The Prompt
Copy and paste into your AI tool
You are a senior Amazon inventory management analyst. You know that safety stock is one of the most important and least-calculated numbers in an Amazon business. Most sellers set safety stock by gut feel — "keep 30 days on hand" — without accounting for their specific demand variability or lead time variability. The result is either chronic stockouts (rank loss, lost revenue) or chronic overstock (cash tied up, storage fees). Your job here is to calculate the correct safety stock level for each SKU provided. I'm going to provide inventory and demand data. Calculate safety stock and reorder points. SAFETY STOCK FORMULA: Safety stock = Z × √(lead time) × demand standard deviation Where: Z = service level factor (how confident you want to be that you won't stock out): - 90% service level: Z = 1.28 - 95% service level: Z = 1.65 - 99% service level: Z = 2.33 Default to 95% unless specified otherwise. Lead time = average lead time in days (supplier production + ocean/air freight + customs + Amazon receiving) Demand standard deviation = standard deviation of daily units sold over the measurement period If daily demand standard deviation is not directly available, calculate it from weekly or monthly data: Daily StdDev ≈ weekly StdDev ÷ √7 Daily StdDev ≈ monthly StdDev ÷ √30 REORDER POINT FORMULA: Reorder point = (average daily demand × average lead time) + safety stock This is the inventory level at which you should place your next order so that you receive new stock before hitting zero. DAYS OF SUPPLY AT SAFETY STOCK: Safety stock days = safety stock ÷ average daily demand This tells you how many days of cover your safety stock provides. LEAD TIME VARIABILITY ADJUSTMENT (advanced): If lead time is itself variable (not consistent), use the extended formula: Safety stock = Z × √((average lead time × demand variance) + (average daily demand²× lead time variance)) Use this formula if lead time standard deviation is provided and is > 20% of average lead time. STEP 1: CALCULATE PER SKU For each SKU, calculate: - Average daily demand - Demand standard deviation (daily) - Safety stock units - Reorder point - Days of supply at safety stock - Current safety stock vs. recommended (over/under) STEP 2: CASH IMPACT For each SKU: - Current safety stock inventory value = current SS × COGS - Recommended safety stock inventory value = recommended SS × COGS - Cash impact of change (positive = cash released, negative = additional cash needed) STEP 3: SERVICE LEVEL SENSITIVITY Show how safety stock changes at 90%, 95%, and 99% service levels for each SKU — so the seller can make an informed trade-off between stockout risk and capital cost. Output format: SAFETY STOCK ANALYSIS SKU RESULTS TABLE | SKU | Avg Daily Demand | Demand StdDev | Lead Time (days) | Safety Stock | Reorder Point | SS Days | Current SS | Status | CASH IMPACT TABLE | SKU | Current SS Value | Recommended SS Value | Cash Impact | SERVICE LEVEL SENSITIVITY | SKU | SS @ 90% | SS @ 95% | SS @ 99% | BEFORE YOU EXECUTE: 1. If any required input is missing, unclear, or looks malformed, stop and ask me a specific clarifying question before proceeding. Do not guess or fill in plausible values. 2. If I haven't provided demand variability data (standard deviation or enough historical data to calculate it), ask. A safety stock calculation without demand variability is just a fixed buffer — flag this clearly if you have to estimate. 3. If lead time is highly variable (> 20% coefficient of variation), recommend using the extended formula and ask for lead time standard deviation. 4. If you are less than 95% confident you understand what I'm asking for, ask me to clarify before executing the task. 5. Verify every arithmetic calculation by working it twice. Round safety stock figures up to the nearest whole unit. ===== PASTE YOUR INVENTORY DATA BELOW. For each SKU include: SKU name, average daily units sold, daily or weekly demand standard deviation (or enough historical sales data to calculate it), average lead time in days (total from order placement to Amazon receiving), lead time standard deviation if known, COGS per unit, and current safety stock level. Also specify your desired service level (90%, 95%, or 99%) or leave blank to use the 95% default. [YOUR DATA HERE]
Example Input
What you'd paste after the divider
Desired service level: 95% SKU: SPAT-3PK Average daily units: 14.2 Weekly sales (last 12 weeks): 98, 105, 87, 112, 94, 118, 101, 96, 122, 88, 109, 103 Average lead time: 52 days (14 days production + 28 days ocean freight + 5 days customs + 5 days Amazon receiving) Lead time variability: sometimes 45 days, sometimes 62 days COGS per unit: $7.35 Current safety stock: 120 units SKU: BOWL-SET Average daily units: 6.1 Weekly sales (last 12 weeks): 44, 39, 48, 41, 52, 38, 47, 43, 55, 36, 49, 42 Average lead time: 58 days Lead time variability: fairly consistent, ±5 days COGS per unit: $11.20 Current safety stock: 80 units
Tips
01
Safety stock is not the same as your reorder point. Safety stock is the buffer you hold against uncertainty — it's the inventory you hope never to touch. The reorder point is the trigger for your next order. Confusing the two leads to either ordering too late or holding too much idle stock.
02
Demand variability matters more than average demand for safety stock calculation. A SKU selling 10 units/day with a standard deviation of 1 needs far less safety stock than one selling 10 units/day with a standard deviation of 5. If you set safety stock based on average demand alone, you're systematically under-protected during volatile weeks.
03
Lead time is almost always longer than sellers think when you include Amazon's receiving time. A 28-day ocean shipment that spends 8 days at an Amazon FC before being received into available inventory is actually a 36-day lead time for planning purposes. Use the total time from order placement to "available to sell" — not just transit time.
Frequently Asked Questions
What does the Safety Stock Calculator prompt do?
Calculate the right safety stock level for each SKU — the buffer inventory you hold to absorb demand spikes and supply delays without going out of stock. Too little and you lose rank every time you stock out. Too much and you're paying storage fees on idle inventory. This prompt finds the right number.
What data do I need to use this prompt?
An example of the exact input format is provided on this page under "Example Input." Generally you'll prepare your data in the structure shown, paste it after the prompt body, and the AI will return the analysis described above. If you're missing any inputs, the prompt will ask you what it needs.
How long does this take to set up?
Setup time for this prompt is < 30 mins. That includes pulling your data, formatting it to match the example, and running the prompt. Once your data pipeline is set up the first time, subsequent runs take only a few minutes.
Which AI tool should I use this with?
This prompt is designed to work with any major large language model — ChatGPT (GPT-4 or newer), Claude (Sonnet 4 or newer), or Gemini. For structured analysis, math, and tabular outputs, Claude and GPT-4 class models produce the most reliable results.
Does this prompt work for Shopify or other platforms?
This prompt is built for Amazon sellers and references Amazon-specific data points such as referral fees, FBA fulfillment fees, and ASIN-level metrics. The underlying methodology can be adapted to other platforms by substituting equivalent inputs, but the prompt as written is Amazon-first.
What skill level is required to use this prompt?
This prompt is rated intermediate. Some familiarity with your platform's data exports and basic AI prompting is helpful for getting the most out of it. Most ecommerce operators can use it productively within a single session.
Is this prompt free to use?
Yes. Every prompt in the SMB Advantage Prompt Library is free for any small business operator to use. The only cost is whatever you pay for your AI tool subscription (ChatGPT Plus, Claude Pro, etc.).
Stay in the loop
Want notes when new prompts ship?
A few times a week, field notes on what's actually working when AI meets ecommerce ops. Plus first look at new prompts and tools as they go live.
Related Prompts