For businesses that hold stock: find out how accurate your demand forecast really is, product by product, and what the errors cost you in cash and missed orders.
How accurate are our forecasts?Product by product, month by month.
Which products are hardest to forecast?Grouped by value and how steady demand is.
What do the errors cost?Excess stock and lost sales, in £.
What should change?Method, routine and who decides.
Founder pricing. The method, the calculation spreadsheet with 16 built-in checks, and a complete worked example are built and tested. The first client for this product gets the founder price, in return for permission to measure the results and, if they are good, write them up as a case study. After that, the price goes up. Book a call to take the founder place.
Forecast against actual for each product, from your own history, with 16 built-in checks that catch missing months, mismatched product codes and unit errors.
By value and by how steady demand is, so effort goes where it pays.
Cash tied up in excess stock and sales lost to stock-outs.
Who forecasts, when, and with what information.
The changes that will improve accuracy most, with owners and dates.
With guided or done for you, each month the audit is rerun on the latest month in your own accounts, against the error you set for your most valuable products, and you are told which products are getting worse. Nothing leaves your business, and no decision changes, without one of your people approving it.
A fictional 46-person wholesaler with 60 stock lines, seasonal and steady. The audit used 12 months of its forecasts, sales and month-end stock.
Its forecast beat the simple baseline overall (30% error against 44%), but 18 products did worse than just using last month's sales, and outdoor lighting ran out at the peak. The routine, a once-a-year forecast by one person, was the root cause.
Export 12–24 months of forecasts, sales and stock by product.
Sort products by value and demand pattern.
Measure accuracy and whether you tend to over- or under-forecast, and cost the errors.
Agree changes to method and routine.
Each month the agent reruns the audit on the latest month in your own accounts and flags the products whose forecast is getting worse, so the improvements hold.
The same method and the same spreadsheet in every option. You choose how much of your own time goes in.
For owners comfortable with a spreadsheet and an AI assistant.
For owners who want a second pair of eyes on the data and the analysis.
For owners who would rather hand over the data and get the answer.
It is built on the open Agent Skills standard and designed for Claude (any plan, with code execution switched on). A paste-in version is included for ChatGPT, Gemini and Microsoft Copilot; it has not yet been tested on them.
The calculations live in the spreadsheet, not in the AI, so the numbers don't depend on which assistant reads them.
Book a short call to talk through how you plan stock and demand.
Book a call