Dashboards
AuraScore 79/100

Live Broadcast Dynamic Ad Insertion Yield Dashboard Specification

Produce a production-grade BI spec for monitoring linear-to-digital ad fill rates, pacing, and revenue yield during live broadcast events.

Use this template when building real-time monetization dashboards for sports broadcasting or live events. It details pacing alerts, ad pod telemetry, programmatic fill rates, and revenue telemetry.

Template

Role: Lead Media Monetization BI Engineer specializing in programmatic ad operations and live linear dynamic ad insertion (DAI).

Context

  • Media Network: {{broadcaster_network}}
  • Inventory Channels: {{monetization_channels}}
  • Ad Server Infrastructure: {{ad_server_ecosystem}}
  • Maximum Latency SLA: {{latency_tolerance_sla}}
  • Monitored Yield Metrics: {{key_yield_metrics}}
  • Target Stakeholders: {{stakeholder_user_group}}

Task

Develop a comprehensive dashboard design specification for monitoring ad pod performance, pacing health, and yield realization across live digital streams for {{broadcaster_network}}.

Method

  1. Define ingestion architecture mapping real-time logs from {{ad_server_ecosystem}} across {{monetization_channels}}.
  2. Construct the technical formula and anomaly threshold for each item in {{key_yield_metrics}}.
  3. Establish latency handling and stream-buffering protocols enforcing the {{latency_tolerance_sla}}.
  4. Design layout modules separating live pacing dials, programmatic bidder response heatmaps, and pod drop-off analytics.
  5. Specify role-based view controls customized for the operational workflows of {{stakeholder_user_group}}.
  6. Detail visual and webhook alerting protocols for inventory under-delivery, timeout spikes, and fill failures.
  7. Formulate fallback data states for handling upstream ad server downtime or telemetry packet loss.

Constraints

  • MUST incorporate real-time SLA thresholds matching {{latency_tolerance_sla}}.
  • MUST NOT leave metric definitions open to interpretation; require explicit mathematical formulation.
  • Ensure visualization choices directly support rapid incident triage during live broadcast windows.
  • Avoid generic UI templates by binding each component to specific ad server transaction lifecycle states.

Output format

Present the specification following this sequence:

  1. Operational Dashboard Objective & Audience Context
  2. Data Stream Architecture & SLA Controls (including ingestion pipeline diagram in text/markdown)
  3. Core Metric Dictionary & Alert Thresholds (KPI, Formula, Unit, Critical Threshold)
  4. Grid Layout & Visual Component Wireframes (Screen zone, widget type, interaction behavior)

Self-review

  • Validate that all metrics in {{key_yield_metrics}} have corresponding calculations and threshold triggers.
  • Confirm that ad server dependencies from {{ad_server_ecosystem}} are accounted for in data contracts.
  • Check that the output format strictly complies with the named sections and constraints.
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 engineering8/12 · 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.

Robustness5/5 · Strong

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
broadcasting
adtech
dai