Improving Agentic AI Opportunity Identification Through GORE Driven Prompt Engineering
Resumo
Agentic AI has emerged as a promising strategy for modernizing legacy software systems; however, systematic approaches for identifying Agentic AI implementation opportunities from existing requirements documentation remain largely unexplored. This paper presents a small-scale industrial study that investigates whether the i* framework can be used as an intermediate Prompt Engineering artifact to improve the identification of Agentic AI opportunities in legacy enterprise systems. The study analyzes the requirements specification of an ERP-based maritime logistics solution supporting fiscal document processing, commercial operations, data migration, system integration, and regulatory compliance activities. Two prompt-based approaches were compared: (i) direct analysis of requirements documentation and (ii) a two-step process using Strategic Dependency and Strategic Rationale models derived from i*. Results indicate that the use of i* did not increase the number or coverage of identified opportunities. However, it produced a more specialized and organizationally aligned multi-agent architecture, improving the connection between proposed agents, organizational objectives, business dependencies, and quality concerns. The findings suggest that i* can serve as an effective intermediary artifact for Prompt Engineering, enabling richer architectural reasoning and providing stronger organizational grounding for Agentic AI solutions in software modernization initiatives.
Palavras-chave:
Requirements Engineering, Agentic AI
Referências
Sallam Abualhaija, Marcello Ceci, Nicolas Sannier, Domenico Bianculli, Salomé Lannier, Martina Siclari, Olivier Voordeckers, and Stanisław Tosza. 2025. LLM-assisted Extraction of Regulatory Requirements: A Case Study on the GDPR. In 2025 IEEE 33rd International Requirements Engineering Conference (RE). IEEE, Valencia, Spain, 142–154. DOI: 10.1109/RE63999.2025.00023
Deepak Bhaskar Acharya, Karthigeyan Kuppan, and B. Divya. 2025. Agentic AI: Autonomous Intelligence for Complex Goals—A Comprehensive Survey. IEEE Access 13 (2025), 18912–18936. DOI: 10.1109/ACCESS.2025.3532853
Khlood Ahmad, Mohamed Abdelrazek, Chetan Arora, Muneera Bano, and John Grundy. 2023. Requirements engineering for artificial intelligence systems: A systematic mapping study. Information and Software Technology 158 (June 2023), 107176. DOI: 10.1016/j.infsof.2023.107176
Nour Ali, Sean Baker, Ross O’Crowley, Sebastian Herold, and Jim Buckley. 2018. Architecture consistency: State of the practice, challenges and requirements. Empir Software Eng 23, 1 (Feb. 2018), 224–258. DOI: 10.1007/s10664-017-9515-3
Wesley K. G. Assunção, Luciano Marchezan, Lawrence Arkoh, Alexander Egyed, and Rudolf Ramler. 2025. Contemporary Software Modernization: Strategies, Driving Forces, and Research Opportunities. ACM Trans. Softw. Eng. Methodol. 34, 5 (June 2025), 1–35. DOI: 10.1145/3708527
AWS. 2026. Agentic AI patterns and workflows on AWS - AWS Prescriptive Guidance. Retrieved 2026-07-10 from [link]
Beatriz Braga Batista, Márcia Sampaio Lima, and Tayana Uchôa Conte. 2024. Teaching Requirements Engineering for AI: A Goal-Oriented Approach in Software Engineering Courses. In Proceedings of the XXIII Brazilian Symposium on Software Quality. ACM, Salvador Bahia Brazil, 613–623. DOI: 10.1145/3701625.3701686
Kent Beck. 2003. Extreme Programming explained: embrace Change (9. print ed.). Addison Wesley, Boston, Mass. Munich.
Paolo Bresciani, Anna Perini, Paolo Giorgini, Fausto Giunchiglia, and John Mylopoulos. 2004. Tropos: An Agent-Oriented Software Development Methodology. Autonomous Agents and Multi-Agent Systems 8, 3 (May 2004), 203–236. DOI: 10.1023/B:AGNT.0000018806.20944.ef
Hayala Nepomuceno Curto. 2025. Building Software Functional Requirements Lists Using RAG with Distinct LLMs in Multiple Interactions. In 2025 IEEE 33rd International Requirements Engineering Conference (RE). IEEE, Valencia, Spain, 612–616. DOI: 10.1109/RE63999.2025.00077
Anne Dardenne, Axel Van Lamsweerde, and Stephen Fickas. 1993. Goal-directed requirements acquisition. Science of Computer Programming 20, 1-2 (April 1993), 3–50. DOI: 10.1016/0167-6423(93)90021-G
Matteo Esposito, Xiaozhou Li, Sergio Moreschini, Noman Ahmad, Tomas Cerny, Karthik Vaidhyanathan, Valentina Lenarduzzi, and Davide Taibi. 2026. Generative AI for software architecture. Applications, challenges, and future directions. Journal of Systems and Software 231 (Jan. 2026), 112607. DOI: 10.1016/j.jss.2025.112607
E. Hudlicka. 1996. Requirements elicitation with indirect knowledge elicitation techniques: comparison of three methods. In Proceedings of the Second International Conference on Requirements Engineering. IEEE Comput. Soc. Press, Colorado Springs, CO, USA, 4–11. DOI: 10.1109/ICRE.1996.491424
Philippe Kruchten. 2007. The rational unified process: an introduction (3. ed., 7. printing ed.). Addison-Wesley, Upper Saddler River, NJ.
Makoto Nakayama, Eli Hustad, and Norma Sutcliffe. 2021. Agility and system documentation in large-scale enterprise system projects: a knowledge management perspective. Procedia Computer Science 181 (2021), 386–393. DOI: 10.1016/j.procs.2021.01.181
Dan North. 2006. Introducing BDD. Retrieved 2026-07-10 from [link]
Tayiba Raheem and Gahangir Hossain. 2025. Agentic AI Systems: Opportunities, Challenges, and Trustworthiness. In 2025 IEEE International Conference on Electro Information Technology (eIT). IEEE, Valparaiso, IN, USA, 618–624. DOI: 10.1109/eIT64391.2025.11103638
Krishna Ronanki, Simon Arvidsson, and Johan Axell. 2026. Prompt Engineering Guidelines for Using Large Language Models in Requirements Engineering. In Software Engineering and Advanced Applications, Davide Taibi and Darja Smite (Eds.). Vol. 16083. Springer Nature Switzerland, Cham, 245–262. DOI: 10.1007/978-3-032-04207-1_17, Series Title: Lecture Notes in Computer Science.
Siar Sarferaz. 2025. Implementing Agentic AI Into ERP Software. IEEE Access 13 (2025), 178945–178960. DOI: 10.1109/ACCESS.2025.3621887
Robert C. Seacord, Daniel Plakosh, and Grace A. Lewis. 2003. Modernizing legacy systems: software technologies, engineering processes, and business practices. Addison-Wesley, Boston Munich.
A. Stone and P. Sawyer. 2006. Identifying tacit knowledge-based requirements. IEE Proc., Softw. 153, 6 (2006), 211. DOI: 10.1049/ip-sen:20060034
IrdinaWanda Syahputri, Eko K. Budiardjo, and Panca O. Hadi Putra. 2025. Unlocking the Potential of the Prompt Engineering Paradigm in Software Engineering: A Systematic Literature Review. AI 6, 9 (Aug. 2025), 206. DOI: 10.3390/ai6090206
Damian A. Tamburri and Rick Kazman. 2018. General methods for software architecture recovery: a potential approach and its evaluation. Empir Software Eng 23, 3 (June 2018), 1457–1489. DOI: 10.1007/s10664-017-9543-z
Burak Uzun and Bedir Tekinerdogan. 2024. Detecting deviations in the code using architecture view-based drift analysis. Computer Standards & Interfaces 87 (Jan. 2024), 103774. DOI: 10.1016/j.csi.2023.103774
Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, and Denny Zhou. 2022. Rationale-Augmented Ensembles in Language Models. DOI: 10.48550/ARXIV.2207.00747, Version Number: 1.
Claes Wohlin and Austen Rainer. 2022. Is it a case study?—A critical analysis and guidance. Journal of Systems and Software 192 (Oct. 2022), 111395. DOI: 10.1016/j.jss.2022.111395
Michael Wooldridge. 2009. An introduction to multiagent systems. John wiley & sons.
Bin Xu. 2026. AI Agent Systems: Architectures, Applications, and Evaluation. arXiv:2601.01743 DOI: 10.48550/ARXIV.2601.01743
Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of Thoughts: Deliberate Problem Solving with Large Language Models. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko,M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 11809–11822. [link]
E.S.K. Yu. 1997. Towards modelling and reasoning support for early-phase requirements engineering. In Proceedings of ISRE ’97: 3rd IEEE International Symposium on Requirements Engineering. IEEE Comput. Soc. Press, Annapolis, MD, USA, 226–235. DOI: 10.1109/ISRE.1997.566873
Eric Yu. 2024. Agent-Oriented Modeling for the Age of AI: Nine Pivots Toward a Reconceptualization of Requirements Engineering. In Social Modeling Using the i* Framework, Xavier Franch, Julio Cesar Sampaio Do Prado Leite, Gunter Mussbacher, John Mylopoulos, and Anna Perini (Eds.). Springer Nature Switzerland, Cham, 207–227. DOI: 10.1007/978-3-031-72107-6_13
Eric S. K. Yu (Ed.). 2011. Social modeling for requirements engineering. MIT Press, Cambridge, Mass.
Deepak Bhaskar Acharya, Karthigeyan Kuppan, and B. Divya. 2025. Agentic AI: Autonomous Intelligence for Complex Goals—A Comprehensive Survey. IEEE Access 13 (2025), 18912–18936. DOI: 10.1109/ACCESS.2025.3532853
Khlood Ahmad, Mohamed Abdelrazek, Chetan Arora, Muneera Bano, and John Grundy. 2023. Requirements engineering for artificial intelligence systems: A systematic mapping study. Information and Software Technology 158 (June 2023), 107176. DOI: 10.1016/j.infsof.2023.107176
Nour Ali, Sean Baker, Ross O’Crowley, Sebastian Herold, and Jim Buckley. 2018. Architecture consistency: State of the practice, challenges and requirements. Empir Software Eng 23, 1 (Feb. 2018), 224–258. DOI: 10.1007/s10664-017-9515-3
Wesley K. G. Assunção, Luciano Marchezan, Lawrence Arkoh, Alexander Egyed, and Rudolf Ramler. 2025. Contemporary Software Modernization: Strategies, Driving Forces, and Research Opportunities. ACM Trans. Softw. Eng. Methodol. 34, 5 (June 2025), 1–35. DOI: 10.1145/3708527
AWS. 2026. Agentic AI patterns and workflows on AWS - AWS Prescriptive Guidance. Retrieved 2026-07-10 from [link]
Beatriz Braga Batista, Márcia Sampaio Lima, and Tayana Uchôa Conte. 2024. Teaching Requirements Engineering for AI: A Goal-Oriented Approach in Software Engineering Courses. In Proceedings of the XXIII Brazilian Symposium on Software Quality. ACM, Salvador Bahia Brazil, 613–623. DOI: 10.1145/3701625.3701686
Kent Beck. 2003. Extreme Programming explained: embrace Change (9. print ed.). Addison Wesley, Boston, Mass. Munich.
Paolo Bresciani, Anna Perini, Paolo Giorgini, Fausto Giunchiglia, and John Mylopoulos. 2004. Tropos: An Agent-Oriented Software Development Methodology. Autonomous Agents and Multi-Agent Systems 8, 3 (May 2004), 203–236. DOI: 10.1023/B:AGNT.0000018806.20944.ef
Hayala Nepomuceno Curto. 2025. Building Software Functional Requirements Lists Using RAG with Distinct LLMs in Multiple Interactions. In 2025 IEEE 33rd International Requirements Engineering Conference (RE). IEEE, Valencia, Spain, 612–616. DOI: 10.1109/RE63999.2025.00077
Anne Dardenne, Axel Van Lamsweerde, and Stephen Fickas. 1993. Goal-directed requirements acquisition. Science of Computer Programming 20, 1-2 (April 1993), 3–50. DOI: 10.1016/0167-6423(93)90021-G
Matteo Esposito, Xiaozhou Li, Sergio Moreschini, Noman Ahmad, Tomas Cerny, Karthik Vaidhyanathan, Valentina Lenarduzzi, and Davide Taibi. 2026. Generative AI for software architecture. Applications, challenges, and future directions. Journal of Systems and Software 231 (Jan. 2026), 112607. DOI: 10.1016/j.jss.2025.112607
E. Hudlicka. 1996. Requirements elicitation with indirect knowledge elicitation techniques: comparison of three methods. In Proceedings of the Second International Conference on Requirements Engineering. IEEE Comput. Soc. Press, Colorado Springs, CO, USA, 4–11. DOI: 10.1109/ICRE.1996.491424
Philippe Kruchten. 2007. The rational unified process: an introduction (3. ed., 7. printing ed.). Addison-Wesley, Upper Saddler River, NJ.
Makoto Nakayama, Eli Hustad, and Norma Sutcliffe. 2021. Agility and system documentation in large-scale enterprise system projects: a knowledge management perspective. Procedia Computer Science 181 (2021), 386–393. DOI: 10.1016/j.procs.2021.01.181
Dan North. 2006. Introducing BDD. Retrieved 2026-07-10 from [link]
Tayiba Raheem and Gahangir Hossain. 2025. Agentic AI Systems: Opportunities, Challenges, and Trustworthiness. In 2025 IEEE International Conference on Electro Information Technology (eIT). IEEE, Valparaiso, IN, USA, 618–624. DOI: 10.1109/eIT64391.2025.11103638
Krishna Ronanki, Simon Arvidsson, and Johan Axell. 2026. Prompt Engineering Guidelines for Using Large Language Models in Requirements Engineering. In Software Engineering and Advanced Applications, Davide Taibi and Darja Smite (Eds.). Vol. 16083. Springer Nature Switzerland, Cham, 245–262. DOI: 10.1007/978-3-032-04207-1_17, Series Title: Lecture Notes in Computer Science.
Siar Sarferaz. 2025. Implementing Agentic AI Into ERP Software. IEEE Access 13 (2025), 178945–178960. DOI: 10.1109/ACCESS.2025.3621887
Robert C. Seacord, Daniel Plakosh, and Grace A. Lewis. 2003. Modernizing legacy systems: software technologies, engineering processes, and business practices. Addison-Wesley, Boston Munich.
A. Stone and P. Sawyer. 2006. Identifying tacit knowledge-based requirements. IEE Proc., Softw. 153, 6 (2006), 211. DOI: 10.1049/ip-sen:20060034
IrdinaWanda Syahputri, Eko K. Budiardjo, and Panca O. Hadi Putra. 2025. Unlocking the Potential of the Prompt Engineering Paradigm in Software Engineering: A Systematic Literature Review. AI 6, 9 (Aug. 2025), 206. DOI: 10.3390/ai6090206
Damian A. Tamburri and Rick Kazman. 2018. General methods for software architecture recovery: a potential approach and its evaluation. Empir Software Eng 23, 3 (June 2018), 1457–1489. DOI: 10.1007/s10664-017-9543-z
Burak Uzun and Bedir Tekinerdogan. 2024. Detecting deviations in the code using architecture view-based drift analysis. Computer Standards & Interfaces 87 (Jan. 2024), 103774. DOI: 10.1016/j.csi.2023.103774
Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, and Denny Zhou. 2022. Rationale-Augmented Ensembles in Language Models. DOI: 10.48550/ARXIV.2207.00747, Version Number: 1.
Claes Wohlin and Austen Rainer. 2022. Is it a case study?—A critical analysis and guidance. Journal of Systems and Software 192 (Oct. 2022), 111395. DOI: 10.1016/j.jss.2022.111395
Michael Wooldridge. 2009. An introduction to multiagent systems. John wiley & sons.
Bin Xu. 2026. AI Agent Systems: Architectures, Applications, and Evaluation. arXiv:2601.01743 DOI: 10.48550/ARXIV.2601.01743
Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of Thoughts: Deliberate Problem Solving with Large Language Models. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko,M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 11809–11822. [link]
E.S.K. Yu. 1997. Towards modelling and reasoning support for early-phase requirements engineering. In Proceedings of ISRE ’97: 3rd IEEE International Symposium on Requirements Engineering. IEEE Comput. Soc. Press, Annapolis, MD, USA, 226–235. DOI: 10.1109/ISRE.1997.566873
Eric Yu. 2024. Agent-Oriented Modeling for the Age of AI: Nine Pivots Toward a Reconceptualization of Requirements Engineering. In Social Modeling Using the i* Framework, Xavier Franch, Julio Cesar Sampaio Do Prado Leite, Gunter Mussbacher, John Mylopoulos, and Anna Perini (Eds.). Springer Nature Switzerland, Cham, 207–227. DOI: 10.1007/978-3-031-72107-6_13
Eric S. K. Yu (Ed.). 2011. Social modeling for requirements engineering. MIT Press, Cambridge, Mass.
Publicado
08/09/2026
Como Citar
MORAES, Edson Andrade de; KALINOWSKI, Marcos.
Improving Agentic AI Opportunity Identification Through GORE Driven Prompt Engineering. In: WORKSHOP EM ENGENHARIA DE SOFTWARE PARA SISTEMAS AGÊNTICOS (SE4AS), 1. , 2026, São Paulo/SP.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 1-6.
DOI: https://doi.org/10.5753/se4as.2026.32414.
