ArcAssist-Web Bot: A Prototype Instantiation for Evidence-Grounded Architectural Decision Support
Resumo
LLM-based bots can draft plausible software-architecture advice without exposing its evidence or readiness for human review. This paper presents ArcAssist-Web Bot, an early Web-system prototype for evidence-grounded architectural decision preparation. A user states an Evolution Concern; the implemented Flask/RAG path retrieves PDF/text architecture knowledge, constrains an external LLM request, and drafts review material. We map this path and its planned extensions to seven responsibilities: Interaction, Web-System and Domain Context, Context and Knowledge, Prompt Orchestration, LLM Reasoning, Validation and QA, and Knowledge Management. These responsibilities are an author-constructed organizing lens, not a validated taxonomy. A public-form scenario illustrates how domain boundaries, privacy, validation, and architectural knowledge enter a structured Decision Package before an external Architect Review gate. The artifact inspection supports technical feasibility of the implemented RAG path, not workflow effectiveness. The contribution is a concrete prototype instantiation, an explicit boundary between drafting and decision acceptance, and an evaluation agenda for traceability, usefulness, and review effort.
Palavras-chave:
Software Engineering Bots, Conversational Agents, Retrieval Augmented Generation, Architectural Decision Support
Referências
R. Dhar, K. Vaidhyanathan, and V. Varma. 2024. Leveraging Generative AI for Architecture Knowledge Management. In 2024 IEEE 21st International Conference on Software Architecture Companion (ICSA-C 2024). IEEE, Piscataway, NJ, USA, 163–166. DOI: 10.1109/ICSA-C63560.2024.00034
T. Eisenreich, S. Speth, and S. Wagner. 2024. From Requirements to Architecture: An AI-Based Journey to Semi-Automatically Generate Software Architectures. In Proceedings of the 1st International Workshop on Designing Software (Designing 2024). Association for Computing Machinery, New York, NY, USA, 52–55. DOI: 10.1145/3643660.3643942
L. Erlenhov, F. G. de Oliveira Neto, and P. Leitner. 2020. An Empirical Study of Bots in Software Development: Characteristics and Challenges from a Practitioner’s Perspective. In Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE 2020). Association for Computing Machinery, New York, NY, USA, 445–455. DOI: 10.1145/3368089.3409680
Y. Gao, Y. Xiong, X. Gao, K. Jia, J. Pan, Y. Bi, Y. Dai, J. Sun, M.Wang, and H.Wang. 2023. Retrieval-Augmented Generation for Large Language Models: A Survey. arXiv preprint arXiv:2312.10997. arXiv:2312.10997 [cs.CL] [link]
D. Garlan and M. Shaw. 1994. An Introduction to Software Architecture. Technical Report CMU/SEI-94-TR-021. Software Engineering Institute, Carnegie Mellon University. [link]
A. Jansen and J. Bosch. 2005. Software Architecture as a Set of Architectural Design Decisions. In Proceedings of the 5th Working IEEE/IFIP Conference on Software Architecture (WICSA 2005). IEEE, Piscataway, NJ, USA, 109–120. DOI: 10.1109/WICSA.2005.61
P. B. Kruchten. 1995. Architectural Blueprints: The “4+1” View Model of Software Architecture. IEEE Software 12, 6 (1995), 42–50. DOI: 10.1109/52.469759
P. Lewis, E. Perez, A. Piktus, F. Petroni, V. Karpukhin, N. Goyal, H. Küttler, M. Lewis, W. Yih, T. Rocktäschel, S. Riedel, and D. Kiela. 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In Advances in Neural Information Processing Systems (NeurIPS 2020, Vol. 33). Curran Associates, Inc., Red Hook, NY, USA, 9459–9474.
Q. Lu, L. Zhu, X. Xu, Z. Xing, S. Harrer, and J. Whittle. 2024. Towards Responsible Generative AI: A Reference Architecture for Designing Foundation Model Based Agents. In 2024 IEEE 21st International Conference on Software Architecture Companion (ICSA-C 2024). IEEE, Piscataway, NJ, USA, 119–126. DOI: 10.1109/ICSA-C63560.2024.00028
C. S. Machado, E. K. Viegas, S. M. Melo, and L. N. Paschoal. 2025. Do LLMs Support Generating Code that is Compliant with Creational Design Patterns?. In Anais do II Workshop sobre Bots na Engenharia de Software (WBOTS 2025). Sociedade Brasileira de Computação, Porto Alegre, RS, Brazil, 31–40. DOI: 10.5753/wbots.2025.15181
D. E. Perry and A. L. Wolf. 1992. Foundations for the Study of Software Architecture. ACM SIGSOFT Software Engineering Notes 17, 4 (1992), 40–52. DOI: 10.1145/141874.141884
B. M. Ribeiro, K. H. S. Souza, L. G. Silva, J. Villa, R. F. Vilela, P. H. D. Valle, and W. Silva. 2025. An Experience Report on User-Centered Chatbot Design through Design Thinking. In Anais do II Workshop sobre Bots na Engenharia de Software (WBOTS 2025). Sociedade Brasileira de Computação, Porto Alegre, RS, Brazil, 57–66. DOI: 10.5753/wbots.2025.15205
M. Rocha, P. Soares, L. Caldeira, P. Souza, R. F. Vilela, P. H. D. Valle, and W. Silva. 2025. Tecnologias de Avaliação da Experiência do Usuário (UX) em Chatbots: Um Mapeamento Sistemático da Literatura. In Anais do II Workshop sobre Bots na Engenharia de Software (WBOTS 2025). Sociedade Brasileira de Computação, Porto Alegre, RS, Brazil, 21–30. DOI: 10.5753/wbots.2025.15180
R. Rubei, A. Di Salle, and A. Bucaioni. 2025. LLM-Based Recommender Systems for Violation Resolutions in Continuous Architectural Conformance. In 2025 IEEE 22nd International Conference on Software Architecture Companion (ICSA-C 2025). IEEE, Piscataway, NJ, USA, 404–409. DOI: 10.1109/ICSA-C65153.2025.00063
E. Shihab, S. Wagner, M. A. Gerosa, M. Wessel, and J. Cabot. 2022. The Present and Future of Bots in Software Engineering. IEEE Software 39, 5 (2022), 28–31. DOI: 10.1109/MS.2022.3176864
C. H. C. da Silva, A. R. Cárdenas Maita, G. A. de Almeida Filho, C. V. M. da Silva, G. Dimant, R. A. Almeida, G. M. L. Costa, A. M. C. Araujo, B. C. D. S. Santana, E. A. Blay, and S. M. Peres. 2025. Evaluating LLM-Based Chatbots through Touchpoint-Driven Process Models. In Anais do II Workshop sobre Bots na Engenharia de Software (WBOTS 2025). Sociedade Brasileira de Computação, Porto Alegre, RS, Brazil, 1–10. DOI: 10.5753/wbots.2025.14148
C. V. M. da Silva, A. R. Cárdenas Maita, G. A. de Almeida Filho, C. H. C. da Silva, G. Dimant, R. A. Almeida, G. M. L. Costa, A. M. C. Araujo, B. C. D. S. Santana, E. A. Blay, and S. M. Peres. 2025. Template-Driven Specification of Requirements for LLM-Based Chatbots. In Anais do II Workshop sobre Bots na Engenharia de Software (WBOTS 2025). Sociedade Brasileira de Computação, Porto Alegre, RS, Brazil, 11–20. DOI: 10.5753/wbots.2025.14151
F. D. L. da Silva and T. A. Coleti. 2025. Middleware para Interceptação de Dados Sensíveis em Chatbots com Modelos de Linguagem de Grande Porte (LLMs). In Anais do II Workshop sobre Bots na Engenharia de Software (WBOTS 2025). Sociedade Brasileira de Computação, Porto Alegre, RS, Brazil, 41–46. DOI: 10.5753/wbots.2025.15215
M. Soliman and J. Keim. 2025. Do Large Language Models Contain Software Architectural Knowledge? An Exploratory Case Study with GPT. In 2025 IEEE 22nd International Conference on Software Architecture (ICSA 2025). IEEE, Piscataway, NJ, USA, 13–24. DOI: 10.1109/ICSA65012.2025.00012
R. F. Vilela, S. A. de Andrade, E. B. F. Santos,W. Silva, and P. H. D. Valle. 2025. An Intelligent Agent for Automated Test Generation from OpenAPI Specifications. In Anais do II Workshop sobre Bots na Engenharia de Software (WBOTS 2025). Sociedade Brasileira de Computação, Porto Alegre, RS, Brazil, 67–76. DOI: 10.5753/wbots.2025.15217
T. Eisenreich, S. Speth, and S. Wagner. 2024. From Requirements to Architecture: An AI-Based Journey to Semi-Automatically Generate Software Architectures. In Proceedings of the 1st International Workshop on Designing Software (Designing 2024). Association for Computing Machinery, New York, NY, USA, 52–55. DOI: 10.1145/3643660.3643942
L. Erlenhov, F. G. de Oliveira Neto, and P. Leitner. 2020. An Empirical Study of Bots in Software Development: Characteristics and Challenges from a Practitioner’s Perspective. In Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE 2020). Association for Computing Machinery, New York, NY, USA, 445–455. DOI: 10.1145/3368089.3409680
Y. Gao, Y. Xiong, X. Gao, K. Jia, J. Pan, Y. Bi, Y. Dai, J. Sun, M.Wang, and H.Wang. 2023. Retrieval-Augmented Generation for Large Language Models: A Survey. arXiv preprint arXiv:2312.10997. arXiv:2312.10997 [cs.CL] [link]
D. Garlan and M. Shaw. 1994. An Introduction to Software Architecture. Technical Report CMU/SEI-94-TR-021. Software Engineering Institute, Carnegie Mellon University. [link]
A. Jansen and J. Bosch. 2005. Software Architecture as a Set of Architectural Design Decisions. In Proceedings of the 5th Working IEEE/IFIP Conference on Software Architecture (WICSA 2005). IEEE, Piscataway, NJ, USA, 109–120. DOI: 10.1109/WICSA.2005.61
P. B. Kruchten. 1995. Architectural Blueprints: The “4+1” View Model of Software Architecture. IEEE Software 12, 6 (1995), 42–50. DOI: 10.1109/52.469759
P. Lewis, E. Perez, A. Piktus, F. Petroni, V. Karpukhin, N. Goyal, H. Küttler, M. Lewis, W. Yih, T. Rocktäschel, S. Riedel, and D. Kiela. 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In Advances in Neural Information Processing Systems (NeurIPS 2020, Vol. 33). Curran Associates, Inc., Red Hook, NY, USA, 9459–9474.
Q. Lu, L. Zhu, X. Xu, Z. Xing, S. Harrer, and J. Whittle. 2024. Towards Responsible Generative AI: A Reference Architecture for Designing Foundation Model Based Agents. In 2024 IEEE 21st International Conference on Software Architecture Companion (ICSA-C 2024). IEEE, Piscataway, NJ, USA, 119–126. DOI: 10.1109/ICSA-C63560.2024.00028
C. S. Machado, E. K. Viegas, S. M. Melo, and L. N. Paschoal. 2025. Do LLMs Support Generating Code that is Compliant with Creational Design Patterns?. In Anais do II Workshop sobre Bots na Engenharia de Software (WBOTS 2025). Sociedade Brasileira de Computação, Porto Alegre, RS, Brazil, 31–40. DOI: 10.5753/wbots.2025.15181
D. E. Perry and A. L. Wolf. 1992. Foundations for the Study of Software Architecture. ACM SIGSOFT Software Engineering Notes 17, 4 (1992), 40–52. DOI: 10.1145/141874.141884
B. M. Ribeiro, K. H. S. Souza, L. G. Silva, J. Villa, R. F. Vilela, P. H. D. Valle, and W. Silva. 2025. An Experience Report on User-Centered Chatbot Design through Design Thinking. In Anais do II Workshop sobre Bots na Engenharia de Software (WBOTS 2025). Sociedade Brasileira de Computação, Porto Alegre, RS, Brazil, 57–66. DOI: 10.5753/wbots.2025.15205
M. Rocha, P. Soares, L. Caldeira, P. Souza, R. F. Vilela, P. H. D. Valle, and W. Silva. 2025. Tecnologias de Avaliação da Experiência do Usuário (UX) em Chatbots: Um Mapeamento Sistemático da Literatura. In Anais do II Workshop sobre Bots na Engenharia de Software (WBOTS 2025). Sociedade Brasileira de Computação, Porto Alegre, RS, Brazil, 21–30. DOI: 10.5753/wbots.2025.15180
R. Rubei, A. Di Salle, and A. Bucaioni. 2025. LLM-Based Recommender Systems for Violation Resolutions in Continuous Architectural Conformance. In 2025 IEEE 22nd International Conference on Software Architecture Companion (ICSA-C 2025). IEEE, Piscataway, NJ, USA, 404–409. DOI: 10.1109/ICSA-C65153.2025.00063
E. Shihab, S. Wagner, M. A. Gerosa, M. Wessel, and J. Cabot. 2022. The Present and Future of Bots in Software Engineering. IEEE Software 39, 5 (2022), 28–31. DOI: 10.1109/MS.2022.3176864
C. H. C. da Silva, A. R. Cárdenas Maita, G. A. de Almeida Filho, C. V. M. da Silva, G. Dimant, R. A. Almeida, G. M. L. Costa, A. M. C. Araujo, B. C. D. S. Santana, E. A. Blay, and S. M. Peres. 2025. Evaluating LLM-Based Chatbots through Touchpoint-Driven Process Models. In Anais do II Workshop sobre Bots na Engenharia de Software (WBOTS 2025). Sociedade Brasileira de Computação, Porto Alegre, RS, Brazil, 1–10. DOI: 10.5753/wbots.2025.14148
C. V. M. da Silva, A. R. Cárdenas Maita, G. A. de Almeida Filho, C. H. C. da Silva, G. Dimant, R. A. Almeida, G. M. L. Costa, A. M. C. Araujo, B. C. D. S. Santana, E. A. Blay, and S. M. Peres. 2025. Template-Driven Specification of Requirements for LLM-Based Chatbots. In Anais do II Workshop sobre Bots na Engenharia de Software (WBOTS 2025). Sociedade Brasileira de Computação, Porto Alegre, RS, Brazil, 11–20. DOI: 10.5753/wbots.2025.14151
F. D. L. da Silva and T. A. Coleti. 2025. Middleware para Interceptação de Dados Sensíveis em Chatbots com Modelos de Linguagem de Grande Porte (LLMs). In Anais do II Workshop sobre Bots na Engenharia de Software (WBOTS 2025). Sociedade Brasileira de Computação, Porto Alegre, RS, Brazil, 41–46. DOI: 10.5753/wbots.2025.15215
M. Soliman and J. Keim. 2025. Do Large Language Models Contain Software Architectural Knowledge? An Exploratory Case Study with GPT. In 2025 IEEE 22nd International Conference on Software Architecture (ICSA 2025). IEEE, Piscataway, NJ, USA, 13–24. DOI: 10.1109/ICSA65012.2025.00012
R. F. Vilela, S. A. de Andrade, E. B. F. Santos,W. Silva, and P. H. D. Valle. 2025. An Intelligent Agent for Automated Test Generation from OpenAPI Specifications. In Anais do II Workshop sobre Bots na Engenharia de Software (WBOTS 2025). Sociedade Brasileira de Computação, Porto Alegre, RS, Brazil, 67–76. DOI: 10.5753/wbots.2025.15217
Publicado
11/09/2026
Como Citar
OLIVEIRA, Vanusa Rodrigues de; SIQUEIRA, Bento Rafael; SILVA, Samira Santos da.
ArcAssist-Web Bot: A Prototype Instantiation for Evidence-Grounded Architectural Decision Support. In: WORKSHOP SOBRE BOTS NA ENGENHARIA DE SOFTWARE (WBOTS), 3. , 2026, Cuiabá/MT.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 12-15.
DOI: https://doi.org/10.5753/wbots.2026.32932.
