An AI Agent for Democratizing Educational Policy Data
Resumo
Equitable educational public policies require accessible data, yet much remains locked in unstructured PDFs. This paper presents a conversational AI agent designed to democratize access to a 15,000-page educational policy corpus, prioritizing source traceability, semantic preservation of tabular data, and epistemic humility. Evaluations demonstrate reliability for public administration: a 91.3% expert accuracy rate (63/69 successful queries) and RAGAS baseline metrics for answer relevancy and context precision. Furthermore, the system fosters trust by explicitly abstaining when data is absent and proves robust against prompt injection and data poisoning attacks. These suggest its potential as an active analytical tool to support evidence-based policymaking.
Palavras-chave:
Retrieval-Augmented Generation, Educational Public Policy, Conversational AI Agent
Referências
Aleven, V., Baraniuk, R., Brunskill, E., Crossley, S., Demszky, D., Fancsali, S., Gupta, S., and Koedinger, K. (2023). Towards the future of ai-augmented human. In Artificial Intelligence in Education. Posters and Late Breaking Results, Workshops and Tutorials, Industry and Innovation Tracks, Practitioners, Doctoral Consortium and Blue Sky: 24th International Conference, AIED 2023, Tokyo, Japan, July 3–7, 2023, Proceedings, page 26. Springer Nature.
Asakura, T., Nguyen, H., Truong, N., Ly, N. T., Nguyen, C. T., Miyazawa, H., Tsuchida, Y., Yamamoto, T., Ito, M., Horie, T., et al. (2023). Digitalizing educational workbooks and collecting handwritten answers for automatic scoring. In iTextbooks@ AIED, pages 78–87.
Es, S., James, J., Anke, L. E., and Schockaert, S. (2024). Ragas: Automated evaluation of retrieval augmented generation. In Proceedings of the 18th conference of the european chapter of the association for computational linguistics: system demonstrations, pages 150–158.
Gao, M. (2025). A rag-enhanced large language model framework for intelligent college entrance recommendation. In Proceedings of the 2025 3rd International Conference on Information Education and Artificial Intelligence, pages 327–332.
Greshake, K., Abdelnabi, S., Mishra, S., Endres, C., Holz, T., and Fritz, M. (2023). Not what you've signed up for: Compromising real-world llm-integrated applications with indirect prompt injection. In Proceedings of the 16th ACM workshop on artificial intelligence and security, pages 79–90.
Kalra, R., Wu, Z., Gulley, A., Hilliard, A., Guan, X., Koshiyama, A., and Treleaven, P. C. (2024). Hypa-rag: A hybrid parameter adaptive retrieval-augmented generation system for ai legal and policy applications. In Proceedings of the 1st workshop on customizable nlp: Progress and challenges in customizing nlp for a domain, application, group, or individual (customnlp4u), pages 237–256.
Khosravi, H., Shum, S. B., Chen, G., Conati, C., Tsai, Y.-S., Kay, J., Knight, S., Martinez-Maldonado, R., Sadiq, S., and Gašević, D. (2022). Explainable artificial intelligence in education. Computers and Education: Artificial Intelligence, 3:100074.
Kibirige, K. S. and Wandabwa, J. (2025). Enhancing access to service delivery through information transparency: a rag-based ai-powered conversational chatbot for algorithmic transparency and regulatory compliance in digital governance. International Journal of Science and Engineering Applications, 14(9):59–75.
Mathur, S., Rittner, R. D., Thakur, V. A., Schiff, D. S., and Islam, T. (2026). Retrieval improvements do not guarantee better answers: A study of rag for ai policy qa. arXiv preprint arXiv:2603.24580.
Medeiros, R., Doarte, M., Viterbo, J., Maciel, C., and Boscarioli, C. (2021). Uma análise comparativa entre repositórios de recursos educacionais abertos para a educação básica. In Simpósio Brasileiro de Informática na Educação (SBIE), pages 213–224. SBC.
Mello, R. F., Freitas, E., Pereira, F. D., Cabral, L., Tedesco, P., and Ramalho, G. (2023). Education in the age of generative ai: Context and recent developments.
Nielsen, J. (1994). Usability engineering. Morgan Kaufmann.
Pan, F., Zhou, Q., Guo, W., and Yang, H. (2025). A survey on retrieval-augmented generation in applications of education and teaching. In 2025 7th International Conference on Computer Science and Technologies in Education (CSTE), pages 803–807. IEEE.
Pereira, F. D., Oliveira, E. H., Oliveira, D. B., Cristea, A. I., Carvalho, L. S., Fonseca, S. C., Toda, A., and Isotani, S. (2020). Using learning analytics in the amazonas: understanding students' behaviour in introductory programming. British journal of educational technology, 51(4):955–972.
Pinho, P. C., da Silva, R. Z., Primo, T. T., Dermeval, D., Bittencourt, I. I., and Isotani, S. (2025). Win-win situation: Generative ai in educational constrained environments. In Simpósio Brasileiro de Informática na Educação (SBIE), pages 1607–1616. SBC.
Pramanik, S. and Husin, M. H. B. (2025). The retrieval-augmented pedagogical assistant (rapa): A methodology for enhancing critical thinking and equity in ai-augmented education. INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 16(12):274–284.
Pujari, T., Pakina, A. K., and Goel, A. (2023). Explainable ai and governance: Enhancing transparency and policy frameworks through retrieval-augmented generation (rag). IOSR Journal of Computer Engineering.
Schiff, D. (2022). Education for ai, not ai for education: The role of education and ethics in national ai policy strategies. International Journal of Artificial Intelligence in Education, 32(3):527–563.
Wang, L., Yang, N., Huang, X., Yang, L., Majumder, R., and Wei, F. (2024). Multilingual e5 text embeddings: A technical report. arXiv preprint arXiv:2402.05672.
Asakura, T., Nguyen, H., Truong, N., Ly, N. T., Nguyen, C. T., Miyazawa, H., Tsuchida, Y., Yamamoto, T., Ito, M., Horie, T., et al. (2023). Digitalizing educational workbooks and collecting handwritten answers for automatic scoring. In iTextbooks@ AIED, pages 78–87.
Es, S., James, J., Anke, L. E., and Schockaert, S. (2024). Ragas: Automated evaluation of retrieval augmented generation. In Proceedings of the 18th conference of the european chapter of the association for computational linguistics: system demonstrations, pages 150–158.
Gao, M. (2025). A rag-enhanced large language model framework for intelligent college entrance recommendation. In Proceedings of the 2025 3rd International Conference on Information Education and Artificial Intelligence, pages 327–332.
Greshake, K., Abdelnabi, S., Mishra, S., Endres, C., Holz, T., and Fritz, M. (2023). Not what you've signed up for: Compromising real-world llm-integrated applications with indirect prompt injection. In Proceedings of the 16th ACM workshop on artificial intelligence and security, pages 79–90.
Kalra, R., Wu, Z., Gulley, A., Hilliard, A., Guan, X., Koshiyama, A., and Treleaven, P. C. (2024). Hypa-rag: A hybrid parameter adaptive retrieval-augmented generation system for ai legal and policy applications. In Proceedings of the 1st workshop on customizable nlp: Progress and challenges in customizing nlp for a domain, application, group, or individual (customnlp4u), pages 237–256.
Khosravi, H., Shum, S. B., Chen, G., Conati, C., Tsai, Y.-S., Kay, J., Knight, S., Martinez-Maldonado, R., Sadiq, S., and Gašević, D. (2022). Explainable artificial intelligence in education. Computers and Education: Artificial Intelligence, 3:100074.
Kibirige, K. S. and Wandabwa, J. (2025). Enhancing access to service delivery through information transparency: a rag-based ai-powered conversational chatbot for algorithmic transparency and regulatory compliance in digital governance. International Journal of Science and Engineering Applications, 14(9):59–75.
Mathur, S., Rittner, R. D., Thakur, V. A., Schiff, D. S., and Islam, T. (2026). Retrieval improvements do not guarantee better answers: A study of rag for ai policy qa. arXiv preprint arXiv:2603.24580.
Medeiros, R., Doarte, M., Viterbo, J., Maciel, C., and Boscarioli, C. (2021). Uma análise comparativa entre repositórios de recursos educacionais abertos para a educação básica. In Simpósio Brasileiro de Informática na Educação (SBIE), pages 213–224. SBC.
Mello, R. F., Freitas, E., Pereira, F. D., Cabral, L., Tedesco, P., and Ramalho, G. (2023). Education in the age of generative ai: Context and recent developments.
Nielsen, J. (1994). Usability engineering. Morgan Kaufmann.
Pan, F., Zhou, Q., Guo, W., and Yang, H. (2025). A survey on retrieval-augmented generation in applications of education and teaching. In 2025 7th International Conference on Computer Science and Technologies in Education (CSTE), pages 803–807. IEEE.
Pereira, F. D., Oliveira, E. H., Oliveira, D. B., Cristea, A. I., Carvalho, L. S., Fonseca, S. C., Toda, A., and Isotani, S. (2020). Using learning analytics in the amazonas: understanding students' behaviour in introductory programming. British journal of educational technology, 51(4):955–972.
Pinho, P. C., da Silva, R. Z., Primo, T. T., Dermeval, D., Bittencourt, I. I., and Isotani, S. (2025). Win-win situation: Generative ai in educational constrained environments. In Simpósio Brasileiro de Informática na Educação (SBIE), pages 1607–1616. SBC.
Pramanik, S. and Husin, M. H. B. (2025). The retrieval-augmented pedagogical assistant (rapa): A methodology for enhancing critical thinking and equity in ai-augmented education. INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 16(12):274–284.
Pujari, T., Pakina, A. K., and Goel, A. (2023). Explainable ai and governance: Enhancing transparency and policy frameworks through retrieval-augmented generation (rag). IOSR Journal of Computer Engineering.
Schiff, D. (2022). Education for ai, not ai for education: The role of education and ethics in national ai policy strategies. International Journal of Artificial Intelligence in Education, 32(3):527–563.
Wang, L., Yang, N., Huang, X., Yang, L., Majumder, R., and Wei, F. (2024). Multilingual e5 text embeddings: A technical report. arXiv preprint arXiv:2402.05672.
Publicado
05/10/2026
Como Citar
PEREIRA, Filipe Dwan et al.
An AI Agent for Democratizing Educational Policy Data. In: SIMPÓSIO BRASILEIRO DE INFORMÁTICA NA EDUCAÇÃO (SBIE), 37. , 2026, Goiânia/GO.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 716-729.
DOI: https://doi.org/10.5753/sbie.2026.27291.
