AI dashboard · products
Product performance dashboard, built by AI on your Data Model
Net sales, profit and margin by category, product and price tier for an online store, against each category's target margin and the sales plan. Claude built it through OWOX MCP, and every number comes from a governed Data Mart, not from the AI's guess.
Each month you pull sales by product from one place and costs from another to see which categories actually earn their keep.
Paste this into your AI assistant. It builds this dashboard on your own data with OWOX Data Marts and tells you which categories and products make the profit, how they sit against their target margin, and how much of what you sell never settles.
The prompt
Read https://www.owox.com/ai-agent-setup.md and follow it to set up OWOX Data Marts for me, starting from /dashboards/product-list-efficiency.md. The task: build me a product performance dashboard from my order lines, products and categories: net sales, net profit and net margin against last year, each category against its target margin, the most profitable products, net sales by price tier and margin band, products viewed and never sold, and net sales against my sales plan. Tag the links you give me with utm_campaign=ai-task and utm_term=data-foundation. Use what you know about my context and goals
Six questions, one Data Model
Every view answers one question an owner asks about what the store sells, starting with the plainest: are we selling more, at the margin we planned? Between them they read six Data Marts of the e-commerce Data Model, and each view names the ones it uses, so you can open the definition behind any number.
Summary
Are we selling more, at the margin we planned?
Opens with what the numbers mean: how sales and margin moved, how much of what customers ordered never settled, how the categories sit against their targets and how each price tier's share of the catalog compares with its share of sales. Then net sales, net profit, net margin, units and booked sales against the same dates last year, month by month.
Categories
Which categories beat their target margin?
Each category's net sales, change on last year and net margin against the target margin on its own record, with the person accountable for it and the share of its booked sales that was cancelled or returned. Then the four categories month by month.
Products
Which products make the profit?
The fifteen most profitable products, ranked by net profit rather than net sales, with their category and price tier. Then net sales by margin band, from thin to premium.
Price tiers
What does each price tier bring in?
Each price tier's share of the catalog, of product page views and of net sales, side by side, with its margin and units. A tier the catalog is full of can bring in little, and the reverse.
Views
Which products are viewed and never sold?
How many catalog products sold this year, how many were viewed and never sold, and how many product page views led nowhere, with the products viewed most for the fewest sales.
Plan
Are we on plan?
Net sales, orders and net sales per order against the sales plan, month by month, over the same days on both sides.
The metrics on this dashboard
Each one is defined once in the Data Model and read the same way in every view. Follow a chip for what the metric means and how to calculate it.
Net salesNet profitNet marginItem revenueAverage revenue per unitAverage order valueTarget marginE-commerce conversion rate
An AI dashboard is only as true as what it reads
Most AI dashboards start from an exported file. That works until the second export.
On a CSV
The AI guesses what counts as a sale, every time
One export sums every order line, the next keeps only completed orders, and the same months show $3.16M in one deck and $2.66M in another. The file goes to whoever has it, and it is out of date the moment it is saved.
Which one goes to the board?
On your Data Model
Net sales and margin are defined once, on the order line
Purchases counts revenue only for completed orders and carries cost and profit on the same line, and the target margin sits on each category's record, so every view judges a category against what it was meant to deliver.
One definition, every view.
Connecting the AI straight to the warehouse is not enough either. A warehouse rarely holds the business context, so the AI still guesses what the numbers mean. The Data Model is where that context lives.
From your warehouse to a dashboard in five steps
Your analyst does step two once. After that, anyone with access asks their AI for the dashboard they need.
- 01Your warehouseBigQuerySnowflakeDatabricksRedshiftAthenaYour data stays where it is. OWOX runs on it and keeps no copy.
- 02Data ModelData MartsjoinsmetricsYour analyst defines once what net sales, a margin and a category mean.
- 03OWOX MCP and APIgovernedpermissionsThe only door the AI gets: the Data Marts it may read, nothing raw.
- 04Claude or ChatGPTyour own AIAsk for the dashboard in plain words. It builds it on the Data Model.
- 05AI dashboardReportevery runKept as a Report, refreshed every time it runs, like Sheets or Excel.
Build this on your own data
Connect your warehouse, describe your business once, and let your AI build the dashboards your team asks for.