An AI-Driven, Workflow-Aware Virtual Customer Support Assistant for Small and Medium-Sized Enterprises
Advanced Journal of Science Technology and Engineering · 17.11.2026 · 6 (2) · 27
DOI: 10.52589/ajste-csgfxk ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Journal of Science Technology and Engineering, online erschienen am 17.11.2026. Verfasst von Damilare Akinwunmi und 13 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Small and medium-sized enterprises (SMEs) that sell through messaging platforms often handle customer enquiries manually, leading to fragmented conversations, delayed responses and inconsistent service. This article proposes a workflow-aware conversational support assistant that combines a large language model (LLM), retrieval grounding, merchant API tools and context-preserving human hand-off. Using a design-science-oriented literature synthesis, in which sources were identified through keyword searches of academic databases, screened for relevance to messaging-based SME support and LLM-agent design, and analysed thematically, the study derives three design priorities: grounding customer-facing claims in current merchant data, separating model reasoning from validated execution, and transferring accumulated conversational state when escalation occurs. The resulting five-layer architecture comprises messaging integration, agent orchestration, retrieval and grounding, store action, and escalation and hand-off. Volatile data such as price, inventory and order status are retrieved live; state-changing operations require explicit customer confirmation and schema validation before execution. The article also specifies an evaluation protocol based on scripted end-to-end customer journeys using journey completion, factual agreement, action correctness, escalation precision and recall, context preservation, and response latency. The contribution is architectural and methodological; implementation and empirical validation remain future work.
Zitieren
APA
Akinwunmi, D., Oladipo, S., Agbonikpeya, E. W., Ejezie, V. O., Finecountry-Okezie, V., Akinyeke, D. F., Chidi-Aja, U., Ijomoni, E. O., Gbambisomo, O. J., Emeka-Ukandu, S. U., Akenroye, O. P., Adekunle, O. J., Fasakin, O. D., & Aiyenimelo, E. F. (2026). An AI-Driven, Workflow-Aware Virtual Customer Support Assistant for Small and Medium-Sized Enterprises. Advanced Journal of Science Technology and Engineering, 6(2), 27. https://doi.org/10.52589/ajste-csgfxk
Vancouver
Akinwunmi D, Oladipo S, Agbonikpeya EW, Ejezie VO, Finecountry-Okezie V, Akinyeke DF, et al. An AI-Driven, Workflow-Aware Virtual Customer Support Assistant for Small and Medium-Sized Enterprises. Advanced Journal of Science Technology and Engineering. 2026;6(2):27. doi:10.52589/ajste-csgfxk
BibTeX
@article{Akinwunmi2026,
author = {Akinwunmi, Damilare and Oladipo, Sunday and Agbonikpeya, Eromoigbe Winner and Ejezie, Valerian Olisaemeka and Finecountry-Okezie, Victor and Akinyeke, Dayo Francis and Chidi-Aja, Uchenna and Ijomoni, Evelyn-Ruth Okiemute and Gbambisomo, Oluwanifemi Joseph and Emeka-Ukandu, Samuel Ugonna and Akenroye, Oluwafiyinsola Praise and Adekunle, Oluwatobiloba Joshua and Fasakin, Oluwatobiloba David and Aiyenimelo, Esther Fisayomi},
title = {An AI-Driven, Workflow-Aware Virtual Customer Support Assistant for Small and Medium-Sized Enterprises},
journal = {Advanced Journal of Science Technology and Engineering},
year = {2026},
volume = {6},
number = {2},
pages = {27},
doi = {10.52589/ajste-csgfxk}
}
EUVIMED