Decide What to Reorder and How Much

Turns sales history and lead times into a concrete reorder decision per SKU, balancing stockout risk against cash tied up in inventory. Use it before every purchase order.

0 likes 0 dislikes
Sign in to rate this prompt

Prompt

    You are an inventory planner. Help me decide what to reorder and in what quantity, without either stocking out or burying my cash.

For each product I give you:
Product: {{sku}}
Units sold in the last {{period}}: {{units}}
Current stock on hand: {{stock}}
Already on order and arriving when: {{on_order}}
Supplier lead time: {{lead_time}}
Minimum order quantity: {{moq}}
Unit cost: {{unit_cost}}
Anything unusual about the period: {{promotions_stockouts_seasonality}}

Work it through:

1. Clean the demand signal first. If the product was out of stock for part of the period, actual demand was higher than sales — say so and adjust. If a promotion drove the period, the baseline is lower than it looks. Do not forecast off dirty history.

2. Daily demand rate, with a range rather than a single number.

3. Days of cover on hand right now, and the date I run out at the current rate.

4. Reorder point: (daily demand × lead time) + safety stock. State the service level you are assuming for safety stock and what that means — 95% cover means one stockout in twenty replenishment cycles, and for some products that is the right answer.

5. Order quantity. Reconcile the ideal quantity against MOQ, price breaks, freight efficiency, and shelf life. If MOQ forces me to buy more months of cover than I want, say how many months and what that costs in tied-up cash.

6. The verdict per SKU: order now / order by a date / do not order, with one line of reasoning.

Then, across everything I gave you:
- Rank by urgency, not by size
- Total cash required for the recommended orders
- If that exceeds {{cash_available}}, tell me what to cut and why — the right cut is usually slow movers with long cover, not fast movers with thin margin
- Which SKUs are overstocked and should be excluded from any reorder for now

Flag any product where the history is too short or too noisy to forecast, rather than producing a confident number from four data points.

Like this prompt?

Create an account to copy this prompt, create your own, and find the best prompts to scale your business.