Average order value trend
Tracks average order value weekly and splits the movement into how many items people buy versus what they pay per item, for new and returning customers.
Authored by Intempt Technologies
Recipe curators
Agentic workflow
Coming soon1 step Blu runs end to end. It drafts a plan and nothing runs until you approve it.
- 1
Break down AOV week by week
Coming soonBlu builds a step
About this recipe
When to use it
AOV going up looks good until you realize it's just because you raised prices, not because people are buying more. This decomposes the trend into units-per-order vs. price-per-unit, and splits new vs. returning customers, so the real driver shows up.
What it delivers
Tracks average order value over time, decomposed into units-per-order and price-per-unit components, with a separate comparison for new vs. returning customers.
How you prompt this
Describe the outcome in your own words and Blu Agent maps it to this recipe, or run it by name. It drafts a plan first and nothing runs until you approve it.
Tell Blu Agent what you want
“Tracks average order value weekly and splits the movement into how many items people buy versus what they pay per item, for new and returning customers.”
recipe.md preview
Built from the published catalog. Blu Agent's full step prompts load in your workspace when you run it.
Inputs & outputs
What the recipe needs before it runs, and what it leaves in your workspace.
Inputs
- Nothing declared beyond an Intempt workspace. Blu asks for anything else it needs as it goes.
Outputs
How the recipe runs
Blu follows the steps in order and shows you each one before anything goes live.
- 01Break down AOV week by weekCreate an Insights report called "AOV Trend". Series A: Event "Placed order", aggregation: Average of "total_price" property, unit: $, label: "AOV" Series B: Event "Placed order", aggregation: Average of items length (count of line items in items array), label: "Units per Order" Series C: Computed: Series A / Series B, unit: $, label: "Average Price per Unit" Time granularity: Weekly Time range: Last 12 weeks Breakdown: By customer type: derive new vs returning from the User.Lifetime value computed attribute (Lifetime value > 0 at the time of the order = returning, otherwise new) OR from User.orders_count. Compare: Previous period (previous 12 weeks) Chart type: Multi-line chart with all three series, separate axes for AOV/Price-per-Unit ($) and Units-per-Order (#) Annotations: - Add a callout showing the period-over-period change in each component (AOV, Units/Order, Price/Unit). - Flag any week where AOV moved >5%: and identify whether the move came from units, price, or both. - Highlight the AOV gap between new and returning customers (returning typically 1.5: 2× new for healthy DTC). AOV moving via price suggests merchandising/pricing impact; AOV moving via units suggests bundling/cross-sell impact. Taxonomy notes: - Placed order has total_price (Shopify) and items (flattened: product_id, title, quantity, price, sku). "order_total" is not a real property. - Users.Lifetime value and User.orders_count (system-computed) are real attributes.
Install Intempt and run it
- 1
Sign up
Create a free Intempt workspace.
- 2
Connect your data
Add the sources this recipe reads from.
- 3
Ask Blu
Type /average-order-value-trend in Blu once this recipe is live there.
- 4
Review and approve
Blu builds each step and waits for your OK before anything goes live.
