Authors : Kinkete Mfumabi Hervé; Lukoji Héritier; Bonzo Mampuya Gloire; Engwele Masamba Benedicte; Minsiensi Kiyanda Gloria; Mfingizi Nathan; Mpata Mbumba Shin-Eun; Mbuyi Mulumba Plamedi

Volume/Issue : Volume 11 - 2026, Issue 8 - August

Google Scholar : https://tinyurl.com/7cz2u5hh

DOI : https://doi.org/10.38124/ijisrt/26aug848

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Background: In the Democratic Republic of the Congo (DRC), access to digital public services is constrained by fragmented administrative information, uneven digital infrastructure, heterogeneous interfaces, and unequal access to reliable connectivity. Policy evidence indicates that universal digital access, digital public infrastructure, and digital skills remain foundations that require consolidation.  Objective: This study designs and instantiates GOVASSIST-RDC, a mediation architecture through which citizens can search by administrative need, receive answers accompanied by identifiable public sources, and reach a human channel when automation is insufficient.  Method: Following Design Science Research, the study connects documentary problem analysis, requirements engineering, architectural design, instantiation, and analytical demonstration. Evaluation is anchored in FEDS through artificial, predominantly formative episodes that inspect requirement coverage, architectural traceability, and visible component instantiation while excluding unmeasured effectiveness claims.  Results: The documented architecture integrates a RAG-oriented assistance layer together with a centralized service catalogue, intent-oriented retrieval, visible provenance, human escalation, content administration, and analytics. Four requirements are visibly instantiated, three remain specified or technically unverified, and one has mixed evidence. Seven design principles are derived: intent-based access, visible provenance, safe abstention, human–AI continuity, inclusion by design, non-substitutive interoperability, and governed traceability.  Contribution: The article defines administrative mediation as a non-adjudicative sociotechnical capability that translates citizenexpressed needs into discoverable services while preserving authority attribution, documentary inspectability, safe nonanswer, and human continuity. It contributes a documented prototype, a reference architecture, a formal model, seven derived design principles, boundary conditions, and testable propositions without conflating interface evidence with backend execution or public-service outcomes.

Keywords : Architecture; Artificial Intelligence; Democratic Republic of the Congo; Design Science Research; Digital Government; Digital Inclusion; Public Services; Retrieval-Augmented Generation.

References :

1. OECD, Recommendation of the Council on Digital Government Strategies, OECD/LEGAL/0406, 2014. [Online]. Available: https://legalinstruments.oecd.org/en/instruments/OECD-LEGAL-0406
2. OECD, The OECD Digital Government Policy Framework: Six Dimensions of a Digital Government. Paris, France: OECD Publishing, 2020, doi: 10.1787/f64fed2a-en.
3. United Nations, Department of Economic and Social Affairs, UN E-Government Survey 2024: Accelerating Digital Transformation for Sustainable Development. New York, NY, USA: United Nations, 2024.
4. World Bank, Democratic Republic of Congo Digital Transformation Project (P180495): Project Information Document. Washington, DC, USA: World Bank, 2023.
5. World Bank, “Digitalizing Eastern and Southern Africa: Democratic Republic of Congo Digital Transformation Project,” 2024. [Online]. Available: https://www.worldbank.org/en/region/afr/brief/afe-digital/overview
6. P. Lewis, E. Perez, A. Piktus, F. Petroni, V. Karpukhin, N. Goyal, et al., “Retrieval-augmented generation for knowledge-intensive NLP tasks,” in Advances in Neural Information Processing Systems, vol. 33, pp. 9459–9474, 2020.
7. S. Es, J. James, L. Espinosa-Anke, and S. Schockaert, “RAGAS: Automated evaluation of retrieval augmented generation,” in Proc. EACL 2024 System Demonstrations, pp. 150–158, 2024, doi: 10.18653/v1/2024.eacl-demo.16.
8. J. Saad-Falcon, O. Khattab, C. Potts, and M. Zaharia, “ARES: An automated evaluation framework for retrieval-augmented generation systems,” in Proc. NAACL-HLT, 2024, doi: 10.18653/v1/2024.naacl-long.20.
9. J. D. Twizeyimana and A. Andersson, “The public value of e-government—A literature review,” Government Information Quarterly, vol. 36, no. 2, pp. 167–178, 2019, doi: 10.1016/j.giq.2019.01.001.
10. A. Androutsopoulou, N. Karacapilidis, E. Loukis, and Y. Charalabidis, “Transforming the communication between citizens and government through AI-guided chatbots,” Government Information Quarterly, vol. 36, no. 2, pp. 358–367, 2019, doi: 10.1016/j.giq.2018.10.001.
11. N. Aoki, “An experimental study of public trust in AI chatbots in the public sector,” Government Information Quarterly, vol. 37, no. 4, Art. no. 101490, 2020, doi: 10.1016/j.giq.2020.101490.
12. A. G. Larsen and A. Følstad, “The impact of chatbots on public service provision,” Government Information Quarterly, vol. 41, no. 2, Art. no. 101927, 2024, doi: 10.1016/j.giq.2024.101927.
13. World Wide Web Consortium, Web Content Accessibility Guidelines (WCAG) 2.2, 2024. [Online]. Available: https://www.w3.org/TR/WCAG22/
14. L. Carter and F. Bélanger, “The utilization of e-government services: Citizen trust, innovation and acceptance factors,” Information Systems Journal, vol. 15, no. 1, pp. 5–25, 2005, doi: 10.1111/j.1365-2575.2005.00183.x.
15. W. H. DeLone and E. R. McLean, “The DeLone and McLean model of information systems success: A ten-year update,” Journal of Management Information Systems, vol. 19, no. 4, pp. 9–30, 2003, doi: 10.1080/07421222.2003.11045748.
16. M. E. Cortés-Cediel, A. Segura-Tinoco, I. Cantador, and M. P. Rodríguez Bolívar, “Trends and challenges of e-government chatbots,” Government Information Quarterly, vol. 40, no. 4, Art. no. 101877, 2023, doi: 10.1016/j.giq.2023.101877.
17. T. Papadopoulos, C. Alexopoulos, and Y. Charalabidis, “Evaluating chatbot architectures for public service delivery: Balancing functionality, safety, ethics, and adaptability,” Frontiers in Political Science, vol. 7, Art. no. 1601440, 2025, doi: 10.3389/fpos.2025.1601440.
18. S. Jiang, X. Xie, et al., “ARGUS: Retrieval-augmented QA system for government services,” Electronics, vol. 14, no. 12, Art. no. 2445, 2025, doi: 10.3390/electronics14122445.
19. S. Han and G. M. Jonathan, “The contextual edge: LLMs and Sweden’s public sector transformation,” in Electronic Government: EGOV 2025, LNCS 15944, pp. 180–195, 2025, doi: 10.1007/978-3-032-01589-1_12.
20. X. Xu, H. Weytjens, D. Zhang, Q. Lu, I. Weber, and L. Zhu, “RAGOps: Operating and managing retrieval-augmented generation pipelines,” arXiv:2506.03401, 2025, doi: 10.48550/arXiv.2506.03401.
21. A. Branco, L. Gomes, R. Santos, E. Santos, J. Silva, N. Marques, and M. Rodrigues, “Sovereign AI-based public services are viable and affordable,” arXiv:2603.01869, 2026, doi: 10.48550/arXiv.2603.01869.
22. V. van der Meer and J. Rossi, “LegalCheck: Retrieval- and context-augmented generation for drafting municipal legal advice letters,” arXiv:2605.12012, 2026, doi: 10.48550/arXiv.2605.12012.
23. T. L. C. da Silva, C. França, M. A. Gonçalves, L. Rocha, L. Alamy, F. S. Pereira, and E. S. de Paiva, “Bridging citizens and public services: Improving service association with retrieval-augmented generation labels,” in Proc. PROPOR 2026, vol. 1, pp. 131–140, 2026.
24. National Institute of Standards and Technology, Artificial Intelligence Risk Management Framework (AI RMF 1.0), NIST AI 100-1, 2023, doi: 10.6028/NIST.AI.100-1.
25. National Institute of Standards and Technology, Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile, NIST AI 600-1, 2024, doi: 10.6028/NIST.AI.600-1.
26. Open Worldwide Application Security Project, OWASP Top 10 for Large Language Model Applications 2025, 2025. [Online]. Available: https://genai.owasp.org/llm-top-10/
27. A. R. Hevner, S. T. March, J. Park, and S. Ram, “Design science in information systems research,” MIS Quarterly, vol. 28, no. 1, pp. 75–105, 2004, doi: 10.2307/25148625.
28. K. Peffers, T. Tuunanen, M. A. Rothenberger, and S. Chatterjee, “A design science research methodology for information systems research,” Journal of Management Information Systems, vol. 24, no. 3, pp. 45–77, 2007, doi: 10.2753/MIS0742-1222240302.
29. J. Venable, J. Pries-Heje, and R. Baskerville, “FEDS: A framework for evaluation in design science research,” European Journal of Information Systems, vol. 25, no. 1, pp. 77–89, 2016, doi: 10.1057/ejis.2014.36.
30. International Organization for Standardization, ISO 9241-11:2018—Ergonomics of Human-System Interaction—Part 11: Usability: Definitions and Concepts. Geneva, Switzerland: ISO, 2018.
31. Ministry of Foreign Affairs, International Cooperation and Francophonie, Democratic Republic of the Congo, “Passport biométrique,” Services, 2026. [Online]. Available: https://diplomatie.gouv.cd/services/
32. Ministry of Foreign Affairs, International Cooperation and Francophonie, Democratic Republic of the Congo, “Les réponses à toutes vos questions sur le nouveau passeport,” 2026. [Online]. Available: https://diplomatie.gouv.cd/foire-aux-questions/
33. Direction Générale de Migration, Democratic Republic of the Congo, “Site officiel de la Direction Générale de Migration,” 2026. [Online]. Available: https://dgm.cd/
34. Democratic Republic of the Congo, Ordonnance-loi no. 23/010 du 13 mars 2023 portant Code du numérique, Journal officiel de la République démocratique du Congo, 2023.