Browse to purchase funnel
Shows how many shoppers move from a category page to a product page, cart, checkout and a completed order, and where you lose them on each device.
Authored by Sid Chaudhary
Founder & CEO at Intempt
Agentic workflow
Coming soon1 step Blu runs end to end. It drafts a plan and nothing runs until you approve it.
- 1
Trace category page to order
Coming soonBlu builds a step
About this recipe
When to use it
Mobile and desktop conversion rates are never the same, but a blended funnel hides where they diverge. This runs the canonical browse-to-purchase funnel with device split at every step.
What it delivers
Builds a funnel from page_viewed through cart events to completed orders, with conversion rate compared side by side across devices at every step.
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
“Shows how many shoppers move from a category page to a product page, cart, checkout and a completed order, and where you lose them on each device.”
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.
- 01Trace category page to orderCreate a Funnel report called "Browse to Purchase". Steps: 1. Event "View page" where content_type indicates a category/listing page (or Page URL contains /collections/ or /category/): "Browsed Category" 2. Event "View page" where Page URL indicates a product detail page (e.g. contains /products/): "Viewed Product Detail" 3. Event "Cart created": "Added to Cart" 4. Event "Checkout created": "Started Checkout" 5. Event "Placed order": "Completed Purchase" Conversion window: 7 days Breakdown: By "device_type" attribute on the Users object (desktop, mobile, tablet) Compare: Previous period (prior 7 days) For each step, also surface: - Median time-to-convert from previous step - Per-device conversion rate at each step Annotations: - Flag the step with the largest drop-off (the primary bottleneck). - Flag any step where mobile conversion lags desktop by >10 percentage points (mobile UX issue). - Highlight any step where overall drop-off worsened by >3 percentage points vs. previous period. Industry benchmarks: 2-3% browse-to-buy for fashion, 4-6% for electronics. Taxonomy notes: - "product_list_viewed" and "product_viewed" as standalone events do not exist. Page-type discrimination is done via View page.Page URL path patterns or View page.content_type. - "checkout_started" does not exist; Checkout created is the canonical pre-payment marker. - Placed order is the canonical purchase event (cart_converted is also valid for cart-source attribution).
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 /browse-purchase-funnel 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.
Related recipes
Sid ChaudharyDiscovery call qualification fieldsGenerates an AI summary for Discovery calls from meeting data using the qualification framework in the summary recipe.View recipe Sid ChaudharyPost demo nurtureKeeps a demo warm for 90 days with a playbook, a case study, an ROI calculator and a customer story, and pulls the AE in early if they bite.View recipe Sid ChaudharyReturn rate by categoryShows which product categories get returned most, and which ones have got worse since last quarter.View recipe 