Adlakha, V., BehnamGhader, P., Lu, X. H., Meade, N., & Reddy, S. (2024). Evaluating correctness and faithfulness of instruction-following models for question answering. arXiv. https://doi.org/10.48550/arXiv.2307.16877
Atf, Z., & Lewis, P. R. (2026). Is trust correlated with explainability in AI? A meta-analysis. IEEE Transactions on Technology and Society, 7(1), 70-77. https://doi.org/10.1109/TTS.2025.3558448
Braun, V., & Clarke, V. (2006). Using thematic analysis in psychology. Qualitative Research in Psychology, 3(2), 77-101. https://doi.org/10.1191/1478088706qp063oa
Braun, V., & Clarke, V. (2025). Reporting guidelines for qualitative research: A values-based approach. Qualitative Research in Psychology, 22(2), 399-438. https://doi.org/10.1080/14780887.2024.2382244
Dallaire, E. (2025). Practical RAG evaluation: A rarity-aware set-based metric and cost-latency-quality trade-offs. arXiv. https://doi.org/10.48550/arXiv.2511.09545
Damşa, C. I., Kirschner, P. A., Andriessen, J. E. B., Erkens, G., & Sins, P. H. M. (2010). Shared Epistemic Agency: An Empirical Study of an Emergent Construct. Journal of the Learning Sciences, 19(2), 143-186. https://doi.org/10.1080/10508401003708381
Es, S., James, J., Espinosa-Anke, L., & Schockaert, S. (2025). RAGAS: Automated evaluation of retrieval augmented generation. arXiv. https://doi.org/10.48550/arXiv.2309.15217
Engeström, Y. (1987/2015). Learning by expanding. Cambridge University Press.
Google (2024). NotebookLM: AI research tool & thinking partner. https://notebook.google
Hassenzahl, M., & Tractinsky, N. (2006). User experience – a research agenda. Behaviour & Information Technology, 25(2), 91–97. https://doi.org/10.1080/01449290500330331
Hong, H.-Y., & Sullivan, F. (2009). Towards an idea-centered, principle-based design approach to support learning as knowledge creation. Educational Technology Research and Development, 57(5), 613-627. https://10.1007/s11423-009-9122-0
Inria (2023, 13 novembre). Les quatre piliers de la recherche en IA pour l’éducation. https://www.inria.fr/fr/quatre-piliers-recherche-ia-education
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W., Rocktäschel, T., Riedel, S., & Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive NLP Tasks. arXiv. https://doi.org/10.48550/arXiv.2005.11401
Li, Z., Wang, Z., Wang, W., Hung, K., Xie, H., & Wang, F. L. (2025). Retrieval-augmented generation for educational application: A systematic survey. Computers and Education: Artificial Intelligence, 8, Article 100417. https://doi.org/10.1016/j.caeai.2025.100417
Marin, L. (2022). How to do things with information online. A conceptual framework for evaluating social networking platforms as epistemic environments. Philosophy & Technology, 35(3), Article 77. https://doi.org/10.1007/s13347-022-00569-5
Mohamed, A., Abdelqader, K., & Shaalan, K. (2025). Explainable artificial intelligence: A systematic review of progress and challenges. Intelligent Systems with Applications, 28, Article 200595 https://doi.org/10.1016/j.iswa.2025.200595
Nouali, S., Badache, I. et Bellot, P. (2025). Exploration du RAG pour la génération de réponses à des questions en contexte éducatif : étude sur les données SCIQ. Dans Actes de l’atelier Intelligence Artificielle générative et ÉDUcation : Enjeux, Défis et Perspectives de Recherche 2025 (IA-ÉDU) (pp. 29-41). Marseille. https://aclanthology.org/2025.jeptalnrecital-iaedu.5/
PÉRISCOPE (s.d.). Le réseau. https://periscope-r.quebec
Rogoff, B. (2014). Learning by observing and pitching in to family and community endeavors: An orientation. Human Development, 57(2/3), 69-81. https://www.jstor.org/stable/26764709
Reigeluth, C. M. (Ed.). (1983). Instructional-design theories and models: An overview of their current status. Lawrence Erlbaum Associates. https://doi.org/10.4324/9780203824283
Scardamalia, M. (2002). Collective cognitive responsibility for the advancement of knowledge. In B. Smith (Ed.), Liberal education in a knowledge society (pp. 67-98). Open Court.
Shahrzadi, L., Mansouri, A., Alavi, M., & Shabani, A. (2024). Causes, consequences, and strategies to deal with information overload: A scoping review. International Journal of Information Management Data Insights, 4(2), Article 10026. https://doi.org/10.1016/j.jjimei.2024.100261
Silva, M., & Breuleux, A. (1994). The use of participatory design in the implementation of internet-based collaborative learning activities in K–12 classrooms. Interpersonal Computing and Technology, 2(3), 99–128.
Sultan, N. (2019). Heuristic inquiry: Researching human experience holistically. SAGE Publications, Inc. https://doi.org/10.4135/9781071802632
Tufino, E. (2025). NotebookLM as a Socratic physics tutor: Design and preliminary observations of a RAG-based tool. arXiv. https://doi.org/10.48550/arXiv.2504.09720
Tyndall, E., Gayheart, C., Some, A., Genz, J., Wagner, T., & Langhals, B. (2025). Impact of retrieval augmented generation and large language model complexity on undergraduate exams created and taken by AI agents. Data & Policy, 7, e57. https://doi.org/10.1017/dap.2025.10024
Vygotsky, L. S. (1978). Mind in society. The development of higher psychological processes. Harvard University Press.
Zhang, J., Tian, Y., Yuan, G., & Tao, D. (2022). Epistemic agency for costructuring expansive knowledge‐building practices. Science Education, 106(4), 890–923.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Amira Zguira, Linda St-Pierre, Thérèse Laferrière
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.