Put AI to workin retail.

Store sales, stock and the promotions calendar read together, so no store runs out of a promoted item.

The challenge

Why does one store run out of olive oil when the next one has plenty?

In a store chain, sales sit in the POS, stock in the ERP and the distribution centre's WMS, and the promotions calendar in a spreadsheet shared with marketing. Each store's order pulls all of this together, often from memory, with every supplier's lead times on top.

  1. 01

    Ordering on experience

    Each store orders from its sales history and the judgement of whoever is on shift. This week's promotion and the weather forecast only come into it when someone remembers them.

  2. 02

    Stock in the wrong store

    One store runs out of an item while another, twenty kilometres away, has two weeks of cover. Transfers get arranged over the phone, when they get arranged at all.

  3. 03

    Margin known at month end

    Supplier funding and shrinkage move the margin every week. Margin by category and by store only becomes clear once the month has closed.

Day to day

Questions that finally get answers

  1. Did the last olive oil promotion bring in margin or just volume?
  2. Which suppliers deliver late most often?
  3. Which stores have the most fresh food waste this month?
  4. How much dairy should we order for week 43?
  5. Which products could we delist without losing sales?
AI at work

Each store gets what it is going to sell.

AI brings together POS sales, stock in the ERP and the distribution centre, the promotions calendar and supplier lead times. From there it forecasts demand by store and by product and suggests orders and transfers for your team to approve.

Stock‑outs during the promotion

Stock cover in each store for the promoted items, with stock‑outs flagged before the promotion starts.

Stock sitting in the warehouse

Slow‑moving SKUs checked against demand in each store, so the stock moves before it has to be marked down.

Margin by category

Gross margin by category after supplier funding and shrinkage, every week, with the effect of each promotion in view.

Supplier orders

Orders suggested from the forecast and each supplier's lead time, then approved by Buying.

Illustrative figures.

The data you already have, put to work

We connect to the systems you already have, without replacing them, and you decide which data each agent can read.

  1. Works with what you already use

    ERP, CRM, email and documents stay where they are, and nobody has to move to a new system.

  2. Reads and cross‑checks your data

    Brings together what is scattered today and finds what does not add up.

  3. Proposes, you approve

    Every sensitive action goes to whoever has the authority to approve it.

  4. Acts and keeps a record

    Works inside your team's systems and records where every decision came from.

One region and one product family to begin with.

We pick a group of stores and a family with frequent stock‑outs, such as dairy, and set the forecast side by side with what the team would have ordered. When the numbers justify it, we extend it to the rest of the network.

  1. 01

    Assessment

    We map the operation and the data and choose what reaches production first.

    • Data sources mapped
    • Opportunities assessed
    • Scope and plan agreed
  2. 02

    First system in production

    We build in the tools you already use and put the system to work on real cases.

    • ERP, POS and distribution centre connected
    • Demand forecast in production
  3. 03

    A team that runs it

    Your team takes the system over and we choose the next process together.

    • Buying team approving suggestions
    • Next process chosen

Frequently asked questions

Can't find your answer? Ask us directly, on a 30-minute call.

Book a call
What data do you need from the POS and the ERP?

From the POS, sales by store and by product, which arrive as a daily export or straight from the database. From the ERP we read stock, orders and supplier terms through the API or scheduled exports, and suggested orders go back into the ERP as proposals for approval.

Does the forecast account for promotions, bank holidays and the weather?

It accounts for anything with history behind it: the promotions calendar and the effect of past promotions, national and local holidays, and the weather forecast for sensitive categories such as drinks and ice cream. A promotion with no comparable history is flagged for the team to check the quantity.

Do orders go to the supplier on their own?

Only if you want them to, and within the limits you set. By default, each suggested order reaches Buying with the quantities, the dates and the reasoning behind each figure, and goes out once approved.

What about franchised stores?

They can be included if they share sales and stock, even as a daily file. Each store has its own forecast, and head office sees the whole network, owned and franchised, on the same dashboard.

Saturday's stock‑outs are decided by Monday's order.

On a 30-minute call we will work out which stores and categories are worth starting with.

Book a call
Not ready for a call yet. I would rather send a question.

Write down the question your operation cannot answer today. We will reply by email with how to get there.