Towards Data Science is a community-powered publication that showcases work in data science, machine learning and artificial intelligence. Every day newcomers, seasoned researchers and industry practitioners publish tutorials, research notes and real-world case studies that help the field move forward.

Towards Data Science

An experiment using Claude Opus 4.6 connected via MCP to a distribution-tracking database to help supply chain planners diagnose delivery failures. The agent analyzes timestamps and boolean flags from ERP, WMS, and TMS systems to resolve real disputes between warehouse and transportation teams. Two scenarios are tested: one where both headquarters and a local team were partially right about late deliveries, and another where a warehouse team misunderstood their own KPIs. The conclusion is that agentic workflows can replace static dashboards for root-cause analysis, empowering non-technical planners to get data-driven answers through natural language.

Can AI Solve Failures in Your Supply Chain?

Understand Logistics Performance Management

How AI Agents Can Analyse Supply Chain Failures?