Before
- Static, rule-based forecast blind to recent demand peaks
- 50% of output rebuilt manually every cycle
- 10/30-day history only
- Manual, inconsistent supplier-rule compliance
- Inventory discipline (DIO) not actively held
>49pp
manual override reduction, from 50% to under 1%
~7h/day
planner time returned
99%+
forecast accuracy, with under 1% of lines overridden
Time to result: 2 weeks
Pilulka forecast demand for ~18,000 SKUs with fixed rules that did not react to recent demand peaks or emerging trends.
Planners manually overrode 50% of the output each cycle, effectively rebuilding half of every forecast.
Before
After Duvo
Duvo helps us react to shifts in demand far earlier. Instead of deciding mainly on ten-day or thirty-day views, we see the signals from the last three days and can act on them before the problem ever shows up in availability.

Petr Marek
Supply Chain Manager, Pilulka
Reads demand across three windows
Duvo reads sales over the last 3, 7, and 30 days. The shorter windows catch newly trending products even when the 30-day history remains weak.
Forecasts across the full assortment
Duvo generates a per-SKU forecast across all 18,000 SKUs in ~1h20m, selects the lines that need action, and recommends quantities. It compares each line with the existing forecast and flags the predicted stock-out day from current sales velocity.
Applies every constraint
Duvo applies minimum stock, DIO, carton, MOV/MOQ, order-day, promotion, assortment, and clearance constraints to every recommendation.
Solves the minimum-order gap
When a line reaches at least 90% of the supplier's minimum order value, Duvo proposes how to fill the remaining 10% and clear the threshold.
Explains every recommendation
Duvo records the reason for every recommendation so the planner can check the logic before approval.
Outcome
>49pp manual override reduction, from 50% to under 1%
Systems involved
Static rule-based system forecast, Warehouse and stock data, Supplier order rules, Promo / campaign data
Control points