Optimises stock levels and reduces tied-up capital.
Developed in Germany · Hosted in the EU or on-premises
Delivered together with
Sovereign hosting in Germany, single-tenant from the first user.
Legal, tax and compliance expertise for legally sound deployment.
Advisory and implementation for the public sector, starting with the AI readiness assessment.
The target cover is set once for the whole product group, usually based on the worst delivery anyone can remember. Anyone who wants to change it has to calculate two figures separately: the replenishment lead time from recent deliveries and the safety stock from sales variability and lead time variability. With 180 items per product group, someone does the maths for the twenty most important and never for the rest.
The 20% less excess stock comes from the 180 items that run on four weeks of target cover, even though replenishment lead time and calculated safety stock together cover fifteen days and sales have been stable for eight months.
The 20% reduction in excess stock is this agent's headline figure. The 180 planned items and the eleven-day replenishment lead time represent an ordinary dry goods product group; none of it was measured.
The agent reads 24 months of sales from the ERP and separates baseline demand, seasonality and promotional peaks. It flags items with erratic demand separately.
Forecast sheet for dry goods, 180 items, 24 months of historyThe agent measures the replenishment lead time from recent deliveries and, alongside it, calculates the safety stock from sales variability and lead time variability. It compares both figures with the stored target cover.
Item TS-40118 pasta 500 g: target cover 28 days, replenishment lead time 11 days, safety stock 4 daysThe agent produces a proposal per item with quantity, date and the resulting cover. Purchasing opens the list in the ERP and places the orders.
Proposal list with 52 lines, 12 of them with a changed quantityIt presents quantity, date and the resulting cover. Every line is approved in the ERP by the buyer who manages the product group.
It works with the lead times of the last 24 deliveries. Purchasing weighs that against what was agreed in the annual review.
The secondary placement for week 40 multiplies demand for two weeks. Until the date is booked, it plans on baseline demand, and purchasing adds the promotional quantity by hand.
Connected systems
Operations
A pilot typically runs on your own data within 4 to 6 weeks. The agent connects to your existing systems rather than running as a separate, parallel environment.
EU cloud or private cloud. Processing is GDPR-compliant and models are never trained on your data. Details in the Trust Center.
It is based on experience from comparable projects and process benchmarks, not a commitment. We work out the realistic effect for your organisation during the assessment before the pilot.