Account engagement score trend
Builds a report that calculates a custom weighted engagement score for each account from user activity and click data. The weighting is arbitrary and not a native product score.
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
Score account engagement weekly
Coming soonBlu builds a step
About this recipe
When to use it
Individual user metrics hide what's happening at the account level. One power user can mask three going quiet. This rolls every user on an account into a single trend line, so expansion and churn risk show up before the renewal call.
What it delivers
Aggregates engagement across every user on an account and tracks the rolled-up score over time, split into accounts trending up (expansion candidates) and accounts trending down (churn risk).
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
“Builds a report that calculates a custom weighted engagement score for each account from user activity and click data. The weighting is arbitrary and not a native product score.”
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.
- 01Score account engagement weeklyCreate an Insights report called "Account Engagement Score Trend". Series A: Event "Session start", aggregation: Count Unique Users: rolled up by Users.the account the user belongs to (so each account's score = number of distinct users from that account who emitted a Session start in the period) Series B: Event "Click on", aggregation: Count, rolled up by Users.the account the user belongs to (raw activity volume per account) Series C: Computed engagement score per account = (Series A × 5) + (Series B × 0.1): a weighted blend giving each account a single number reflecting both breadth (distinct users) and depth (activity volume) Time granularity: Weekly Time range: Last 12 weeks Breakdown: By Account record (top 30 accounts by current engagement score) Compare: Previous period (prior 12 weeks) Chart type: Multi-line chart with one line per account, plus a heatmap small-multiple showing score change week-over-week Annotations: - Flag accounts whose engagement score dropped >30% in the last 4 weeks vs. trailing 8-week baseline (acute disengagement: churn risk). - Flag accounts whose engagement score grew >50% in the last 4 weeks (expansion candidates: sales should reach out). - Flag accounts where Series A (distinct users) is shrinking but Series B (activity) is stable: the account is consolidating to a smaller power-user group; risky if that user departs (single-threaded account). - Highlight the top 5 accounts by absolute engagement score AND the top 5 by week-over-week growth rate: different lists, both worth sales attention. Use case: the canonical B2B account-health view. Single-user metrics miss the real story in B2B; an account where 1 user is hyperactive while 20 others ignore the product is at risk despite high "activity." This recipe rolls up to the account level. Taxonomy notes: - Users.the account the user belongs to is the canonical relation linking users to accounts. - The Accounts object has 58 attributes including engagement-score relation possibilities. - Session start and Click on are canonical engagement signals.
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 /account-engagement-score-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.
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 