LO
DeploymentCognitive automation2023-07-13
An LLM tool deployed in Microsoft's cloud supply chain answers planners' what-if questions that once needed three operators and an on-call engineer, with planners confirming or overriding
Supply chain planneroccupation page →
Event date / reported
2023-07-13
Evidence stage
DeploymentAn employer has put it into production. Can move the baseline — weighted by scale and how similar the setting is.
Tasks this bears on
Planning meetings and trade-offs
Balancing supply against sales in sales and operations planning, deciding what gives when capacity, cost and service conflict, and answering for the plan.
Still human-led✓ Evidence-backed
Disruptions and re-planning
Seeing a disruption coming — weather, a port, a supplier — working out what it does to the plan, and re-planning.
Being augmented✓ Evidence-backed
Where this applies
United States, Microsoft Azure's server supply chain. The paper says the authors deployed the OptiGuide tool for the server deployment optimisation used in Azure's supply chain; that the main consumers of the optimisation are planners, who confirm that its outcome meets business needs or override it; that before OptiGuide, answering one what-if question needed more than three operators and one on-call engineer; and that preliminary evaluation shows more than 90% accuracy in distribution. Microsoft both built and uses the tool, and sells the underlying models.
What this means
The tool takes the analysis work that used to need several people and an engineer; the decision on whether the plan fits the business stays with the planner.
What it does not yet show
One company's internal tool with preliminary accuracy figures; no staffing effects reported.
What you can check
Open arXiv 2307.03875 and find "The main consumers of IFS are planners" in the paper.
Does it change the assessment?
No. The impact index is never moved by a single event. What this record did: the 2 linked task judgements above now rest on evidence instead of inference.
Source
Li, Mellou, Zhang et al. (Microsoft Research, Microsoft Cloud Supply Chain) — Large Language Models for Supply Chain Optimization, arXiv 2307.03875 (v2, 13 Jul 2023) · verified 2026-09-29 · Claude (VOLO agent) · interpreted 2026-09-29 · Claude (VOLO agent)
Primary source — published by the party that did this, or the authority of record. No co-signature needed.