Agentic data platform
Intelligence needs a foundation
A commerce-native semantic layer with every entity — orders, products, customers, inventory, marketing, costs — modeled for agents. Not a chatbot on dashboards. Real AI reasoning over structured commercial data.
Orders
Products
Inventory
Costs
Stores
Sessions
Creatives
Marketing
Customers
Semantic layer
Commerce-native schema that unifies orders, marketing, customers, and inventory into one model the agent can reason over.
Profit depth
Revenue to CM3 — real profit after every cost, discount, return, and fee. Not vanity ROAS.
Smart modeling
Returns, cost rules, joins, and tracking configured for real-world complexity — not spreadsheet hacks.
Agent-native semantic layer
One schema the agent, dashboards, and reports all share
GA4 + Shopify + ad platforms + Excel = conflicting numbers. Dema replaces the patchwork with a commerce-native semantic layer. Every entity, metric, and relationship is modeled so the agent can reason across your full business — not just query a table.
Commerce data model
The unified schema the agent uses to reason across all connected sources. Metrics are auto-mapped or manually configured.
MetricSourceTypeStatusRevenueShopifyCurrencyMappedAd SpendGoogle Ads, MetaCurrencyMappedROASComputedRatioMappedImpressionsGoogle Ads, MetaIntegerMappedContribution Margin 3Shopify + CostsCurrencyMappedNew Customer RevenueShopifyCurrencyUnmappedSessionsGA4IntegerUnmapped
Orders
Revenue, COGS, fulfillment, shipping, returns, discounts, profit at every level.
Marketing
Spend, impressions, clicks, campaigns, ad sets, ads — connected to orders, not siloed.
Customers
New vs. returning, cohorts, order sequence, LTV predictions, acquisition source.
Inventory
Stock levels, incoming, size curves, warehouses, days of supply, sell-through forecasts.
Sessions
Visits, product views, impressions, landing pages, devices — down to product and country level.
Creatives
Images, video, headlines, CTAs, format — linked to performance, not just ad metrics.
Stores
Physical store sales, and inventory — unified with online data for true omnichannel visibility.
Costs
Transaction fees, shipping, customs, pick & pack — per country, per provider. Real P&L, not estimates.
Returns
Return rates, reasons, refund amounts, and restocking timelines — tracked per product, country, and channel.
Smart modeling
Configured for real-world complexity
Returns, cost rules, joins, and tracking — the details that separate a toy model from a production one. Every rule updates profit metrics in real time.
Return #4821
| Order placed | Day 0 | €89.00 | |
| Return estimated (33% risk) | Day 5 | −€9.80 | |
| Return requested | Day 12 | ||
| Return shipped | Day 15 | −€7.43 | |
| Return received | Day 19 | Inspected | |
| GP3 adjusted | Day 20 | −€15.33 |
Return handling
Every return event — shipping refund, restocking, inspection — adjusts GP3 automatically. No manual reconciliation.
CostsCurrencyPer orderPer itemPer shipment% of value
Transaction costsEUR ▾0000%
Shipping costsEUR ▾10000%
Country: AustriaEUR ▾7,43000%
DHLEUR ▾3,75000%
UPSEUR ▾7,5000%
DHL ExpressEUR ▾4,3000%
Add row
CostsCurrencyPer orderPer itemPer shipment% of value
Transaction costsEUR ▾0000%
Shipping costsEUR ▾10000%
Country: AustriaEUR ▾7,43000%
DHLEUR ▾3,75000%
UPSEUR ▾7,5000%
DHL ExpressEUR ▾4,3000%
Add row
Cost rules
Transaction fees, shipping, customs, pick & pack — per country, per provider. Your P&L reflects reality.
Automatic joins
Marketing, orders, products, and inventory join automatically across sources. No manual data stitching or SQL.
Own tracking
Dema's tracking captures visits, product views, and impressions at product and country level — independent of GA4.
MCP integration
Model Context Protocol lets agents read from and write to external tools natively — Slack, sheets, ad platforms.
Profitability metrics
From gross sales to true profit — after every cost and return
The full chain: Gross sales → Net sales → GP1 (after COGS) → GP2 (after shipping & payment) → GP3 (after returns) → NGP3 (after pick & pack and overhead). Every metric computed per order line item in real time. Dema speaks P&L, not just ROAS.
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
100+
Pre-built commerce metrics — profit, acquisition, retention, inventory — available from day one
Forecasting built in
Not just historical reporting
Live data and ML-powered predictions — available as regular metrics in every dashboard and report. Order forecasts, inventory sell-through, and profit-based LTV all update daily and sit alongside actuals.
CM3 forecast
4-week forward forecast for Contribution Margin 3 based on current spend trajectory and seasonal patterns.
68k
W10
72k
W11
65k
W12
78k
W13
82k
W14
85k
W15
88k
W16
91k
W17
Actual
Forecast
Predicted CM3 (4w)
€91,200+12%
“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.”
Connects to your full commerce stack
Ad platforms, e-commerce, analytics, email, and more. Data flows in, the semantic layer normalizes it, and the agent reasons across all of it.
Plus warehouse, POS, and ERP integrations via CSV, sFTP, and APIs.
View all integrationsOne model, every product
The foundation for everything Dema does
The agent, self-serve analytics, MMM, and incrementality testing all read from the same modeled data. No separate pipelines, no conflicting numbers.
AI Agent
Ask questions in plain language. The agent translates them into queries across the full data model — profit, inventory, marketing, and customers in one answer.
Self-serve analytics
100+ metrics, 40+ dimensions, real-time dashboards. The same modeled data, available through a point-and-click explorer.
Unified measurement
Always-on MMM and geo-based incrementality tests that read profit, spend, and channel data directly from the model. Budget optimization grounded in real margins, calibrated by causal experiments.
Customer stories
Trusted by category leaders
Frequently asked questions
A semantic layer defines what metrics mean, how entities relate, and what calculations are correct — before anyone queries the data. The agent, dashboards, and reports all use the same definitions, so numbers always match.
GA4 tracks events and sessions. Shopify shows gross margin. Neither connects marketing spend to inventory to profit after all costs. Dema unifies the full picture and adds forecasting and an AI agent on top.
The full hierarchy: Gross Profit 1 (after COGS), GP2 (after shipping & payment fees), GP3 / NGP3 (after returns), and contribution margin. All computed per order line item in real time.
Connect your e-commerce platform and ad accounts, configure your cost structure, and you're live. Most teams are running within a day.
Yes. Dema layers on top of your stack — it ingests data from Shopify, Google, Meta, TikTok, Klaviyo, and more. You don't need to replace anything.