Inventory Analytics AI Prompt

Analyze inventory performance and identify stock-out and overstock risks.

Inventory data: {{inventory_data}} (SKU, units_on_hand, daily_sales_rate, lead_time_days, reorder_point)
Sales data: {{sales_data}}

1. Inventory coverage analysis:
   - Days of Inventory Outstanding (DIO): units_on_hand / average_daily_sales_rate
   - Flag: DIO > 90 days = likely overstock
   - Flag: DIO < 14 days = reorder urgently (below safety stock for most lead times)
   - Distribution of DIO across the catalog

2. Stock-out risk assessment:
   - Products with DIO < lead_time_days: will stock out before reorder arrives
   - Products currently at zero inventory: lost sales occurring now
   - Lost revenue estimate from out-of-stocks:
     Out-of-stock loss = (days_out_of_stock x average_daily_revenue_when_in_stock)

3. Overstock identification:
   - Products with DIO > 90 days: cash and storage tied up unproductively
   - Total overstock value: units_excess x unit_cost (units_excess = inventory - 90 days supply)
   - Products with declining sales trend: overstock risk is growing over time

4. Reorder point calculation:
   Reorder Point = (Average Daily Sales x Lead Time) + Safety Stock
   Safety Stock = Z x Standard Deviation of Demand x sqrt(Lead Time)
   - Z = 1.65 for 95% service level, 2.05 for 98%
   - Compare current reorder points to calculated optimal reorder points

5. ABC classification:
   - A items: top 20% of products by revenue (80% of revenue) - high control
   - B items: next 30% of products (15% of revenue) - moderate control
   - C items: bottom 50% of products (5% of revenue) - minimal control
   - A items should never stock out; C items can have lower service levels

6. Inventory optimization actions:
   - Immediate: order products in stock-out risk category
   - Short term: markdown or bundle overstock items to release cash
   - Medium term: revise reorder points and safety stock levels for top-50 SKUs

Return: DIO distribution, stock-out risk list with lost revenue, overstock list with excess value, optimized reorder points, ABC classification, and action priorities.