Merchandising
Rank every page by profit, not by gut.
Bestseller logic buries the products that actually make money. Rank collections and category pages on margin, sell-through, and traffic — with stock and size eligibility enforced — and push the approved order to Shopify.
Agent examples
Agents that merchandise while you sleep.
One rebuilds the bestseller collection every Monday with the team's eligibility rules — no broken sizes, no sale items, no near-stockouts. One re-ranks category pages per market and stages the order for approval.
Collection Curator
Runs Mondays 06:00
Rebuild the “Most popular” collection in Shopify every Monday from actual sales — excluding sale items and anything with broken sizes.
Reasoning
“Two of last week's top sellers are missing core sizes and one is mid-markdown — putting them in “Most popular” would merchandise a bad experience.”
Queried modeled data
Units sold, margin, stock by size, and markdown status · last 7 days
Used skill: collection-eligibility
Exclude sale-tagged items, broken curves, and under 3 weeks of cover
Ranked the collection
24 products · 5 swapped in, 5 rotated out
Collection updated in 3 storefronts
Applied automaticallyShopify
Swap list posted to #merch with the reason for each change
App examples
The studio where the ranking gets decided.
Margin, sell-through, and traffic weighted by the merch team themselves, per market — with the new page order staged, reviewed, and pushed to Shopify on approval.
Apps /PLP Ranking Studio···
Ask appPLP Ranking Studio
Category page ranking · margin, sell-through & traffic · per market
Pages ranked
18
Products moved
64
Proj. margin uplift
+€8.2K/wk
Markets
4
Staged changes
3 pages
Ranking weights · set by the merch team, per market
Contribution margin40
40% of score
Sell-through35
35% of score
Traffic25
25% of score
Market
Germany
Page
Knitwear
Season
SS26
Compare to
Current order
ProductMoveMarginSell-through
Field overshirt
Oat knit crewneck
Cream boxy tee
Navy linen polo
New ranking staged for 3 category pages → ShopifyQuestion examples
The questions merch argues about mid-season.
Which products are buried, which are selling below cost, where the size curve broke — answered on the same numbers the ranking 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.
Rebuild the “Most popular” collection in Shopify every Monday from actual sales — excluding sale items and anything with broken sizes.
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 ranking is the easy part.
What makes it safe to publish is everything underneath: margin and stock in one model, eligibility rules the AI cannot skip, and a workflow where the storefront 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.
“The most valuable thing with the agent is that I can tell it what I want to figure out, let it write its own prompt, run the analysis, and come back to a finished report. I don't have to build it manually anymore.”
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 ranking knows what is on the shelf, whether the eligibility rules survive whoever runs it, and whether the new order actually reaches the storefront. 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 product export with sales columns — no live stock, no sizes, no margin after returns.
Dema
Margin, sell-through, stock by size, and traffic in one live model.
What a metric means
An AI assistant on your exports
“Bestseller” re-derived in the prompt — units, revenue, or margin, depending on who asks.
Dema
Ranking logic defined once by the merch team, then reused every week.
Whether the recommendation holds up
An AI assistant on your exports
Ranks by last month's units and calls it demand.
Dema
Eligibility enforced — broken size curves and near-stockouts never get promoted.
Who gets it, and when
An AI assistant on your exports
Whoever remembers to re-run the prompt and re-order the page by hand.
Dema
The collection rebuilds every Monday at 06:00, rules included.
What happens when the data is wrong
An AI assistant on your exports
It answers anyway, in exactly the same confident tone.
Dema
A stale stock feed gets flagged before it merchandises a stockout.
What it is allowed to change
An AI assistant on your exports
Nothing. You drag products around the storefront yourself.
Dema
Approved rankings and collections publish to Shopify.
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 pages that re-rank weekly, which is more than a throwaway question needs.
Product-level clarity
“We finally have full visibility into what drives both growth and profitability, down to the product level. It's helped us make faster, smarter decisions across marketing, merchandising, and planning.”
Jeanette Dyhre Kvisvik
CEO, Villoid
Questions
Questions about profit-based merchandising
Yes — that is the point. The merch team sets the weights across margin, sell-through, and traffic themselves, per market, and can change them any time. The ranking logic is yours, not a black box score.
Eligibility rules run before anything is ranked: broken size curves, sale-tagged items, and products under your cover threshold are excluded automatically — and come back on their own when they qualify again.
Only what you approve. Collections can rebuild on a schedule with your rules enforced, while page re-rankings are staged for a named approval before anything changes in Shopify. You choose per workflow.
Yes. Rankings, weights, and eligibility run per market — what tops the page in Germany can differ from Sweden because demand, margin, and stock differ. One setup, every storefront.
The same data works on the floor: zone placement joined to style-level sales and stock lets you see which placements earn their position — the store money map is built by describing it, like any other app.
Bring a category page