Support volume versus churn
Compare weekly support ticket volume with weekly subscription cancellations to see how the counts change over time.
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
Line up tickets against churn
Coming soonBlu builds a step
About this recipe
When to use it
If support ticket volume reliably rises before cancellations do, that's an early-warning system you're not using. This plots both on one dual-axis chart with priority decomposition and the actual lead-lag between them.
What it delivers
Plots support ticket volume against subscription cancellations on a dual axis, decomposed by ticket priority, with the lead-lag time between a ticket spike and a churn spike measured directly.
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 weekly support ticket volume with weekly subscription cancellations to see how the counts change over time.”
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.
- 01Line up tickets against churnCreate an Insights report called "Support Volume vs Churn". Series A: Event "Ticket created", aggregation: Count, label: "Tickets" Series B: Event "Subscription canceled", aggregation: Count, label: "Churns" Time granularity: Weekly Breakdown for Series A: By "priority" property on Ticket created (the canonical event has priority as a property) Breakdown for Series B: By "reason" property on Subscription canceled (text: group by cleaned/tokenized reason categories) Time range: Last 12 weeks Compare: Previous period (prior 12 weeks) Chart type: Dual-axis chart: left axis tickets (stacked area by priority), right axis churns (lines by reason group) Annotations: - Highlight any week where high-priority tickets exceeded the trailing 8-week average by 50% or more. - For each spike in churns, surface the leading 2-week ticket volume: flag if elevated by more than 30% vs. baseline. Surface whether high-priority ticket spikes precede churn spikes (typical lag is 2-4 weeks). If correlation is strong, identify which Subscription canceled.reason categories are most associated with prior support load. Taxonomy notes: - Ticket created is canonical (no "support_" prefix). Properties: ticket_id, priority, source_type, status, subject. - Subscription canceled (British spelling) carries reason as a free-text field. Cluster reasons before breakdown.
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 /support-tickets-vs-churn-correlation 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 