Logistics / Supply ChainNewVerified Real deployment at a named or precisely described company, with a measured result from a primary source.

AI moves fast-selling items closer to the pickers and shortens pick routes in the warehouse (Coram, Gildemeister)

Added 2026-10-28 · Last updated 2026-10-28

Manufacturers in this case: Coram · all manufacturers using AI

Role

Logistics (warehouse: where each item is stored and the route pickers walk) · Typical users: warehouse manager or supervisor, order picker, inventory planner, logistics manager, WMS administrator

The problem

In a finished-goods or spare-parts warehouse, items are often stored where there was room when they arrived, and pick routes follow a fixed order. Demand changes every week, so fast-selling items end up at the back or on top shelves, and pickers walk far for each order line. In peaks, the company hires temporary workers or pays overtime to keep up. Coram, a Dutch manufacturer of bathroom fixtures and accessories exporting to more than 50 countries, faced rising labour demands as order volumes swung with promotions and large projects. Automotores Gildemeister, a vehicle distributor and dealer group in Chile, Peru and Costa Rica, manages more than 53,000 spare-parts SKUs; its old tool reclassified inventory only once a month, so fast-moving parts could stay outside the best locations for weeks, and each peak season it hired three extra workers just to keep up with picking.

How AI helps

Two related uses of AI on warehouse transaction history. Pick path optimization: instead of a fixed route, the system computes a shorter route through the warehouse for each pick list, without changing the layout. Dynamic slotting: a machine-learning model reads 12 months of picks, finds the small share of items that make up most of the picks, and recommends moving them to the 'golden zone' (the locations closest to the pickers and at waist height); it reruns daily as demand changes. The recommendations feed the warehouse management system (WMS), so workers keep following their usual put-away and pick instructions.

Step by step

1. Export 6 to 12 months of pick lines (item, location, date, quantity) and the list of locations with their zone and height.
2. Rank items by number of picks, not by value, and see how many items make up 80% of the picks.
3. Mark your golden-zone locations (closest to the shipping area, waist height) and check how many of your top items are actually there.
4. Plan the moves in small waves (for example the top 50 items that are badly placed), during quiet hours, and update the WMS locations at the same time.
5. Measure picks per hour or travel time before and after each wave; then decide whether you need a slotting module that reruns automatically.
6. Repeat the ranking monthly or after seasonal changes, so the golden zone does not fill with items that no longer sell.

Tools

• Infor WMS with Infor Velocity Suite (AI pick path optimization): used at Coram
• Infor AI/ML (Infor Velocity Suite) and Infor Data Fabric, dynamic slotting engine connected to Infor WMS: used at Gildemeister
• Other tools to evaluate: the slotting module of your WMS (for example Mecalux Easy WMS Slotting, Manhattan, Blue Yonder, SAP EWM), Lucas Systems dynamic slotting, Optricity
• For a first analysis without new software: a pick history export plus any LLM (ChatGPT, Claude, Copilot, Gemini) with the prompt below, and a spreadsheet for the counts

In the AI tools index: Infor Velocity Suite (Infor WMS) · all AI tools used by manufacturers

As reported by the source; most figures are vendor or self-reported and not independently verified.

Human review: cautions

• Both stories are published by the vendor (Infor); none is independently verified. Gildemeister is a distributor, not a manufacturer, but its spare-parts warehouse works like a manufacturer's parts or finished-goods warehouse.
• Gildemeister's productivity and on-time-in-full gains are for its whole digitalization program; only the golden-zone, travel, overtime and temporary labour figures are tied to slotting.
• Moving items costs labour and creates picking errors if the WMS location is not updated at the same time: move in small waves.
• Check weight, safety and ergonomics rules before moving items; the best location for speed is not always allowed.

You are a warehouse improvement analyst at a manufacturer.

I will paste: (1) a summary of our pick history by item [item code, description, number of pick lines in the last 12 months, current location, zone, shelf level]; (2) our location list [location, zone, shelf level, distance class: near / middle / far from shipping]; (3) item constraints [heavy, fragile, hazardous, must stay with another item].

Do this:
1. Using the pick-line counts as given, list the items in order of pick lines, and mark the items that are in the top group but stored in a 'far' location or on a top or bottom shelf.
2. Propose up to 50 moves: item, from location, to location, reason, and any constraint that limits the move. Never place heavy items on high shelves or break a constraint I gave.
3. Group the moves into waves of about 10 that can be done in one quiet shift.
4. List items with no picks in 12 months as candidates to move out of the picking area, marked 'CHECK WITH PLANNING'.
5. Write a short instruction for the team doing the moves, including updating each location in the WMS at the moment of the move.

Do not compute percentages, totals or travel savings yourself: tell me which spreadsheet formulas to use. Use only the data I paste in; if something is missing, write 'not found' or list it as a question instead of guessing. Do not send, order, post or change anything in any system: produce drafts for my review and approval.

Related cases

• AI orchestrates a plant-attached warehouse: more loads shipped straight from the plant, fewer shuttle moves (P&G Lima)
• Inventory drones count the plant warehouse on a regular schedule, so inventory is right without stopping production (LAPP USA, GKN Automotive, Hyundai Glovis)
• Cameras at the dock door read every pallet and stop the wrong one before it is loaded (Yazaki, Danfoss, a flooring manufacturer)
• AI predicts when shipments will really arrive, so planners act before a late delivery stops a line (Faurecia, Magna)

All 12 Logistics / Supply Chain use cases →

Sources

• https://www.infor.com/en-gb/customer-stories/improving-labor-efficiency-ai-driven-warehouse-pick-path-optimization
• https://dam.infor.com/api/public/content/0ec52d499e074ee6bfbebc175f2b2d77?v=91b86a28