IMPLEMENTASI MULTI-AGENT UNTUK OTOMATISASI KONTEN PROMOSI DIGITAL PADA UMKM
Abstract
Micro, Small, and Medium Enterprises (MSME) often face challenges in producing engaging and consistent digital promotional content due to limited time, resources, and creative capabilities. This study aims to develop a CrewAI-based content creator assistant system to automate promotional content creation. The system was developed using Research and Development (R&D) methods with a Multi-Agent System approach consisting of a Content Planning Agent, a Caption Generator Agent, and a Visual Recommendation Agent. Implementation was carried out using Python on Google Collaboratory, utilizing the Large Language Model (LLM), the OpenAI API, and the BLIP model for product image analysis. Evaluation of 17 MSMEs was carried out based on time efficiency, ease of use, and user satisfaction. The results showed that the system was able to reduce the average content creation time from 52.65 minutes to 6.71 minutes, with an efficiency of 87.26%. In addition, the system obtained an ease of use score of 3.36 and a user satisfaction score of 3.28 on a 4-point Likert scale. These results indicate that the CrewAI-based multi-agent approach is effective in helping MSMEs produce promotional content more quickly and easily
Downloads
References
R. Suarantalla, “Peran Artificial Intelligence (AI) dalam Optimalisasi Pemasaran Digital pada Usaha Mikro, Kecil, dan Menengah (UMKM),” RIGGS J. Artif. Intell. Digit. Bus., vol. 4, no. 3, pp. 8480–8491, 2025, doi: 10.31004/riggs.v4i3.3277.
D. Andriana, J. Fadilah, and W. Widarti, “Implementasi Artificial Intelegence (AI) Dalam Perancangan Strategi Komunikasi Pemasaran Produk UMKM,” J-Ika, vol. 11, no. 2, pp. 78–89, 2024, doi: 10.31294/kom.v11i2.23473.
D. Duei Putri, G. F. Nama, and W. E. Sulistiono, “Analisis Sentimen Kinerja Dewan Perwakilan Rakyat (DPR) Pada Twitter Menggunakan Metode Naive Bayes Classifier,” J. Inform. dan Tek. Elektro Terap., vol. 10, no. 1, pp. 34–40, 2022, doi: 10.23960/jitet.v10i1.2262.
N. Gunawan and M. I. P. Nasution, “Perancangan Sistem Perencanaan Konten Media Sosial Berbasis Web Terintegrasi Artificial Intelligence (AI) Bagi UMKM Menggunakan Framework Next.js dengan Model Prototype,” JUSIFOR J. Sist. Inf. dan Inform., vol. 4, no. 2, pp. 233–242, 2025, doi: 10.70609/jusifor.v4i2.8343.
L. Zhang and C. Hur, “The Impact of Generative AI Images on Consumer Attitudes in Advertising,” Adm. Sci., vol. 15, no. 10, 2025, doi: 10.3390/admsci15100395.
H. Hendrayati, M. Achyarsyah, F. Marimon, U. Hartono, and L. Putit, “The Impact of Artificial Intelligence on Digital Marketing: Leveraging Potential in a Competitive Business Landscape,” Emerg. Sci. J., vol. 8, no. 6, pp. 2343–2359, 2024, doi: 10.28991/ESJ-2024-08-06-012.
N. A. Respati, J. Etienvre, and P. Anggahegari, The Evolving Position of Artificial Intelligence in Digital Marketing: A Qualitative Study of SMEs in Indonesia, no. Gcbme 2023. Atlantis Press International BV, 2024. doi: 10.2991/978-94-6463-443-3_80.
D. Grewal, C. B. Satornino, T. Davenport, and A. Guha, “How generative AI Is shaping the future of marketing,” J. Acad. Mark. Sci., vol. 53, no. 3, pp. 702–722, 2025, doi: 10.1007/s11747-024-01064-3.
G. A. A. Ghonisyah and A. K. Asyiah, “The Amplification of Generative Artificial Intelligence (AI) in Content Marketing For Women Micro-Entrepreneurs: Qualitative Case Study Approach,” Indones. J. Bus. Entrep., vol. 11, no. 3, p. 724, 2025, doi: 10.17358/ijbe.11.3.724.
J. Hartmann, Y. Exner, and S. Domdey, “The power of generative marketing: Can generative AI create superhuman visual marketing content?,” Int. J. Res. Mark., vol. 42, no. 1, pp. 13–31, 2025, doi: 10.1016/j.ijresmar.2024.09.002.
S. Lappin, “Assessing the Strengths and Weaknesses of Large Language Models,” J. Logic, Lang. Inf., vol. 33, no. 1, pp. 9–20, 2024, doi: 10.1007/s10849-023-09409-x.
P. Kumar, Large language models (LLMs): survey, technical frameworks, and future challenges, vol. 57, no. 9. Springer Netherlands, 2024. doi: 10.1007/s10462-024-10888-y.
T. Guo et al., “Large Language Model based Multi-Agents: A Survey of Progress and Challenges,” IJCAI Int. Jt. Conf. Artif. Intell., pp. 8048–8057, 2024.
C. Jimenez-Romero, A. Yegenoglu, and C. Blum, “Multi-agent systems powered by large language models: applications in swarm intelligence,” Front. Artif. Intell., vol. 8, 2025, doi: 10.3389/frai.2025.1593017.
R. Li, X. Wang, D. Berlowitz, J. Mez, H. Lin, and H. Yu, “CARE-AD: a multi-agent large language model framework for Alzheimer’s disease prediction using longitudinal clinical notes,” npj Digit. Med., vol. 8, no. 1, pp. 1–9, 2025, doi: 10.1038/s41746-025-01940-4.
S. Handayani, F. Fajrizal, and T. Taslim, “AI and Python Literacy Training via Google Colab for Pekanbaru High School Teachers,” Din. J. Pengabdi. Kpd. Masy., vol. 9, no. 6, pp. 2015–2024, 2025, doi: 10.31849/dinamisia.v9i6.28440
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
