Shopify integration for Rig
The easiest way to connect Shopify to Claude and other AI tools
Shopify is an e-commerce platform where merchants sell products, manage orders, and process payments across online and retail channels.
What Rig syncs from Shopify
Once connected, Rig models these objects so questions resolve to the right tables and joins:
- Orders
- Order line items
- Products
- Variants
- Customers
- Transactions
- Refunds
- Fulfillments
- Discounts
- Inventory levels
How Shopify connects to Rig
Rig Ingest syncs your Shopify orders, line items, products, customers and transactions into your warehouse on a schedule, tracking new and edited orders. Rig then models orders down to line-item grain so revenue, AOV, repeat-purchase and product questions resolve correctly.
Track revenue, AOV and discount impact
Net revenue is gross order value less refunds, discounts and taxes, and AOV is net revenue divided by order count. Rig reads Shopify orders, line items, discounts and refunds, so you can break revenue and AOV down by channel, product, discount code and period without exporting reports. It also shows how much each discount code actually costs in margin.
- What was net revenue and AOV by sales channel last month?
- How much revenue did each discount code drive, and what did it cost?
- Show daily revenue this quarter versus the same period last year
Measure repeat purchase, LTV and cohorts
Repeat-purchase rate is the share of customers who place a second order, and LTV is the cumulative net revenue per customer over time. Rig joins Shopify customers to their full order history, so you can build acquisition-month cohorts, track second-order rate, and compare lifetime value by first product or first discount.
- What is the repeat-purchase rate for customers acquired in the last six months?
- Show 12-month LTV by acquisition cohort
- Which first product leads to the highest repeat rate?
Analyse product and inventory performance
Rig reads Shopify products, variants and inventory levels alongside line-item sales, so you can rank products by units and revenue, spot slow movers, and flag variants at risk of stocking out. That turns the catalogue into a ranked view of what sells and what ties up cash.
- Which products and variants drove the most revenue last quarter?
- Which SKUs are selling fast but low on inventory?
- Show sell-through rate by product over the last 90 days
Understand contribution margin per order
Contribution margin per order is net revenue less product cost, discounts and refunds for that order. By joining Shopify line items and refunds to product cost in your warehouse, Rig shows true margin by product, order and customer, so you can see which products and channels actually make money rather than just drive top-line.
- What is contribution margin by product after discounts and refunds?
- Which orders had negative margin once shipping and refunds are counted?
- Show margin by sales channel this quarter
Ask your Shopify data in Claude, ChatGPT or Cursor
Rig serves your Shopify data to AI assistants over MCP. Once Shopify is synced into your warehouse, you can ask questions in plain English from the tool you already use, and every answer is backed by validated, governed SQL.
Frequently asked questions
- What Shopify data does Rig sync?
- Orders, order line items, Products, Variants, Customers, Transactions, Refunds, Fulfillments, Discounts and inventory levels, down to line-item grain.
- Can I analyse Shopify revenue and AOV without building reports?
- Yes. Rig models orders and line items, so you ask revenue, AOV, repeat-purchase and margin questions in plain English and get governed SQL answers.
- Can I query Shopify data in Claude or ChatGPT?
- Yes. Once Shopify is synced to your warehouse, Rig serves it to Claude, ChatGPT, Cursor and other AI tools over MCP.
- How often does Shopify data refresh?
- Rig Ingest syncs on a schedule you set and picks up new and edited orders, products and refunds so figures stay current.
Related integrations
Connect Shopify data to AI tools like Claude
Rig builds a governed context layer over your data so every team, and every AI tool, asks questions and gets answers they can trust.