Data Visualization & BI Dashboards5.0 · 0 ratings

Cohort Retention Heatmap Specification

Specifies a cohort retention heatmap including cohort definition, aggregation, and reading guidance.

Role-BasedStep-by-Step

Prompt

You are a product analytics lead who builds retention visualizations. CONTEXT: The event data is [EVENT_SCHEMA], the activation event is [ACTIVATION_EVENT], and the return event is [RETURN_EVENT]. Cohorts are grouped by [COHORT_DIMENSION] over [COHORT_PERIODS]. The retention window unit is [WINDOW_UNIT].

TASK STEPS:
1. Define the cohort assignment logic and the retention numerator and denominator precisely.
2. Specify the heatmap structure: rows, columns, cell value, and color encoding scale.
3. Write the aggregation query or pseudocode that produces the cohort matrix.
4. Describe how to read the diagonal, the first column, and horizontal decay for insights.
5. Recommend annotations that highlight the strongest and weakest cohorts.

OUTPUT FORMAT: Cohort Logic block, Heatmap Spec (rows/cols/value/color), Query pseudocode, Reading Guide, and Annotation Recommendations.

CONSTRAINTS: Use percentage retention, not absolute counts, unless [USE_ABSOLUTE] is true; handle cohorts with fewer than [MIN_COHORT_SIZE] users by suppressing them; keep the color scale perceptually uniform.

How to use this prompt

  1. 1

    Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.

  2. 2

    Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.

  3. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

Role-Based

Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.

Learn this technique
Step-by-Step

Forces explicit intermediate reasoning instead of jumping to a conclusion, which improves accuracy on hard tasks.

Learn this technique

Recommended models

claudegpt-4ogemini

Build on this prompt

Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.

Open in Studio How to prompt AI correctly

More in Data Visualization & BI Dashboards

Executive KPI Dashboard Blueprint Architect

Designs a single-screen executive KPI dashboard layout with metric hierarchy, chart selection, and drill-down logic.

Read prompt

Chart Type Selection Decision Tree

Reasons step by step from data shape and analytic intent to the optimal chart type with ranked alternatives.

Read prompt

SQL-to-Dashboard Metric Layer Definer

Translates raw tables into a governed semantic metric layer with definitions, grains, and reusable measures.

Read prompt

Dashboard Redesign Critique and Rework

Critiques an existing dashboard against visualization best practices, then prescribes a concrete redesign.

Read prompt