AI dashboard

AI dashboard · conversion

Checkout funnel dashboard, built by AI on your Data Model

Sessions, orders and conversion for an online store, step by step from visit to order, by device and traffic type, and against the plan. Claude built it through OWOX MCP, and every number comes from a governed Data Mart, not from the AI's guess.

5 Data MartsBuilt by Claude via OWOX MCPRefreshed every Report runE-commerce data model

The dashboard

Hand this to your AI

When sales dip, you still can't say whether fewer people came, or the same people stopped buying, and at which step.

Paste this into your AI assistant. It builds this dashboard on your own data with OWOX Data Marts and tells you where shoppers drop out between visit and order, and how mobile, paid traffic and the plan compare.

The prompt

build me a checkout funnel dashboard from my sessions, page views and orders: sessions, orders and conversion rate against last year, the share of sessions at each step from visit to product page, checkout and order, conversion by device and by traffic type, and sessions, orders and conversion against my plan

What each view answers

Five questions, one Data Model

Every view answers one question a marketing lead asks about the storefront, starting with the one behind every dip in sales: where are we losing people? Between them they read five 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.

The E-commerce data model: 12 Data Marts and how they join
E-commerce data model · 12 Data Marts · 15 relationships · open it →

Summary

Are visits turning into orders?

Opens with what the numbers mean: how orders grew, where shoppers drop out, how conversion moved, what mobile is worth and how paid traffic converts. Then sessions, orders, conversion rate, the two checkout steps and sessions per visitor against the same dates last year, month by month.

SessionsOrdersPageviewsPagesConversion rate

Funnel

Where do shoppers drop out?

Sessions at each step, from visiting the store to viewing a category, a product, checkout and an order, this year against last, drawn to scale. Then the share of product sessions that reach checkout, month by month.

PageviewsPagesSessionsOrdersE-commerce conversion rate

Devices

Does mobile convert?

Sessions, orders and conversion rate on mobile and desktop, against last year.

SessionsOrders

Traffic

Which traffic converts?

Paid, organic, owned and direct traffic side by side: its share of sessions, its orders and its conversion rate against last year.

SessionsOrdersTraffic Sources

Plan

Are we on plan?

Sessions, orders and conversion rate against the storefront plan, month by month, over the same days on both sides.

SessionsOrders

Metrics

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.

SessionsOrdersConversion rateE-commerce conversion rateSessions per visitorProduct to checkoutCheckout to order

Connected, not a snapshot

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 a conversion rate divides by, every time

One export divides orders by the sessions that viewed a product, the next by every session, and the same months show 3.09% in one deck and 2.34% in another. The file goes to whoever has it, and it is out of date the moment it is saved.

Two exports of the same orders giving a conversion rate of 3.09% and 2.34%

Which one goes to the board?

On your Data Model

Conversion rate is one field, right at every cut

Sessions defines conversion rate once, as orders per session, and keeps it right by day, device or traffic type; the page type sits on Pages, so every step of the funnel counts the same way.

The e-commerce Data Model: Sessions joined to Orders, Pageviews, Pages and Traffic Sources

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.

How it is built

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.

  1. 01Your warehouseBigQuerySnowflakeDatabricksRedshiftAthenaYour data stays where it is. OWOX runs on it and keeps no copy.
  2. 02Data ModelData MartsjoinsmetricsYour analyst defines once what a session, an order and a conversion mean.
  3. 03OWOX MCP and APIgovernedpermissionsThe only door the AI gets: the Data Marts it may read, nothing raw.
  4. 04Claude or ChatGPTyour own AIAsk for the dashboard in plain words. It builds it on the Data Model.
  5. 05AI dashboardReportevery runKept as a Report, refreshed every time it runs, like Sheets or Excel.

Build yours

Build this on your own data

Connect your warehouse, describe your business once, and let your AI build the dashboards your team asks for.