Predicting stock-outs before they happen
An AI agent for a UK retailer with 22+ stores and 5 warehouses that predicts stock-outs from events and demand signals, and recommends what to move where.
saved every month
and 5 warehouses
replenishment planning
the situation
Replenishment across stores and warehouses was planned by hand by a 10-person team, and manual errors were expensive.
the hard part
Demand moves with events, so planning from averages misses exactly the spikes that cause stock-outs. The system had to see them coming and say what to do about them.
what i built
Central data pipeline
One view of stock and sales across 22+ stores and 5 warehouses.
Event-aware demand forecasting
Forecasts demand using events and other criteria, not just history.
Stock-out prediction and recommendations
Flags likely stock-outs ahead of time and recommends what to move where.
Automated replenishment
Replenishment plans generated automatically, removing manual error.
how it fits together
results
- $65K a month in cost reduction.
- Replenishment planning automated, replacing manual work by a 10-person team.
stack
next case study
Sovereign AI for a national defence programme
Private, air-gapped AI that connects intelligence from across the globe and predicts whether critical assets are ready for a mission.
Air-gappedno data leaves controlled infrastructure
Sovereignmodels trained and served in-house