Bring these inputs
SKU-level stock, sales, lead times, returns and outstanding orders with a dated export.
Use approved, minimized data. Replace personal details with anonymous IDs.
Work through the lesson
- Normalize SKU identifiers and dates. Separate available, reserved and incoming units; record uncertainty in supplier lead times.
- Ask AI to identify stockouts, unusual returns and late orders. Require the underlying rows and calculation for each alert.
- Model reorder scenarios using demand ranges and lead-time variability. Historical averages can mislead when a promotion or stockout changes observed sales.
- Assign each exception to an owner. Keep purchase orders, refunds and customer notifications as drafts until reviewed.
- Compare alerts with actual events and update the rules. Track false alarms and missed issues, not just the number of tasks automated.
Try this prompt
Replace the bracketed fields with your own evidence.
Review [inventory and order exports]. Validate SKU joins and date ranges first. Produce an exception table with evidence rows, calculation, confidence, owner and proposed action. Show low/base/high demand scenarios. Do not place purchase orders or issue refunds.
Worked example
Illustrative planning: 10 units per day over a 14-day lead time implies 140 units of lead-time demand before buffers. This simple model is inadequate when demand or delivery time is volatile.
Before you use the result
- Units and dates are consistent.
- Stockouts are not mistaken for low demand.
- A human reviews financial commitments.
Complete the exercise
Create the deliverable described at the top of this lesson. Save the input evidence, your edited output, unresolved questions and the name of the reviewer in your workbook.