AI-Powered Multi-Agent Fashion Assistant for Personalized Retail Recommendations
Abstract
As fashion retail navigates a new era shaped by heightened consumer expectations and rapidly evolving digital interactions, the need for deeply personalized, stylistically coherent, and context-aware recommendation systems has become paramount. Traditional engines, reliant on static rules or collaborative filtering, often fall short in capturing the complexity of human taste and the visual-semantic richness inherent in fashion products. This paper introduces Boyner’s AI-powered Multi-Agent Fashion Assistant, an enterprise-grade personalization platform architected on Microsoft Azure AI Foundry. The system orchestrates multiple specialized agents to deliver real-time, occasion-aware, and visually grounded fashion recommendations across omnichannel touchpoints. Leveraging multimodal embeddings, behavioral clustering, semantic search, and real-time trend signals, each agent operates with a distinct cognitive function, from silhouette-based outfit pairing to brand–season compatibility evaluation. Our implementation demonstrates how agentic AI systems can bridge the gap between algorithmic precision and stylistic intuition in large-scale fashion environments. The assistant not only enhances conversion and engagement metrics but also redefines the digital shopping journey as an explainable, adaptive, and human-centric dialogue. By operationalizing multi-agent orchestration within a live retail environment, Boyner pioneers a new paradigm in AI-powered visual discovery, offering a scalable blueprint for next-generation personalization in the global fashion ecosystem.
References
- 1.T. Schick et al. (2023). “Toolformer: Language Models Can Teach Themselves to Use Tools,” arXiv preprint, arXiv:2302.04761.
- 2.Y. Jiang et al. (2023). “Agents: An Open Platform for Language Models as Autonomous Agents,” arXiv preprint, arXiv:2308.08155.
- 3.OpenAI. (2024). “GPT-4 Technical Report”.
- 4.Microsoft. (2024). “Azure AI Agents and Foundry Documentation,” [Online]. Available: https://learn.microsoft.com/en-us/azure/ai-services/Link
- 5.X. Han et al. (2017). “Automatic spatially-aware fashion concept discovery,” in Proc. ICCV.
- 6.M. Vasileva et al. (2018). “Learning Type-Aware Embeddings for Fashion Compatibility,” in Proc. ECCV.
- 7.T. Lin et al. (2021). “FashionBERT: Text and Image Matching with Adaptive Loss for Cross-modal Retrieval,” arXiv preprint, arXiv:2004.03688.
- 8.Amazon Science, “Outfit Recommendation with GCN and Contrastive Learning,” 2021.
- 9.Gartner. (2023). “Operationalizing AI in Retail: From Pilots to Scale,”.
- 10.McKinsey & Company. (2022). “The State of AI in Retail,”.
- 11.IDC. (2024). “The Future of AI Agents in the Enterprise,”.
- 12.RTIH. (2023). “AI in Fashion Retail Innovation Report,”.
- 13.A. Neelakantan et al. (2022). “Text and Code Embeddings with OpenAI’s ADA-002 Model,” OpenAI.
- 14.Zilliz. (2023). “Milvus: Open-source Vector Database for Scalable AI,”[Online]. Available: https://milvus.io/.Link
- 15.J. Devlin et al. (2019). “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” in Proc. NAACL-HLT.
- 16.TÜSİAD. (2023). “Türkiye'de Perakende ve Dijitalleşme Raporu,”.
- 17.Boyner AI Initiative. (2024). “Internal Documentation & Use Case Landscape,” Boyner Holding.
Dursun, S., Çelik, S., Önel, B., Işıkkent, T., Alacan, M. (2025). AI-Powered Multi-Agent Fashion Assistant for Personalized Retail Recommendations. *The European Journal of Research and Development*, 5(1), 624-634. https://doi.org/10.56038/ejrnd.v5i1.755
Bibliographic Info