Manual plans kept next to the statistical forecast
For a launch with no history, a line you are discontinuing, or a number the board committed to: set the plan by hand and keep it beside the statistical forecast, so you can see where the two disagree.
For SKUs without enough history
The engine needs about a year of sales before it can fit a seasonal pattern. A launch has none. A manual plan gives that SKU a real number to buy against in the meantime.
Shown next to the forecast, not in place of it
Both numbers stay visible. When the statistical forecast starts disagreeing with your assumption, you see it.
Board commitments as an explicit plan
A number committed in a board meeting drives real purchasing whether or not the forecast agrees. Kept as an explicit plan, the gap between the target and the forecast is a number you can see.
What the agent does with your own numbers
Every night
The agent plans against your manual number where you set one, and the overnight check tells you when actual sales have drifted away from it.
What it can’t do
It cannot set, change, or override a manual plan. Where you have said what the number is, that is the number.
Example: a launch with no sales history
Take a new flavour that ships in six weeks with no history. The forecast has nothing to fit and says so. The team sets a manual plan from comparable launches and buys against it. Eight weeks in, with real sales recorded, the statistical forecast starts to differ from the plan — the signal to re-order.
How it fits together
Every capability runs on the same demand forecast, so each one makes the others more useful.
Demand forecasting
What the manual plan sits beside: a model fitted per SKU, needing about 52 weeks of history to find a seasonal pattern.
Explore Demand forecastingDemand planningBase plan and live plan
Keep a baseline next to the live plan and measure how far the working plan moved.
Explore Base vs live planPlan the SKUs with no history
Bring your next launch and see it planned beside the forecast.