Engenharia de Prompt na Geração de Interfaces a partir de Protótipos Visuais: uma Avaliação Empírica em IDE Agêntica
Resumo
A geração de código assistida por Large Language Models (LLMs) em ambientes de desenvolvimento agênticos tem deslocado o esforço humano da escrita literal de código para a formulação de instruções em linguagem natural, consolidando a Engenharia de Prompt (EP) como disciplina central para orientar modelos generativos. Este trabalho compara empiricamente cinco técnicas de EP (zero-shot, role prompting, structured prompting, Chain-of-Thought e combined prompting) na geração de interfaces React a partir de protótipos visuais de alta fidelidade do Figma, no Cursor, IDE agêntica integrada ao modelo Claude Sonnet 4.6. Em três execuções por técnica, seis métricas de esforço de geração (tempo, intervenções humanas, contexto consumido, linhas de código, tokens e prompts adicionais) foram combinadas à avaliação de três desenvolvedores sobre fidelidade visual, layout, funcionalidade, completude, consistência e erros visuais. Os resultados indicam uma tensão estrutural entre a autonomia do agente e a aderência ao protótipo: o role prompting obteve a maior qualidade média (4,00) ao custo do maior esforço humano do conjunto, enquanto o combined prompting emergiu como a abordagem de melhor equilíbrio, com o menor score de esforço (0,05) e qualidade competitiva (3,71), sendo a única a concluir as execuções representativas sem correção adicional. A complexidade da tela amplifica essas diferenças, com prompts mais elaborados levando vantagem em interfaces estruturalmente mais complexas, resultado com implicações diretas sobre o esforço corretivo exigido quando essas interfaces entram em manutenção.
Palavras-chave:
Engenharia de Prompt, Modelos de Linguagem de Grande Escala, Geração de Interfaces, IDEs Agênticas, Prototipação de Interfaces
Referências
ANTHROPIC. 2026. Claude Sonnet 4.6 System Card. [link]. Acesso em: 10 ago. 2026.
Berk Atıl, Sarp Aykent, Alexa Chittams, Lisheng Fu, Rebecca J. Passonneau, Evan Radcliffe, Guru Rajan Rajagopal, Adam Sloan, Tomasz Tudrej, Ferhan Ture, Zhe Wu, Lixinyu Xu, and Breck Baldwin. 2025. Non-Determinism of “Deterministic” LLM System Settings in Hosted Environments. In Proceedings of the 5th Workshop on Evaluation and Comparison of NLP Systems, Mousumi Akter, Tahiya Chowdhury, Steffen Eger, Christoph Leiter, Juri Opitz, and Erion Çano (Eds.). Association for Computational Linguistics, Association for Computational Linguistics, Mumbai, India, 135–148. DOI: 10.18653/v1/2025.eval4nlp-1.12
Tom B. Brown, Benjamin Mann, Nick Ryder, et al. 2020. Language models are few-shot learners (NIPS ’20). Neural Information Processing Systems Foundation, Curran Associates Inc., Red Hook, NY, USA, Article 159, 25 pages.
Federico Cassano, John Gouwar, Francesca Lucchetti, Claire Schlesinger, Anders Freeman, Carolyn Jane Anderson, Molly Q. Feldman,Michael Greenberg, Abhinav Jangda, and Arjun Guha. 2024. Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMs. Proc. ACM Program. Lang. 8, OOPSLA2, Article 338 (Oct. 2024), 28 pages. DOI: 10.1145/3689735
Mark Chen, Jerry Tworek, Heewoo Jun, et al. 2021. Evaluating Large Language Models Trained on Code. arXiv:2107.03374 [cs.LG] DOI: 10.48550/arXiv.2107.03374
Rogelio Cruz, Jonatan Contreras, Francisco Guerrero, Ezequiel Rodriguez, Carlos Valdez, and Citlali Carrillo. 2025. Prompt engineering and framework. arXiv:2506.10989 [cs.SE] DOI: 10.48550/arXiv.2506.10989
Roy Derks. 2022. React Projects. Packt Publishing.
Matthias Galster, Seyedmoein Mohsenimofidi, Jai Lal Lulla, Muhammad Auwal Abubakar, Christoph Treude, and Sebastian Baltes. 2026. Configuring Agentic AI Coding Tools. arXiv:2602.14690 [cs.SE] [link]
Kosei Horikawa, Hao Li, Yutaro Kashiwa, Bram Adams, Hajimu Iida, andAhmed E. Hassan. 2025. Agentic Refactoring. arXiv:2511.04824 [cs.SE] DOI: 10.48550/arXiv.2511.04824
E. G. Santana Jr, Gabriel Benjamin, Melissa Araujo, Harrison Santos, David Freitas, Eduardo Almeida, Paulo Anselmo da M. S. Neto, Jiawei Li, Jina Chun, and Iftekhar Ahmed. 2025. Which Prompting Technique Should I Use? An Empirical Investigation of Prompting Techniques for Software Engineering Tasks. arXiv:2506.05614 [cs.SE] [link]
Kristian Kolthoff, Felix Kretzer, Christian Bartelt, Alexander Maedche, and Simone Paolo Ponzetto. 2025. GUIDE. 4 pages. DOI: 10.1109/ICSE-Companion66252.2025.00010
Felix Kretzer, Kristian Kolthoff, Christian Bartelt, Simone Paolo Ponzetto, and Alexander Maedche. 2025. Closing the Loop betweenUser Stories andGUI Prototypes. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems (Yokohama, Japão) (CHI ’25). ACM SIGCHI, Association for Computing Machinery, New York, NY, USA, Article 879, 19 pages. DOI: 10.1145/3706598.3713932
Ryan Li, Yanzhe Zhang, and Diyi Yang. 2025. Sketch2Code. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), Luis Chiruzzo, Alan Ritter, and Lu Wang (Eds.). Association for Computational Linguistics, Association for Computational Linguistics, Albuquerque, New Mexico, 3921–3955. DOI: 10.18653/v1/2025.naacl-long.198
Atefeh Nirumand and Jordi Cabot. 2025. From Mock-Ups to IFML-Like GUI Models. In Web Engineering: 25th International Conference, ICWE 2025, Delft, The Netherlands, June 30 – July 3, 2025, Proceedings (Delft, The Netherlands). Springer-Verlag, Berlin, Heidelberg, 253–268. DOI: 10.1007/978-3-031-97207-2_20
Zeeshan Rasheed, Muhammad Waseem, Kai Kristian Kemell, Aakash Ahmad, Malik Abdul Sami, Jussi Rasku, Kari Systä, and Pekka Abrahamsson. 2025. Large Language Models for Code Generation. arXiv:2501.16998 [cs.SE] DOI: 10.48550/arXiv.2501.16998
Yvonne Rogers, Helen Sharp, and Jennifer Preece. 2023. Interaction Design (6th ed.). Wiley. [link]
Pranab Sahoo, Ayush Kumar Singh, Sriparna Saha, Vinija Jain, Samrat Mondal, and Aman Chadha. 2025. A Systematic Survey of Prompt Engineering in Large Language Models. arXiv:2402.07927 [cs.AI] [link]
Sander Schulhoff, Michael Ilie, Nishant Balepur, et al. 2025. The Prompt Report. arXiv:2406.06608 [cs.CL] [link]
Chenglei Si, Yanzhe Zhang, Ryan Li, Zhengyuan Yang, Ruibo Liu, and Diyi Yang. 2025. Design2Code. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), Luis Chiruzzo, Alan Ritter, and Lu Wang (Eds.). Association for Computational Linguistics, Association for Computational Linguistics, Albuquerque, New Mexico, 3956–3974. DOI: 10.18653/v1/2025.naacl-long.199
STACK OVERFLOW. 2025. Stack Overflow Developer Survey 2025. Industry survey. [link]. Acesso em: 10 ago. 2026.
Yuxuan Wan, Chaozheng Wang, Yi Dong, Wenxuan Wang, Shuqing Li, Yintong Huo, and Michael Lyu. 2025. Divide-and-Conquer. Proc. ACM Softw. Eng. 2, FSE, Article FSE094 (June 2025), 24 pages. DOI: 10.1145/3729364
Guoqing Wang, Zeyu Sun, Sixiang Ye, Zhihao Gong, Yizhou Chen, Yifan Zhao, Qingyuan Liang, and Dan Hao. 2025. Do advanced language models eliminate the need for prompt engineering in software engineering? ACM Trans. Softw. Eng. Methodol. (Oct. 2025). DOI: 10.1145/3771933, Just Accepted.
Yue Wang, Hung Le, Akhilesh Gotmare, Nghi Bui, Junnan Li, and Steven Hoi. 2023. CodeT5+. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Houda Bouamor, Juan Pino, and Kalika Bali (Eds.). ACL SIGDAT, Association for Computational Linguistics, Singapore, 1069–1088. DOI: 10.18653/v1/2023.emnlp-main.68
Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2022. Chain-of-thought prompting elicits reasoning in large language models. In Proceedings of the 36th International Conference on Neural Information Processing Systems (New Orleans, LA, USA) (NIPS ’22). Neural Information Processing Systems Foundation, Curran Associates Inc., Red Hook, NY, USA, Article 1800, 14 pages.
JulesWhite, Quchen Fu, SamHays, Michael Sandborn, Carlos Olea, Henry Gilbert, Ashraf Elnashar, Jesse Spencer-Smith, and Douglas C. Schmidt. 2023. A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT. In Proceedings of the 30th Conference on Pattern Languages of Programs (Monticello, IL, USA) (PLoP ’23). The Hillside Group, The Hillside Group, USA, Article 5, 31 pages.
Claes Wohlin, Per Runeson, Martin Höst, Magnus C. Ohlsson, Björn Regnell, and Anders Wesslén. 2012. Experimentation in Software Engineering. Springer, Berlin, Heidelberg. DOI: 10.1007/978-3-642-29044-2
Jingyu Xiao, Ming Wang, Man Ho Lam, Yuxuan Wan, Junliang Liu, Yintong Huo, and Michael R. Lyu. 2025. DesignBench. arXiv:2506.06251 [cs.SE] DOI: 10.48550/arXiv.2506.06251
Shuhong Xiao, Yunnong Chen, Jiazhi Li, Liuqing Chen, Lingyun Sun, and Tingting Zhou. 2024. Prototype2Code. arXiv:2405.04975 [cs.SE] DOI: 10.48550/arXiv.2405.04975
Zhihang Zhang, Ye Ding, and Chenlin Huang. 2023. Automatic Front-end Code Generation from image Via Multi-Head Attention. In 2023 4th International Conference on Computer Engineering and Application (ICCEA) (Hangzhou, China). IEEE, 869–872. DOI: 10.1109/ICCEA58433.2023.10135462
Ting Zhou, Yanjie Zhao, Xinyi Hou, Xiaoyu Sun, Kai Chen, and Haoyu Wang. 2025. DeclarUI. 2, FSE, Article FSE011 (June 2025), 23 pages. DOI: 10.1145/3715726
Yangtian Zi, Harshitha Menon, and Arjun Guha. 2025. More Than a Score. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, Kentaro Inui, Sakriani Sakti, Haofen Wang, Derek F. Wong, Pushpak Bhattacharyya, Biplab Banerjee, Asif Ekbal, Tanmoy Chakraborty, and Dhirendra Pratap Singh (Eds.). AFNLP, The Asian Federation of Natural Language Processing and The Association for Computational Linguistics, Mumbai, India, 2380–2402. DOI: 10.18653/v1/2025.ijcnlp-long.128
Berk Atıl, Sarp Aykent, Alexa Chittams, Lisheng Fu, Rebecca J. Passonneau, Evan Radcliffe, Guru Rajan Rajagopal, Adam Sloan, Tomasz Tudrej, Ferhan Ture, Zhe Wu, Lixinyu Xu, and Breck Baldwin. 2025. Non-Determinism of “Deterministic” LLM System Settings in Hosted Environments. In Proceedings of the 5th Workshop on Evaluation and Comparison of NLP Systems, Mousumi Akter, Tahiya Chowdhury, Steffen Eger, Christoph Leiter, Juri Opitz, and Erion Çano (Eds.). Association for Computational Linguistics, Association for Computational Linguistics, Mumbai, India, 135–148. DOI: 10.18653/v1/2025.eval4nlp-1.12
Tom B. Brown, Benjamin Mann, Nick Ryder, et al. 2020. Language models are few-shot learners (NIPS ’20). Neural Information Processing Systems Foundation, Curran Associates Inc., Red Hook, NY, USA, Article 159, 25 pages.
Federico Cassano, John Gouwar, Francesca Lucchetti, Claire Schlesinger, Anders Freeman, Carolyn Jane Anderson, Molly Q. Feldman,Michael Greenberg, Abhinav Jangda, and Arjun Guha. 2024. Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMs. Proc. ACM Program. Lang. 8, OOPSLA2, Article 338 (Oct. 2024), 28 pages. DOI: 10.1145/3689735
Mark Chen, Jerry Tworek, Heewoo Jun, et al. 2021. Evaluating Large Language Models Trained on Code. arXiv:2107.03374 [cs.LG] DOI: 10.48550/arXiv.2107.03374
Rogelio Cruz, Jonatan Contreras, Francisco Guerrero, Ezequiel Rodriguez, Carlos Valdez, and Citlali Carrillo. 2025. Prompt engineering and framework. arXiv:2506.10989 [cs.SE] DOI: 10.48550/arXiv.2506.10989
Roy Derks. 2022. React Projects. Packt Publishing.
Matthias Galster, Seyedmoein Mohsenimofidi, Jai Lal Lulla, Muhammad Auwal Abubakar, Christoph Treude, and Sebastian Baltes. 2026. Configuring Agentic AI Coding Tools. arXiv:2602.14690 [cs.SE] [link]
Kosei Horikawa, Hao Li, Yutaro Kashiwa, Bram Adams, Hajimu Iida, andAhmed E. Hassan. 2025. Agentic Refactoring. arXiv:2511.04824 [cs.SE] DOI: 10.48550/arXiv.2511.04824
E. G. Santana Jr, Gabriel Benjamin, Melissa Araujo, Harrison Santos, David Freitas, Eduardo Almeida, Paulo Anselmo da M. S. Neto, Jiawei Li, Jina Chun, and Iftekhar Ahmed. 2025. Which Prompting Technique Should I Use? An Empirical Investigation of Prompting Techniques for Software Engineering Tasks. arXiv:2506.05614 [cs.SE] [link]
Kristian Kolthoff, Felix Kretzer, Christian Bartelt, Alexander Maedche, and Simone Paolo Ponzetto. 2025. GUIDE. 4 pages. DOI: 10.1109/ICSE-Companion66252.2025.00010
Felix Kretzer, Kristian Kolthoff, Christian Bartelt, Simone Paolo Ponzetto, and Alexander Maedche. 2025. Closing the Loop betweenUser Stories andGUI Prototypes. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems (Yokohama, Japão) (CHI ’25). ACM SIGCHI, Association for Computing Machinery, New York, NY, USA, Article 879, 19 pages. DOI: 10.1145/3706598.3713932
Ryan Li, Yanzhe Zhang, and Diyi Yang. 2025. Sketch2Code. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), Luis Chiruzzo, Alan Ritter, and Lu Wang (Eds.). Association for Computational Linguistics, Association for Computational Linguistics, Albuquerque, New Mexico, 3921–3955. DOI: 10.18653/v1/2025.naacl-long.198
Atefeh Nirumand and Jordi Cabot. 2025. From Mock-Ups to IFML-Like GUI Models. In Web Engineering: 25th International Conference, ICWE 2025, Delft, The Netherlands, June 30 – July 3, 2025, Proceedings (Delft, The Netherlands). Springer-Verlag, Berlin, Heidelberg, 253–268. DOI: 10.1007/978-3-031-97207-2_20
Zeeshan Rasheed, Muhammad Waseem, Kai Kristian Kemell, Aakash Ahmad, Malik Abdul Sami, Jussi Rasku, Kari Systä, and Pekka Abrahamsson. 2025. Large Language Models for Code Generation. arXiv:2501.16998 [cs.SE] DOI: 10.48550/arXiv.2501.16998
Yvonne Rogers, Helen Sharp, and Jennifer Preece. 2023. Interaction Design (6th ed.). Wiley. [link]
Pranab Sahoo, Ayush Kumar Singh, Sriparna Saha, Vinija Jain, Samrat Mondal, and Aman Chadha. 2025. A Systematic Survey of Prompt Engineering in Large Language Models. arXiv:2402.07927 [cs.AI] [link]
Sander Schulhoff, Michael Ilie, Nishant Balepur, et al. 2025. The Prompt Report. arXiv:2406.06608 [cs.CL] [link]
Chenglei Si, Yanzhe Zhang, Ryan Li, Zhengyuan Yang, Ruibo Liu, and Diyi Yang. 2025. Design2Code. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), Luis Chiruzzo, Alan Ritter, and Lu Wang (Eds.). Association for Computational Linguistics, Association for Computational Linguistics, Albuquerque, New Mexico, 3956–3974. DOI: 10.18653/v1/2025.naacl-long.199
STACK OVERFLOW. 2025. Stack Overflow Developer Survey 2025. Industry survey. [link]. Acesso em: 10 ago. 2026.
Yuxuan Wan, Chaozheng Wang, Yi Dong, Wenxuan Wang, Shuqing Li, Yintong Huo, and Michael Lyu. 2025. Divide-and-Conquer. Proc. ACM Softw. Eng. 2, FSE, Article FSE094 (June 2025), 24 pages. DOI: 10.1145/3729364
Guoqing Wang, Zeyu Sun, Sixiang Ye, Zhihao Gong, Yizhou Chen, Yifan Zhao, Qingyuan Liang, and Dan Hao. 2025. Do advanced language models eliminate the need for prompt engineering in software engineering? ACM Trans. Softw. Eng. Methodol. (Oct. 2025). DOI: 10.1145/3771933, Just Accepted.
Yue Wang, Hung Le, Akhilesh Gotmare, Nghi Bui, Junnan Li, and Steven Hoi. 2023. CodeT5+. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Houda Bouamor, Juan Pino, and Kalika Bali (Eds.). ACL SIGDAT, Association for Computational Linguistics, Singapore, 1069–1088. DOI: 10.18653/v1/2023.emnlp-main.68
Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2022. Chain-of-thought prompting elicits reasoning in large language models. In Proceedings of the 36th International Conference on Neural Information Processing Systems (New Orleans, LA, USA) (NIPS ’22). Neural Information Processing Systems Foundation, Curran Associates Inc., Red Hook, NY, USA, Article 1800, 14 pages.
JulesWhite, Quchen Fu, SamHays, Michael Sandborn, Carlos Olea, Henry Gilbert, Ashraf Elnashar, Jesse Spencer-Smith, and Douglas C. Schmidt. 2023. A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT. In Proceedings of the 30th Conference on Pattern Languages of Programs (Monticello, IL, USA) (PLoP ’23). The Hillside Group, The Hillside Group, USA, Article 5, 31 pages.
Claes Wohlin, Per Runeson, Martin Höst, Magnus C. Ohlsson, Björn Regnell, and Anders Wesslén. 2012. Experimentation in Software Engineering. Springer, Berlin, Heidelberg. DOI: 10.1007/978-3-642-29044-2
Jingyu Xiao, Ming Wang, Man Ho Lam, Yuxuan Wan, Junliang Liu, Yintong Huo, and Michael R. Lyu. 2025. DesignBench. arXiv:2506.06251 [cs.SE] DOI: 10.48550/arXiv.2506.06251
Shuhong Xiao, Yunnong Chen, Jiazhi Li, Liuqing Chen, Lingyun Sun, and Tingting Zhou. 2024. Prototype2Code. arXiv:2405.04975 [cs.SE] DOI: 10.48550/arXiv.2405.04975
Zhihang Zhang, Ye Ding, and Chenlin Huang. 2023. Automatic Front-end Code Generation from image Via Multi-Head Attention. In 2023 4th International Conference on Computer Engineering and Application (ICCEA) (Hangzhou, China). IEEE, 869–872. DOI: 10.1109/ICCEA58433.2023.10135462
Ting Zhou, Yanjie Zhao, Xinyi Hou, Xiaoyu Sun, Kai Chen, and Haoyu Wang. 2025. DeclarUI. 2, FSE, Article FSE011 (June 2025), 23 pages. DOI: 10.1145/3715726
Yangtian Zi, Harshitha Menon, and Arjun Guha. 2025. More Than a Score. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, Kentaro Inui, Sakriani Sakti, Haofen Wang, Derek F. Wong, Pushpak Bhattacharyya, Biplab Banerjee, Asif Ekbal, Tanmoy Chakraborty, and Dhirendra Pratap Singh (Eds.). AFNLP, The Asian Federation of Natural Language Processing and The Association for Computational Linguistics, Mumbai, India, 2380–2402. DOI: 10.18653/v1/2025.ijcnlp-long.128
Publicado
11/09/2026
Como Citar
SOUSA, Caio Rian Reinaldo de; OLIVEIRA, Beatriz Nascimento de; SILVA, Francisco Jerferson Martins da; BEZERRA, Carla.
Engenharia de Prompt na Geração de Interfaces a partir de Protótipos Visuais: uma Avaliação Empírica em IDE Agêntica. In: WORKSHOP DE VISUALIZAÇÃO, EVOLUÇÃO E MANUTENÇÃO DE SOFTWARE (VEM), 14. , 2026, São Paulo/SP.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 144-150.
DOI: https://doi.org/10.5753/vem.2026.32996.
