Dashboards
AuraScore 79/100

Streaming Platform Churn and Content Consumption Telemetry Specification

Architect an executive-ready BI dashboard specification for tracking SVOD viewer drop-off, catalog utilization, and subscriber cohort retention.

Use this template when designing or overhauling an analytics dashboard for subscription video-on-demand services. It establishes data grain, telemetry lineage, drill-down logic, and executive UI requirements.

Template

Role: Principal Streaming Analytics Architect with fifteen years of experience designing real-time observability and subscriber BI platforms.

Context

  • Streaming Platform: {{streaming_service_name}}
  • Subscriber Segment: {{target_subscriber_tier}}
  • Ingestion Sources: {{primary_telemetry_sources}}
  • Sync Frequency: {{refresh_cadence}}
  • Retention Metrics: {{core_retention_kpis}}
  • Privacy & Compliance: {{governance_framework}}

Task

Author a comprehensive technical and functional dashboard specification for an executive viewer retention and content consumption dashboard that surfaces subscriber churn drivers and catalog performance for {{streaming_service_name}}.

Method

  1. Map data lineage from {{primary_telemetry_sources}} into staging and semantic layer models for {{target_subscriber_tier}}.
  2. Define metric calculations, filtering parameters, and baseline thresholds for {{core_retention_kpis}}.
  3. Establish aggregation windows and time-grain intervals aligned with {{refresh_cadence}}.
  4. Design visual hierarchy prioritizing high-level churn velocity, content drop-off funnels, and cohort longevity curves.
  5. Outline interactive drill-down pathways from macro subscriber counts down to title-level telemetry and binge-rate indices.
  6. Detail alert trigger rules for abnormal subscriber churn spikes, drop-off anomalies, and playback error correlations.
  7. Specify column-level security and data sanitization guidelines in adherence to {{governance_framework}}.

Constraints

  • MUST define precise SQL aggregation logic or pseudocode for each of the {{core_retention_kpis}}.
  • MUST NOT specify raw PII exposure at any level of the dashboard interface.
  • Every chart component must include declared latency tolerances, default states, and error handling states.
  • Keep implementation stack agnostic while providing concrete dimensional model schemas.

Output format

Provide the specification in four structured markdown sections:

  1. Executive Architecture Summary (max 200 words)
  2. Metric Catalog & Semantic Calculations (table format with KPI, Source, Granularity, Formula)
  3. Layout & Wireframe Component Specifications (ordered top-to-bottom, left-to-right)
  4. Security, Refresh, and Governance Parameters

Self-review

  • Confirm all 6 context variables are deeply integrated into the calculations and schema.
  • Verify that each metric specification contains an explicit formula and telemetry data source.
  • Ensure compliance constraints for {{governance_framework}} are concretely addressed in the schema design.
AuraScore breakdown
79/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering10/12 · Adequate

Hard boundaries — what the model must and must not do.

Output specification6/14 · Thin

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness3/5 · Adequate

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

data-analytics
data-dashboards
media-entertainment
streaming
svod
churn