NPS tracking
Tracks your Net Promoter Score month by month with the promoter, passive and detractor split behind it.
Authored by Intempt Technologies
Recipe curators
Agentic workflow
Coming soon1 step Blu runs end to end. It drafts a plan and nothing runs until you approve it.
- 1
Score NPS each month
Coming soonBlu builds a step
About this recipe
When to use it
A rising NPS number can hide two very different stories: more promoters, or just fewer detractors. This decomposes the score into all three groups over time, so you know which one is actually moving.
What it delivers
Tracks NPS score over time from real feedback_submitted events, decomposed into promoter, passive, and detractor counts so the driver behind any trend is visible.
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
“Tracks your Net Promoter Score month by month with the promoter, passive and detractor split behind it.”
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 NPS each monthCreate an Insights report called "NPS Tracking". Series A: Event "Feedback submitted" where survey_type = "nps", aggregation: Count where score >= 9 (promoters), label: "Promoters" Series B: Event "Feedback submitted" where survey_type = "nps", aggregation: Count where score is between 7 and 8 (passives), label: "Passives" Series C: Event "Feedback submitted" where survey_type = "nps", aggregation: Count where score <= 6 (detractors), label: "Detractors" Series D: Computed NPS: (Series A − Series C) / (Series A + Series B + Series C) × 100, unit: # (NPS is reported as a score from -100 to +100), label: "NPS Score" Series E: Trailing 90-day rolling NPS for trend smoothing, label: "NPS (90-day rolling)" Time granularity: Monthly Time range: Last 12 months Breakdown for the trend chart: optional Plan (saas) or first-purchase product category (ecommerce) Compare: Year-over-year Chart type: Stacked bar chart for Series A/B/C distribution per month, with Series D (NPS) as a line on a secondary axis. Use color: Promoters green, Passives gray, Detractors red. Annotations: - Add benchmarks per industry: B2B SaaS median NPS is 30; top-quartile 50+; SaaS world-class 70+. eCommerce DTC median 30: 40; top-quartile 60+. Below 0 indicates a serious problem (more detractors than promoters). - Flag any month where Series D dropped >10 points vs. trailing-3-month average. - Highlight the % of detractors who left feedback_text: these are the highest-leverage voice-of-customer signals (act on the qualitative comments, not just the score). - Highlight any plan/segment whose NPS is significantly below the blended average (>15 points lower): these are the audiences where product-market fit is weakest. - Surface response volume per month: a falling NPS from a small sample (<30 responses/month) may not be statistically meaningful. Add a "low confidence" flag when monthly sample size <30. Use case: every business tracks NPS but most never visualize the underlying promoter/passive/detractor distribution shifts that drive the score. A score of 30 with rising detractors is very different from a score of 30 with falling passives: same headline number, opposite direction. Taxonomy notes: - Feedback submitted has score, sentiment, survey_type, feedback_text, masterID, submitted_at: all canonical. - This recipe assumes the workspace uses survey_type = "nps" to discriminate NPS surveys from other feedback. If the project uses a different value (e.g. "net_promoter"), adjust the filter. - score is expected to be 0: 10 numeric. Workspaces emitting Feedback submitted from custom surveys may need to validate score range matches NPS convention. - If the workspace doesn't have Feedback submitted events flowing reliably from their NPS tool (Delighted, AskNicely, Wootric, custom in-app surveys), this recipe degrades to "no data." Recommend ensuring NPS-survey integration is configured.
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 /nps-tracking 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.
