Agentic AI framework improves spatial decisions in supply chains
Agentic AI Orchestration Framework for Spatial Intelligence: Supply Chain Deployment
Artificial IntelligenceMultiagent SystemsSoftware Engineering
Summary
Deciding how to arrange and move things in complex spaces like supply chains can be hard because different systems don’t share a common map or language. The authors created ANASSA, a system where intelligent agents talk in clear, structured ways about space, check their claims against trusted maps, and involve humans in key decisions. They tested ANASSA in a real supply chain for shipping goods, spotting risks like temperature problems with refrigerated containers. Their early test showed better data quality, faster workflows, and quicker decisions compared to before.
What this means in practice
- •For supply chain managers: Coordinate complex spatial workflows and risk detection across diverse systems with integrated AI and human checks.
- •For logistics operations teams: Automate and speed up hazard assessments and container monitoring to reduce delays and improve data quality.
Authors
Constantinos Papantoniou, Brian Hilton
Abstract
Industrial spatial decisions are assembled across systems that share neither a reference frame nor an owner, and analysts spend substantial effort reconciling those systems rather than reasoning about space. This paper presents ANASSA, a reference architecture integrating structured reasoning, multi-agent workflow orchestration, authoritative spatial grounding, and feedback-driven execution, and reports its instantiation in an operating supply-chain deployment. The architecture places typed data contracts at agent boundaries, validates spatial claims against a certified authoritative foundation, and enforces two blocking human-in-the-loop approvals inside a six-step cognitive loop. The deployment covers multi-hazard risk assessment on an ocean-and-inland freight lane, including cold-chain excursion detection over container telemetry. Across a three-month proof of concept (POC) with three implementation iterations, three deployment outcomes are reported: 25% improvement in data quality, 50% reduction in spatial workflow runtime, and 60% lower decision latency relative to the preceding manual workflow. Absolute deployment-scale quantities and baseline counts are confidential; reported percentages are observed relative changes. These are uncontrolled deployment observations, not controlled experiments. We therefore specify instrumentation and ablation protocols for mechanism-level evaluation.