Case studies
Five warehouses, five different reasons to stop counting by hand.
Ten sites across five countries run Sentispec Inventory in production. The five studies here are what different operations actually bought it for, and each one measured something different.
Each of the five bought the same thing, a camera unit on a forklift they already owned, and used it for something different. Every figure on this page is measured at a live site after go live, and the benchmark states the method behind each one. To put your own audit cost and count frequency against them, the ROI calculator needs no form.
Six operations
What each one was trying to fix.
The outcomes are above. These are the problems that sent each operation looking in the first place, which is usually the better guide to whether a site resembles yours.
Three warehouses priced as three of everything
Every counting method the operator had priced put fixed equipment or an autonomous vehicle into each building, so the cost scaled with buildings rather than with pallets. The audit was the expensive part, not the count.
ManufacturingA wind turbine plant was losing production time
Low inventory accuracy was stopping lines, and manual stocktaking could not keep pace with high value, high tempo manufacturing. By the time a count was reconciled, the floor had already moved.
3PL, retail and fashionA global 3PL was absorbing its clients' audit load
Clients required frequent, comprehensive audits of 30,000 to 100,000 pallets, and an out of stock caused by a wrong record hits the client's revenue. The labour came out of a single digit margin.
3PL, multi customer hubA three warehouse hub was counting blind between events
Two wall to wall scans of 90,000 pallets a year, and no real time inventory visibility in between. Whatever the last count found was the best available answer for the following six months.
Pharma, cold storeA pharmaceutical site was sending people up scissor lifts
Stocktaking was slowest and costliest in cold storage, where labour cost and regulatory constraints are both higher, and reading high locations meant raising employees to racking height.
The ten sites
Ten live deployments, and what each one measured.
Every live deployment, not a selection. Accuracy is measured after implementation, and break even is the point at which the site had recovered its cost.
| Location | Pallet locations | Accuracy after go live | Sector | Value realised | Break even |
|---|---|---|---|---|---|
| Duisburg, Germany | 30,000 | 99.9% | Retail and fashion | 95% lower stocktaking cost, 90% fewer loading errors | 1 month |
| Cuxhaven, Germany | 5,000 | 99%+ | Manufacturing | 95% fewer stock errors, production stops eliminated at €7,000 loss per minute | 1 month |
| Łódź, Poland | 15,000 | 99.99% | Manufacturing, retail and fashion | 90% lower stocktaking cost, 90% fewer loading errors | 3 months |
| Bremen, Germany | 35,000 | 99.5% | Retail and fashion | 85% lower stocktaking cost, 90% fewer loading errors | 3 months |
| Mechelen, Belgium | 65,000 | 99.99%+ | Retail | 95% fewer put away errors, 90% lower stocktaking cost | 3 months |
| Venlo and Roermond, Netherlands | 85,000 | 99%+ | Retail and fashion | 95% lower stocktaking cost | 4 months |
| Willebroek, Belgium | 29,000 | 99.99% | Retail and fashion | Contract renewed, 90% lower stocktaking cost, 9 point accuracy gain | 5 months |
| Kolding, Denmark | 25,000 | 99%+ | Food | 80% lower stocktaking cost, 80% fewer loading errors | 6 months |
| Horsens, Denmark | 40,000 | 99%+ | Retail | 85% lower stocktaking cost, 90% fewer loading errors | 6 months |
| Geel, Belgium | 7,000 | 99.99%+ | Pharma | 85% lower stocktaking cost, alignment with safety regulation | 6+ months |
Break even runs from 1 month to 6 months and beyond, and the spread is mostly explained by how expensive the manual count was to begin with. See the benchmark page for the method behind every column.
Next step
Ask us for the site that looks most like yours.
A 30 minute demo using recordings from a warehouse with your racking, your label format and your count frequency.