Feature usage by signup cohort
Compare feature usage across signup cohorts to see how adoption differs between groups.
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
Heatmap features against cohorts
Coming soonBlu builds a step
About this recipe
When to use it
If last month's signups suddenly stop touching a feature that used to be sticky for every cohort before them, that's an onboarding regression - and it usually goes unnoticed until churn shows up weeks later. This heatmap catches it immediately.
What it delivers
Maps feature usage against signup cohort in a heatmap, identifying historically sticky features and flagging when a newer cohort's usage of them regresses versus prior cohorts.
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
“Compare feature usage across signup cohorts to see how adoption differs between groups.”
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.
- 01Heatmap features against cohortsCreate an Insights report called "Feature Usage by Cohort". Series A: Event "Click on" filtered by target_id (matching a defined feature pattern), aggregation: Count Unique Users Series B: Computed: Series A / cohort size × 100, unit: %, label: "Adoption Rate within Cohort" Breakdown: By target_id (feature) AND by cohort month derived from User.First seen (system-set datetime) bucketed to month Time range: Last 90 days of usage; cohorts from Users with First seen in the last 6 months Chart type: Heatmap (feature on Y axis, cohort month on X axis), cell value = adoption rate %, color intensity scaled Annotations: - Flag features that show "left-side fade" in the heatmap (older cohorts have higher adoption than newer cohorts): likely an onboarding regression where newer users aren't being introduced to the feature. - Flag features that show "right-side rise" (newer cohorts adopt at higher rates): recent product or onboarding improvements working. - Highlight rows (features) where adoption is uniformly >30% across all cohorts: universally sticky features. - Highlight columns (cohorts) where adoption is uniformly low across most features: that cohort's onboarding may have been broken. Surface which features need to be re-introduced to recent cohorts and which cohort months had degraded onboarding. Taxonomy notes: - Users.First seen is a system-set datetime; "signup_cohort_month" is a derived bucketing of First seen, not a stored property. - Click on.target_id is the canonical feature handle.
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 /feature-usage-heatmap-by-cohort 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 