Forecasting
Look beyond this week’s sales.
Compare predicted sell-through, stock by size and inbound deliveries. Spot a broken size curve before the style looks sold out.
Inventory & merchandising
Plan the season. With more than a forecast.
Bring demand predictions, size curves, sell-through, returns, stock and contribution into one planning view. Build the buying app your team needs, or have agents monitor the season and prepare reorders and markdowns.
Season planningGermany · Knitwear
Black wool henley
240 units available
2.4wStock cover
- Sell-through
- 76%
- Return rate
- 12.4%
- CM3
- 32%
Today
3 weeks agoIn 4 weeks
ObservedProjected
ERP
100 units / week demand · 2-week supplier lead timeReorder 480 units. Review before sending to the ERP.
Trusted by the teams
behind leading brands.
Demand, margin and the next decision.
A season plan needs more than a stock count. Bring the commercial context into every reorder and markdown.
Product analysis
Plan by the role a product plays.
Separate seasonal stock from carryovers. Compare demand, return rate and contribution to decide what to reorder, promote or mark down.
Measurement included
Keep demand plans and spend connected.
Use MMM scenarios to explore marketing-driven demand alongside your stock plan. Feed forecasted sell-through into product advertising rules.
Agent examples
Keep the season moving within your rules.
Prepare reorders and markdowns, protect ad spend using forecasted sell-through, and catch size-level stock gaps.
Your instruction
Prepare weekly reorder and markdown suggestions from live demand, cover, and margin.
Reorder Planner
Runs Mondays 06:00- Queried modeled data
Demand velocity, stock cover, and margin by SKU and market · live
- Used skill: reorder-rules
Respect MOQs, lead times, and the season calendar
App examples
Plan the range. Review what arrives next.
Use the sell-through planner for product decisions and the control tower for inbound timing and replenishment. Review changes together before they reach the ERP.
You / App instruction
Build a sell-through planner where the team reviews reorders and pushes approved changes to the ERP.
Apps /Sell-through Planner···
Ask appSell-through Planner
Cover weeks, velocity & margin by SKU · non-DPA · Online
At-risk SKUs
14
Avg cover
4.2 wks
Reorder value
€182K
Markdown candidates
9
Sell-through (wk)
68%
Target cover
4 weeks
Market
All markets
Season
SS26
Sort by
Risk (high→low)
ProductCoverSell-throughS-TPrepared action
Black wool henley
DE
2.4 wks
82%Reorder 480
Sand twill chino
SE
6.1 wks
54%Hold
Ecru heavyweight tee
NL
1.8 wks
91%Reorder 320
Charcoal wool cardigan
US
11.2 wks
31%Markdown −20%12 reorders and 3 markdowns prepared → ERP
Awaiting approval · Merch leadQuestion examples
Make the mid-season calls with context.
Find styles behind pace, compare markdown options and check which sizes run out before the next delivery.
01 /Ask
Which products will break their stock cover in the next 4 weeks at the current run rate?
Ranked breaks with the revenue at risk
02 /Ask
Rank this season's styles by sell-through against plan and flag the ones behind pace.
Styles ranked vs plan, laggards flagged
03 /Ask
Which styles look healthy overall but break cover in a core size within the next 3 weeks?
Size breaks the style-level number hides
04 /Ask
List products over ten weeks of cover and the markdown depth that clears them by season end without killing margin.
Overstock ranked with margin-safe depths
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.
Connect your data once
Store, ad platforms, and logistics connect in about a day and stay maintained — nobody on your team owns a pipeline.
Describe this workflow
Prepare weekly reorder and markdown suggestions from live demand, cover, and margin.
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.
It's live for the whole team
Runs on schedule
LiveShared with the team
YLEMTAdjusted in chat
~40s
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.
Bring margin, stock and shared definitions into the same forecast. Review proposed reorders before they reach the ERP, with measurement available to inform the wider plan.
01
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.
02
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.
“Before, we struggled with fragmented insights from multiple tools. Now, with unified and enriched data from Dema's AI models, our strategic discussions are sharper, and our time spent on analysis is greatly reduced.”
Contribution
After costs. After advertising.
Net revenue€100,000
- Product costs
- − €40,000
- Operations
- − €15,000
- Ad spend
- − €25,000
Contribution margin20%
Defined once. Used by both.
ReportsAgents
03
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!”
Defined by your teamCurrency
Net revenue
Sales−Discounts−Returns
- Tax basis
- Excludes VAT
- Date basis
- Order date
Break down by
MarketProductChannel
04
Your rules. Your approval.
Set what a workflow can change and which actions need a person to review them. Budget moves, reorders and storefront updates stay within the permissions you set.
ERP
Reorder 480 units
Black wool henley · Germany
Order quantity (units)
- Current
- 0
- Proposed
- 480
Purchase orders need the buying team’s approval.
Lisa ErikssonBuying lead
ReviewerWaiting for approval
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.
Monday trading report
Shared
Lisa ErikssonCan edit
06
Measurement included.
Marketing mix modeling, incrementality testing and causal attribution are built into Dema. Bring that evidence into your questions, budget reviews and recurring workflows, alongside the rest of your commerce data.
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 actually on the shelf, whether the suggestions respect margin, and whether an approved reorder reaches the ERP. That is the difference between a prompt and a system.
Where the numbers come from
An AI assistant on your exportsA stock export from the moment someone downloaded it — stale by the time it is pasted.
DemaLive demand velocity, stock by size and market, and margin in one model.
What a metric means
An AI assistant on your exportsWeeks of cover and sell-through re-derived in the prompt, differently each time.
DemaDefined once by your team, then reused by every forecast, alert and suggestion.
Whether the recommendation holds up
An AI assistant on your exportsProjects a straight line from whatever columns it was given.
DemaSuggestions checked against margin — a markdown that kills profit never gets proposed.
Who gets it, and when
An AI assistant on your exportsWhoever remembers to re-run the prompt and paste the result into #planning.
DemaIn #planning every Monday at 06:00, with roles deciding who can change it.
What happens when the data is wrong
An AI assistant on your exportsIt answers anyway, in exactly the same confident tone.
DemaMissing feeds and impossible stock positions get flagged instead of forecast from.
What it is allowed to change
An AI assistant on your exportsNothing. You re-key every reorder into the ERP yourself.
DemaApproved reorders and markdowns push to the connected ERP.
Where it runs
An AI assistant on your exportsThe provider's default region, on the provider's terms.
DemaEU or US inference, your choice, and never used to train a model.
A one-off idea, right now
An AI assistant on your exportsGenuinely better. No setup, no connection, no context — just ask it.
DemaBuilt for the buying cycle that repeats, which is more than a throwaway question needs.
| An AI assistant on your exports | Dema | |
|---|---|---|
| Where the numbers come from | A stock export from the moment someone downloaded it — stale by the time it is pasted. | Live demand velocity, stock by size and market, and margin in one model. |
| What a metric means | Weeks of cover and sell-through re-derived in the prompt, differently each time. | Defined once by your team, then reused by every forecast, alert and suggestion. |
| Whether the recommendation holds up | Projects a straight line from whatever columns it was given. | Suggestions checked against margin — a markdown that kills profit never gets proposed. |
| Who gets it, and when | Whoever remembers to re-run the prompt and paste the result into #planning. | In #planning every Monday at 06:00, with roles deciding who can change it. |
| What happens when the data is wrong | It answers anyway, in exactly the same confident tone. | Missing feeds and impossible stock positions get flagged instead of forecast from. |
| What it is allowed to change | Nothing. You re-key every reorder into the ERP yourself. | Approved reorders and markdowns push to the connected ERP. |
| Where it runs | The provider's default region, on the provider's terms. | EU or US inference, your choice, and never used to train a model. |
| A one-off idea, right now | Genuinely better. No setup, no connection, no context — just ask it. | Built for the buying cycle that repeats, which is more than a throwaway question needs. |
Clarity and control
“Dema has given us the clarity and control we needed to scale profitably, ensuring we make the right decisions across inventory, marketing, and product strategy.”
Jorge de Castro
COO, Mikuta
Questions
Questions about forecasting sell-through
Down to SKU and size, per market. Cover, demand velocity, and margin are modeled at the level where the decision actually happens — a style can look healthy while two core sizes are about to break.
Yes. Lead times, MOQs, and pack sizes are constraints you set once. Reorder suggestions are sized against them, so a suggestion that cannot actually be ordered never reaches the queue.
Only approved ones. The default workflow prepares reorders and markdowns and waits for the team to review. You can keep it fully read-only, or let approved changes push to the connected ERP without re-keying.
Margin is checked before either is suggested. A markdown that kills the product's profit never gets proposed, and a suggestion is withdrawn when demand recovers — you see that reasoning on every line.
Impossible positions, missing feeds, and stale syncs get flagged instead of forecast from. Your team controls the checks, so a broken integration surfaces as an alert rather than a bad buying decision.
Bring your stock list
See which products would be flagged this week.
Build with Dema.