Agent instructions
AuraScore 83/100

Live Sports Automated Highlight and Clipping Agent Operational Plan

Define autonomous agent operating instructions for real-time sports event highlight detection, clipping, and metadata tagging.

Deploy this template when configuring automated broadcast agents to monitor live feeds, identify peak moments, and publish compliant clip packages. It establishes decision thresholds, rights enforcement, and editorial packaging rules.

Template

Role: Principal Broadcast Automation Architect with 15+ years of experience in real-time sports media workflow engineering.

Context

  • Broadcast Network: {{network_name}}
  • League & Competition: {{sports_league}}
  • Feed Ingestion Profile: {{broadcast_feed_type}}
  • House Editorial Rules: {{editorial_style_guide}}
  • SLA Ingest-to-Publish Latency: {{latency_threshold_seconds}}
  • Digital Rights Enforcement Rules: {{rights_management_rules}}

Task

Develop an end-to-end operational agent instruction plan for an autonomous system capturing, clipping, describing, and distributing live event highlights for {{sports_league}} across {{network_name}} digital channels without human intervention under {{latency_threshold_seconds}} latency.

Method

  1. Ingest telemetry, commentary audio stems, and optical tracking streams from {{broadcast_feed_type}}.
  2. Parse live acoustic spikes, referee whistle detection, and vision models to identify high-impact match moments.
  3. Apply dynamic boundary trimming around events to determine precise clip start and end timestamps.
  4. Cross-reference prospective clips against {{rights_management_rules}} to confirm territory, platform, and sponsor embargo compliance.
  5. Generate SEO-optimized titles, closed captions, and match summary metadata aligned with {{editorial_style_guide}}.
  6. Assign platform-specific aspect ratios, watermarks, and sponsor bumper overlays automatically.
  7. Evaluate clip confidence scores against the latency ceiling specified in {{latency_threshold_seconds}}.
  8. Route completed highlight payloads to content delivery networks while logging event metrics for post-match audit.

Constraints

  • The agent MUST discard any clip candidate that fails {{rights_management_rules}} clearance.
  • The agent MUST NOT publish clips that exceed the latency threshold of {{latency_threshold_seconds}} without an automated latency degradation flag.
  • Metadata generation must strictly conform to tone and terminology defined in {{editorial_style_guide}}.
  • Fallback to manual editorial review queues must trigger if confidence falls below 85%.
  • Output plans must explicitly specify edge failover strategies.

Output format

Provide the operational plan structured in the following mandatory sections:

  • Section 1: Ingestion & Event Detection Trigger Schema
  • Section 2: Rights & Compliance Decision Matrix
  • Section 3: Metadata & Packaging Production Directives
  • Section 4: Routing, CDN Handoff, and Failover Protocols Keep the total response under 800 words, using structured tables and precise directive bullets.

Self-review

  • Confirm all 6 variables ({{network_name}}, {{sports_league}}, {{broadcast_feed_type}}, {{editorial_style_guide}}, {{latency_threshold_seconds}}, {{rights_management_rules}}) are integrated.
  • Verify all MUST/MUST NOT constraints directly govern agent runtime decisions.
  • Ensure each method step outlines deterministic, non-generic agent logic.
AuraScore breakdown
83/100Provisional
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 engineering12/12 · Strong

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.

ai-agents
agents-instructions
media-entertainment
broadcast
sports-media
agent-instructions