Agentic ai improves supply chain decisions with modular experts
A Hybrid Agentic AI Framework for Intelligent Supply Chain Analytics
Artificial IntelligenceMultiagent Systems
Summary
Supply chain planners often struggle because making decisions needs many different expert skills, like data handling, forecasting, and business knowledge. The authors created a system where a main AI understands what the planner wants and breaks the work into tasks that specialized AI agents handle. This setup lets users switch between asking open-ended questions and following fixed analysis steps, making the process easier and more flexible. Tests showed the system is accurate and uses much less computing effort, helping it work faster and cheaper.
What this means in practice
- •For supply chain planners: Use an AI system that divides complex supply chain analysis into specialized tasks, improving decision accuracy and lowering computation costs.
- •For business intelligence developers: Build scalable decision-support tools that combine flexible queries and structured processes using modular specialist AI agents.
Authors
Xian Yeow Lee, Teppei Inoue, Haiyan Wang, Chetan Gupta
Abstract
Efficient utilization of supply chain analytics for decision making remains a significant challenge for planners, as critical tasks such as database querying, key performance indicator (KPI) analysis, demand forecasting, and performance diagnosis require heterogeneous expertise spanning data engineering, operations research, and domain knowledge. In this work, we propose an agentic system for supply chain analytics that bridges the gap between business decision-making and technical expertise, where a coordinator agent interprets user intent and delegates sub-tasks to specialized agents. The system supports both exploratory analysis and deterministic workflows, enabling planners to transition between ad hoc questions and structured processes. Domain logic is encapsulated within specialist agents and prompts, yielding a scalable, modular, and auditable design and lowering the cost of functional extension through prompt-centric development. We evaluate the proposed architecture on a test environment that replicates multi-echelon inventory management operations. Results show that our multi-agent design achieves a 90\% accuracy, which is competitive with a single agent baseline while reducing input token usage by roughly fourfold, substantially improving scalability and cost-efficiency. Furthermore, we provide case studies to demonstrate interpretable suboptimality detection and automated forecast optimization, illustrating how agentic architectures can effectively combine open-ended exploratory analysis and deterministic supply chain analytics workflows, and provide a practical pathway toward more accessible and extensible decision-support systems.