Skip to main content
Intempt
Coming soon

Account health and churn risk

Shows account health and customer base health using return-rate retention and NPS.

Authored by Sid Chaudhary

Founder & CEO at Intempt

Agentic workflow

Coming soon

1 step Blu runs end to end. It drafts a plan and nothing runs until you approve it.

  1. 1

    Build the account health board

    Coming soon

    Blu builds a step

About this recipe

When to use it

Account health, expansion signals, and at-risk intelligence usually live in separate tools a CSM has to check individually. This puts them on one dashboard built for the CS Lead / CSM view.

What it delivers

Surfaces account health, expansion signals, NRR, NPS, and at-risk account intelligence for the CS Lead or CSM.

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 account health and customer base health using return-rate retention and NPS.”

recipe.md preview

Built from the published catalog. Blu Agent's full step prompts load in your workspace when you run it.

Sign up to read the full recipe.md and run it with Blu Agent.

Sign up to see the full recipe

Inputs & outputs

What the recipe needs before it runs, and what it leaves in your workspace.

Inputs

  1. 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.

    1. 01Build the account health boardCreate a Dash board (12-column composition canvas) titled "Customer Success". Persona: Customer Success Lead or individual CSM. Question answered: "Which accounts need my attention this week, and is the customer base healthy overall?" Board-level configuration: - defaultDateRange: last_30_days - exclusionPeriod: incomplete_periods - visibility: project - boardFilters: none by default; CSMs typically add a filter on owner_id at runtime to view their book of business - boardBreakdowns: none Layout: 4 rows. Row 1: Health KPIs (heightPx: 200, four metric cards at widthUnits: 3): - Card 1: Insights metric to source recipe: accounts-at-risk-count, vizType: metric, titleOverride: "Accounts at Risk" - Card 2: Insights metric to source recipe: monthly-logo-retention-trend, vizType: metric, titleOverride: "Monthly Logo Retention" - Card 3: Retention metric to source recipe: net-revenue-retention-by-cohort, vizType: metric, titleOverride: "Trailing-12mo NRR" - Card 4: Insights metric to source recipe: nps-tracking, vizType: metric, titleOverride: "NPS Score" Row 2: Account-level intelligence (heightPx: 440, full-width single card at widthUnits: 12): - Card 1: Insights to source recipe: account-engagement-score-trend, displayMode: table (top 30 accounts by current engagement score, sortable by week-over-week change). The two key sort modes: sort by score-decline (descending) to "accounts to save"; sort by score-rise (descending) to "accounts to expand" Row 3: Revenue retention dynamics (heightPx: 400, two cards at widthUnits: 6): - Card 1: Retention to source recipe: net-revenue-retention-by-cohort, displayMode: chart, vizType: line (cohort NRR curves) - Card 2: Insights to source recipe: expansion-revenue-trend, displayMode: chart, vizType: stacked_bar (upgrade vs. seat expansion mix) Row 4: Churn early-warning (heightPx: 440, two cards at widthUnits: 6): - Card 1: Insights to source recipe: support-tickets-vs-churn-correlation, displayMode: chart, vizType: line (dual-axis tickets vs churns) - Card 2: Path to source recipe: pre-churn-behavioral-signals, displayMode: chart (precursor-event ranking by lift over baseline) Annotations: - Row 1's four KPIs together answer "how is the customer base health" from four angles: how many are slipping (Accounts at Risk), are we keeping them (Logo Retention), are they paying more (NRR), and how do they feel (NPS). - Row 2 (the full-width account table) is the centerpiece. CSMs work this list weekly: top of the "decline" sort = save plays; top of the "rise" sort = expansion outreach. - Row 4 is leading-indicator territory: support spikes precede churn by 2-4 weeks, and pre-churn behavioral signals surface 30 days out. Use these to fire intervention before retention erosion shows up in Row 3's NRR curves. Taxonomy notes: - All source recipes use canonical events: Session start, Click on, Ticket created, Subscription canceled, Subscription updated, Feedback submitted. - Account-level rollups via Users.the account the user belongs to. - accounts-at-risk-count, monthly-logo-retention-trend, and nps-tracking are new v5 recipes designed to fill the headline-KPI slots cleanly.

    Install Intempt and run it

    1. 1

      Sign up

      Create a free Intempt workspace.

    2. 2

      Connect your data

      Add the sources this recipe reads from.

    3. 3

      Ask Blu

      Type /customer-success-dashboard in Blu once this recipe is live there.

    4. 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

    More recipes by Sid Chaudhary

    Discovery call qualification fieldsGenerates an AI summary for Discovery calls from meeting data using the qualification framework in the summary recipe.View recipe Post 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 Return rate by categoryShows which product categories get returned most, and which ones have got worse since last quarter.View recipe

    Got a play worth sharing?

    Publish it to the Intempt Collective Marketplace and earn when other teams run it.

    Submit a recipe