Eight checks, in the same order, on every run.
The engine runs daily for fast categories and weekly for slower ones. Each run follows the same eight steps, so every recommendation can be traced back to the data and rules behind it.
From signal to decision.
Read the signals
Sales history, stock on hand and on order, plus calendar, weather and sports feeds.
Expected demand
The normal weekly rate, multiplied by what the same event did last year in that region.
Compare with what we hold
Stock on hand plus on order, against the demand just calculated.
Fork
Selling faster than we hold goes to buying. Holding more than we can sell goes to promoting. Matched stops here.
Branch checks
Buying: can we afford it, can the supplier deliver in time? Promoting: is it safe and appropriate here, now?
Work out the number
A quantity and order-by date, or a lever, depth and sell-through target.
Apply the ceilings
Budget, storage and shelf life for buying. Margin floor and brand limit for promoting.
Send it
To a buyer for approval, live through the cart, or to your systems as a recommendation.
02Six levers
The fix isn’t always a discount.
Zyntel asks one question of every product, every day: is it in trouble, or about to be? Then it recommends the cheapest fix that works, and explains why in plain words.
Every product, every run
Is it selling faster than we hold, or holding more than we can sell?
The engine compares expected demand, including events ahead, with stock on hand and on order.
Selling faster than we hold
Buying path
Buy
A reorder quantity and an order-by date, worked back from the supplier’s lead time. Capped by open-to-buy, storage and shelf life.
Holding more than we can sell
Promoting path · cheapest fix first
Move
Send it where it sells: another store, region or warehouse.
Get seen
Put it in front of more people through creators and affiliates.
Wait
A festival or season is coming that clears it at full price.
Discount
Step down the category’s ladder, above the margin floor.
Exit
Clear to an outlet, bundle or liquidator and free the space.
Keeps marginCosts margin for good
09Walkthrough on your data
Bring one category. See tomorrow’s worklist.
We load a sample of your catalogue, sales and stock, run the engine on it, and walk you through every recommendation, the reason behind it and what it would have earned.
Go live with as few as 100 SKUs and any length of sales history.
- Your catalogue and stock, loaded
- SKU health and risk scores
- Buy, move and markdown calls
- Festival effects for your regions
- Your brand and store rules
- Live cart or recommendations only
- What it would have saved
- A rollout plan by category