As of 13 August 2026, AI can only partly calculate how much stock you should order.
Most people should hand this to a purpose-built tool.
Can you do it?
15 minutesto a draft.
30 minutesto something you’d act on.
Cost, all in£0
Skill neededchat-fluent
Who has to check ita colleague
What the alternative costsNo priced alternative is listed in the supplied tool data.
If this goes wrong, you can order too little and lose sales or order too much and tie up cash, create waste or exceed storage capacity.
What to actually do
Use a tool built for this
The route this page recommends
Do it yourself
Second choiceA chat interface, chat-fluent skill, and roughly 30 minutes until you can act on the result.
How to actually do it
- Open your stock-control or spreadsheet system and export current stock, stock already on order, recent usage or sales, product identifiers and supplier details.
- Gather the current supplier rules for each item, including lead time, delivery days, minimum order quantity, pack size, order multiple and any storage or shelf-life limit.
- Write down the review period, safety-stock rule, planned promotions, seasonal changes, closures and any known supply disruption that could alter demand.
- Paste the data and the copyable prompt into a chatbot, keeping units consistent and asking it to flag missing or contradictory figures rather than guessing.
- Compare the generated table with the source spreadsheet by checking the stock balance, demand period, lead-time calculation, safety stock and rounding for each item.
- Ask a colleague who understands your stock policy and supplier constraints to check the flagged exceptions and approve the final quantities.
- Enter only the approved quantities into your purchasing system and compare the draft order with supplier minimums, pack sizes, storage capacity and available cash before sending it.
Prompt
Calculate suggested stock order quantities from the data below. Use only the figures and rules I provide, and do not invent missing values. For each item, show current stock, stock already on order, recent demand, forecast demand if supplied, supplier lead time, review period, safety-stock rule, minimum order quantity, order multiple, pack size and the resulting suggested order quantity. State the formula and assumptions used for every item. Flag any missing, contradictory or stale input instead of guessing. Separate items that can be ordered now from items needing a human decision. Round orders up to the supplier's pack size or order multiple where supplied, and explain the rounding. Do not place an order or claim that the result is optimal. Return a table that I can paste into a spreadsheet, followed by a short list of checks I must complete before ordering. Business context: [business type and storage constraints] Ordering date: [date] Target service level or safety-stock rule: [rule] Review period: [number of days] Stock and demand data: [paste spreadsheet or table] Supplier and product rules: [paste supplier lead times, minimum order quantities, pack sizes, order multiples, price breaks and known constraints] Planned promotions, closures, seasonal changes or unusual demand: [paste details, or write none] Do not estimate any missing figure. Ask focused questions for information needed to calculate the order quantities.
Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.
Hand it to a person
The distant thirdA person who owns the outcome does this end to end, worth it when the failure is dear.
What it gets wrong
- AI cannot know whether your stock records are accurate, current and recorded in the right units.
- AI cannot reliably predict an unusual demand change, supplier delay, promotion effect or local trading pattern without trustworthy inputs.
- AI cannot choose the right safety-stock policy when the trade-off between availability, waste and cash is unclear.
- AI cannot see physical stock, damaged goods, expiry dates, storage limits or an unrecorded delivery.
- AI does not carry responsibility for a shortage, over-order or supplier commitment.
What caps this at PARTLY: judgement under ambiguity, real time truth and stakes of error.
How we scored this
Five axes, each scored nought to two by hand: ten means AI carries the task cleanly, and the thresholds that turn a total into YES, PARTLY or NO are published in the methodology. Each axis name links to its definition.
| Axis | Score (0–2) |
|---|---|
| Output | 2 |
| Inputs | 1 |
| Verification | 1 |
| Liability | 1 |
| Effort delta | 2 |
| Total | 7 / 10 |
The methodology and its thresholds are published in full.
FAQ
- Can ChatGPT tell me how much stock to order?
- Partly. It can calculate quantities from your sales, stock, lead-time and ordering-rule data, but it cannot confirm that those inputs are accurate or decide the right safety stock when the trade-off is unclear.
- What data does AI need to calculate order quantities?
- Give it current stock, stock already on order, recent demand, supplier lead times, review period, safety-stock rules, minimum order quantities, pack sizes and order multiples. Also include promotions, seasonal changes, closures, storage limits and known supply problems.
- Can AI predict how much stock I will sell?
- It can produce a forecast from historical demand if you provide suitable data, but the forecast is not a fact. You must account for promotions, seasonality, closures, supply disruption and changes in customer demand before using it to place an order.
- Can AI place my stock order automatically?
- A general chatbot can calculate and format a proposed order, but it should not be treated as approval to buy. A colleague should check the quantities against current stock, supplier rules, storage and cash before you send the order.
Nearby answers
- Can AI calculate VAT on a UK supplier invoice?YES
- Can AI check whether a supplier has a product in stock?PARTLY
- Can AI check whether a supplier is genuine?PARTLY
- Can AI check whether a UK supplier is legitimate?PARTLY
- Can AI compare wholesale prices from UK suppliers?YES
- Can AI create a purchase order for my UK business?YES
Assessed by gpt-5.6-luna (gpt-5.6-luna) on 2026-08-13, second-checked by an independent model. Wrong somewhere? Email [email protected] and it gets re-checked.
The newsletter
AI news, new answers and product picks, straight to your inbox.