Back to home
Function · Inventory
Artellis builds a tool that watches run-rate and drafts the reorder before you run dry; you approve the PO.
The pain
Why this one is worth fixing
You find out a line is out of stock when a customer tries to order it. The reorder point was set in 2022, the run-rate has doubled, and nobody has time to re-tune it, so the alerts are noise until they are a problem.
What Artellis builds
A live watch on run-rate and lead times, with the reorder PO drafted before you run dry. You approve, the PO goes.
How it works
- 01Tracks real run-rate, not a static thresholdRolling 4- and 12-week rates, seasonally aware, per SKU.
- 02Drafts the PO before the shelf emptiesUses your usual supplier, the last agreed price and their real lead time.
- 03You approve, it sends and logsThe PO goes; the expected date is on the calendar; the reorder point retunes itself.
Example artefact
What the output actually looks like.
PO-00417 · Draft
Supplier: Northline · Lead time 5 days
SKU-204 · 48 units @ €12.40 = €595.20
SKU-207 · 24 units @ €9.10 = €218.40
Total: €813.60 · Expected: Fri 20 Jun
You edit and send.
Where it plugs in
Your inventory system / spreadsheetShopify / Unleashed / Cin7Xero / QuickBooksEmail to supplier
Guardrails
- Human-in-the-loop: nothing sends, signs or spends without you approving it.
- Your data stays yours, hosted in your tenant or a dedicated Artellis workspace, never used to train public models.
- Week-one build: something small and useful is live in the first week, before we scope anything bigger.
FAQ
How long until we see something working?
A first working version of the inventory tool inside week one. Refinement and rollout happen after you have seen it work against your real inputs.
What do you need from us to start?
About 45 minutes to walk through the current flow, sample inputs (emails, files, screenshots, whatever you actually work from) and one person on your side who owns the outcome.
What happens if the AI gets it wrong?
Every draft goes to a human before it leaves the building. When you correct it, the tool learns your standard so the next one lands closer to right.
Bring us this workflow
One workflow. One week. Something working.

