As of 13 August 2026, AI can only partly value your current stock.

What to actually do

1. Hand it to a person

   The route this page recommends

   A person who owns the outcome does this end to end, worth it when the failure is dear.

2. Use a tool built for this

   Second choice

3. Do it yourself

   The distant third

   A chat interface, chat-fluent skill, and roughly 30 minutes until you can act on the result.

   How to actually do it

   1. Export the current stock list from your stock system with SKU, description, quantity, location, condition and last movement date, then save the export unchanged.
   2. Gather the purchase invoices or cost file that supports each unit cost, including any agreed treatment of discounts, delivery, VAT and currency.
   3. Separate damaged, expired, obsolete and unidentified items in a notes file, and record the stocktake date if the quantities came from a physical count.
   4. Paste the stock export, cost data, notes and any agreed valuation rule into the prompt, then ask the model to calculate the result without filling gaps.
   5. Copy the model's line-value table into a spreadsheet and recalculate quantity multiplied by unit cost, checking the subtotals and total against the displayed calculations.
   6. Compare unusual lines and every flagged missing or adjusted item against the original stock system and purchase invoices, then have a colleague confirm the valuation basis and exceptions.
   7. Use the confirmed figure only for the purpose it was checked for, and send it to your accountant before using it in statutory accounts or tax work.

   Prompt

   Value the stock in the data below as at [valuation date]. Use only the figures I provide and do not invent quantities, costs, dates or accounting rules. First identify the valuation basis that can be supported by the data, such as unit cost, weighted average cost or another stated basis. If the basis is unclear, show the possible interpretations instead of choosing silently.
   
   Separate sellable, damaged, obsolete, expired and unidentified items where the data supports this. Flag missing unit costs, duplicate lines, negative quantities, unusual costs, currency differences and items with no recent movement. Show a table with SKU, description, quantity, unit cost used, adjustments, line value and reason for any adjustment. Then give subtotals and a total, with the calculation written plainly enough to reproduce in a spreadsheet.
   
   Do not treat a sales price as a stock cost. Do not decide whether a write-down, landed cost, VAT treatment or accounting policy applies unless I have supplied the rule. List every assumption and every row that needs human confirmation. End with a reconciliation checklist comparing the result with the stock system, purchase invoices and any stocktake count.
   
   Stock data:
   [Paste the stock export here]
   
   Cost and purchasing data:
   [Paste unit costs, invoices or cost rules here]
   
   Condition, movement and location notes:
   [Paste relevant notes here]
   
   Business or accounting rule to apply, if already agreed:
   [Paste the rule here]

   Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.