Home · Business · Operations & Logistics · Inventory & stock
As of 13 August 2026, AI can create SKU numbers for your products.
Most people should hand this to a purpose-built tool.
Can you do it?
5 minutesto a draft.
30 minutesto something you’d act on.
Cost, all in£0
Skill neededchat-fluent
Who has to check ityou
What the alternative costsNo comparable human or software price is supplied in the available tool data.
If this goes wrong: duplicate or incorrectly structured SKUs can disrupt stock records, picking and orders until the affected products are corrected.
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 current stock or product spreadsheet and export the product name, variant details, brand, colour, size, supplier reference and any internal product ID.
- Copy the existing SKU column into a separate list, including discontinued and reserved codes if your business still treats them as unavailable.
- Choose the exact SKU structure and write down which product fields each section represents, such as category, colour, size and a sequence number.
- Paste the SKU rules, existing SKU list and product catalogue into a chatbot using the prompt above.
- Check the returned product and variant rows against the source spreadsheet, and resolve every exception instead of accepting a guessed attribute.
- Sort the proposed SKU column and compare it with the existing SKU list to confirm that no code is duplicated and every code follows the chosen format.
- Enter the approved SKUs into a copy of your inventory system first, match them to the correct product IDs, and test a small stock lookup or order workflow before publishing the full list.
Prompt
Create SKU numbers for the products in the catalogue below. SKU rules: - Use this exact format: [INSERT FORMAT, FOR EXAMPLE BRAND-CATEGORY-COLOUR-SIZE-NUMBER] - Use uppercase letters and numbers only, with hyphens if the format requires them. - Do not invent product attributes, variants or existing identifiers. - Do not reuse any SKU from the existing SKU list. - Keep the same product and variant represented by the same SKU. - If required information is missing or a proposed SKU would conflict with an existing SKU, do not guess. Put it in a separate exceptions table and explain what is missing or conflicting. - Make the numbering deterministic so the same input produces the same result. Return: 1. A table with product name, variant details, proposed SKU and the fields used to build it. 2. An exceptions table for incomplete or conflicting rows. 3. A short count of products processed, products needing decisions and duplicate SKUs found within the new list. Existing SKU list: [PASTE EXISTING SKUS OR WRITE NONE] Product catalogue: [PASTE PRODUCT NAMES, VARIANTS, ATTRIBUTES AND INTERNAL PRODUCT IDS HERE]
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 which product attributes your warehouse, website and suppliers already rely on unless you provide those rules.
- AI cannot guarantee uniqueness across systems it cannot access, including another warehouse, marketplace or supplier database.
- AI cannot decide whether a code should remain reserved after a product is discontinued or renamed.
- AI cannot repair links between SKUs, barcodes, product IDs and sales channels without access to those systems.
- You remain responsible for approving the codes and for correcting stock or order records if a code is wrong.
Even on a YES, the friction has a name: context depth 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 | 2 |
| Verification | 2 |
| Liability | 1 |
| Effort delta | 2 |
| Total | 9 / 10 |
The methodology and its thresholds are published in full.
FAQ
- Can ChatGPT generate SKU numbers?
- Yes. Give it your product catalogue, existing SKU list and exact naming rules, and it can produce a consistent draft with exceptions separated out. It cannot check systems or guarantee that a code is unused unless you provide the relevant data.
- What information do I need to create SKUs?
- You need the product name, variant details and the attributes that matter to your stock process, such as brand, colour, size or supplier reference. You also need your SKU format, any reserved codes and the existing SKU list.
- Can AI make sure my SKUs are unique?
- It can check uniqueness within the catalogue and existing list that you paste into the chat. It cannot check a live inventory system, marketplace or supplier database that it cannot access, so run the final duplicate check in your own system.
- Should I use a barcode as my SKU?
- Not automatically. A barcode, supplier reference and internal SKU can serve different purposes, so choose a structure that matches your stock, sales and fulfilment processes. Ask AI to document the distinction, but confirm the decision against your inventory and sales systems before importing anything.
Nearby answers
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.