Inventory & operations
See the stock problem before it costs you.
Stockouts and overstock both show up too late in spreadsheets. Watch predicted sell-through against inbound orders, get replenishment prioritized daily, and give the warehouse its volumes before they ask.
Agent examples
Agents that run the operations rhythm.
One gives the 3PL a 35-day capacity forecast in their own sheet every Monday; one prioritizes NOOS replenishment daily against lead times; one watches the shipping backlog before customer service feels it.
Warehouse Forecaster
Runs Mondays 06:00
Forecast 35 days of outbound volume and inbound returns per warehouse, and deliver it to the 3PL in Google Sheets every Monday.
Reasoning
“The campaign calendar adds a spike in week 3 and returns from the last drop peak the same week — the 3PL needs both numbers, not just outbound.”
Queried modeled data
Order forecasts, return rates by drop, and campaign calendar · 35 days out
Used skill: forecast-vintages
Track every forecast against actuals and tune the model on the misses
Built the forecast
2 warehouses · outbound and returns, daily granularity
Forecast written to the 3PL's sheet
DeliveredGoogle Sheets
Summary emailed to logistics with forecast accuracy attached
App examples
The control tower ops actually opens.
Stockout risk, cover weeks, and the inbound timeline in one view — with a reorder queue where approved orders push to the ERP instead of being re-keyed.
Apps /Replenishment Control Tower···
Ask appReplenishment Control Tower
Stockout risk vs inbound timeline · NOOS & seasonal · all warehouses
SKUs at risk
23
Revenue at risk
€214K
POs inbound
7
Median cover
5.8 wks
Queue
9 reorders
Warehouse
All warehouses
Assortment
NOOS
Horizon
8 weeks
Sort by
Risk (high→low)
ProductCoverInboundPrepared action
Black wool henley
1.9 wks
PO #2214 · Jul 18Air freight 320
Ecru heavyweight tee
2.6 wks
PO #2209 · Jul 4Reorder 640
Stone selvedge jeans
3.1 wks
None plannedReorder 280
Sand twill chino
7.4 wks
PO #2201 · Jun 27Hold9 reorders and 1 air-freight request queued → ERP
Awaiting approval · Ops leadQuestion examples
The calls ops has to make this week.
Air freight or wait, retire or promote, how much revenue a stockout would cost — answered on the same forecasts the control tower runs on.
Getting started
Live before the end of the week.
No implementation project, no code, no analyst backlog — connect once, describe the workflow, and the whole team has it.
01
Connect your data once
Store, ad platforms, and logistics connect in about a day and stay maintained — nobody on your team owns a pipeline.
Forecast 35 days of outbound volume and inbound returns per warehouse, and deliver it to the 3PL in Google Sheets every Monday.
02
Describe this workflow
Type what you want the way you'd brief a colleague. Every example on this page is a real prompt — that sentence is the whole setup.
Runs on schedule
LiveShared with the team
YLEMTAdjusted in chat
~40s
03
It's live for the whole team
Scheduled, shared, and permissioned from day one. Teammates use it without setting anything up, and changes happen in chat.
See this on your own data
Leave your email and pick a time — we'll walk through this workflow live on a 20-minute call.
The forecast is the easy part.
What makes it worth ordering against is everything underneath: stock and margin in one model, definitions ops set once, and a workflow where the ERP change waits for a name.
01
The number is CM3, and everyone gets the same one.
Orders, spend, COGS, fulfilment and returns are reconciled into one profit figure. Marketing, finance and merchandising stop arguing about which export is right.
Profit waterfall
Revenue to CM3 breakdown for the current period. Each row shows the contribution or cost deducted.
Revenue
€284,000
COGS
−€112,000
Gross Profit
€172,000
Ad Spend
−€52,300
Shipping & Returns
−€28,400
Fixed Costs
−€18,700
CM3
€72,600
02
The AI never has to guess what a metric means.
Your metrics, markets and relationships are modeled before AI touches them, so it reads the definition your team set instead of inferring one from raw tables.
“Dema's Agent is truly mind-blowing. We struggled to get AI to understand our data structures and metrics, but Dema worked perfectly right out of the box. It's the first tool that truly understands our data from the very first prompt!”
Metrics
Select which metrics to include in this analysis. The agent will track and report on all selected metrics.
Search metrics
Available metrics
Revenue
Contribution Margin 3
ROAS
New Customer Rate
Impressions
CPA
Sessions
AOV
4 of 8 selected
03
Margin and stock in one model, not two tools.
Sell-through by size, weeks of cover and inventory as of any past date sit beside spend and profit — so pushing harder gets checked against what is on the shelf.
“Dema has been a game-changer for our brand. It's given us the clarity and control we needed to scale profitably, ensuring we make the right decisions across inventory, marketing, and product strategy.”
04
It already knows how your company works.
Organisation-wide instructions set the rules every agent follows, and each person's own preferences sit on top. New joiners inherit the house standard instead of learning it.
Organization instructions106/1500
Prioritize profit over revenue in all analyses. Always report CM3, not CM2. Focus on Nordic markets first.
Personal instructions129/1500
Show me weekly trends by default. Include new customer contribution in all reports. Highlight anomalies with a brief explanation.
05
A good prompt lives on one laptop. This runs for the team.
Share it, set who can edit, and have it delivered into Slack on a schedule. When that person leaves, the workflow stays.
Share
Share this analysis with team members or generate a public link for stakeholders.
People with access
Y
You
you@company.com
LE
Lisa Eriksson
lisa@company.com
MT
Marketing Team
team channel
Link settings
Anyone with the link can view
06
The tool your team wanted, live this afternoon.
Build the app around how the team actually works instead of waiting for a roadmap. Anyone who can describe the change can make it.
“With Dema Agent, what took two people three to four months now runs in a single command. We built 20 skills in three weeks without writing a line of code.”
Weekly Performance: NordicsMar 31 – Apr 6
07
Teams like yours already shipped this.
More than a million AI actions run inside Dema every month, at brands like Acne Studios, Axel Arigato and Represent. These are workflows their own commercial teams built, not pilots a vendor set up.
AI actions run in Dema every month
1M+
Anyone can get an answer once.
The question is whether the forecast knows what is inbound, whether the 3PL gets their numbers without you, and whether an approved reorder reaches the ERP. That is the difference between a prompt and a system.
An AI assistant on your exports
Where the numbers come from
An AI assistant on your exports
A stock snapshot from whenever it was exported — no inbound, no lead times, no returns flow.
Dema
Live stock, predicted sell-through, inbound orders, and margin in one model.
What a metric means
An AI assistant on your exports
Weeks of cover re-derived in the prompt, differently each time someone asks.
Dema
Cover, risk, and priority defined once by ops, then reused by every forecast.
Whether the recommendation holds up
An AI assistant on your exports
Projects a straight line and calls it a forecast.
Dema
Sell-through predicted per SKU and checked against its own forecast history.
Who gets it, and when
An AI assistant on your exports
Whoever remembers to re-run the prompt and email the 3PL a spreadsheet.
Dema
The 3PL's sheet updates every Monday at 06:00, accuracy tracked.
What happens when the data is wrong
An AI assistant on your exports
It answers anyway, in exactly the same confident tone.
Dema
Impossible stock positions and stale feeds get flagged instead of forecast from.
What it is allowed to change
An AI assistant on your exports
Nothing. You re-key every reorder into the ERP yourself.
Dema
Approved reorders and air-freight requests push to the connected ERP.
Where it runs
An AI assistant on your exports
The provider's default region, on the provider's terms.
Dema
EU or US inference, your choice, and never used to train a model.
A one-off idea, right now
An AI assistant on your exports
Genuinely better. No setup, no connection, no context — just ask it.
Dema
Built for a replenishment cycle that repeats, which is more than a throwaway question needs.
Prediction in production
“Our collaboration has been nothing short of a revolution. Dema's solution is now the beating heart of our operation and we'll keep evolving and growing together.”
Questions
Questions about inventory & operations workflows
As far as the decision needs. Replenishment runs on a rolling horizon against lead times, the warehouse forecast covers 35 days of outbound and returns-inbound volume, and stockout risk is projected per SKU against what is actually on order.
Yes. Every risk figure is netted against inbound — a product two weeks from breaking cover with a PO landing in one week is not a problem, and the forecast knows the difference.
Those are constraints you set once. Suggestions are sized against them, so a reorder that cannot actually be placed never reaches the queue — and end-of-life shortlists factor the MOQ before proposing a repeat.
In their own Google Sheet, updated every Monday before their capacity planning, with forecast accuracy tracked against actuals. No exports, no email chains — the same numbers your team sees.
Only approved ones. The default workflow prepares reorders and air-freight requests and waits for a named approval — you can keep everything read-only, or let approved changes push without re-keying.
Bring your stock list