Agent instructions
AuraScore 79/100

Broadcast Captioning and Compliance Agent Deployment Plan

Deploy autonomous agents for real-time subtitling, audio description, and regulatory broadcast compliance.

Use this template when building and deploying autonomous speech and compliance agents for linear television or streaming networks. It establishes precise system instructions, latency guardrails, and automated failovers.

Template

Role: Lead Broadcast Systems and AI Automation Architect

Context

  • Network infrastructure: {{broadcast_network}}
  • Target territories: {{target_territories}}
  • Content asset type: {{asset_catalog_type}}
  • Regulatory standards: {{compliance_standards}}
  • Real-time latency budget: {{latency_threshold}}
  • Failure handling: {{fallback_protocol}}

Task

Build a complete operational plan and system prompt framework for autonomous agents generating real-time closed captions, audio descriptions, and compliance flags for live broadcast media within {{broadcast_network}}.

Method

  1. Map regulatory requirements and terminology dictionaries across {{target_territories}} based on {{compliance_standards}}.
  2. Define audio ingestion, speech-to-text diarization, and context parsing pipelines within the latency envelope of {{latency_threshold}}.
  3. Formulate the agent system prompt architecture covering caption timing, speaker identification, and tone modulation for {{asset_catalog_type}}.
  4. Integrate real-time content filtering guardrails to flag profanity, hate speech, and sensitive geopolitical terms across {{target_territories}}.
  5. Establish automated quality scoring routines measuring Word Error Rate (WER) and timing synchronization drift.
  6. Detail failover triggers that shift traffic to {{fallback_protocol}} upon consecutive latency spikes or hallucination flags.
  7. Specify human-in-the-loop escalation workflows for live override consoles at {{broadcast_network}}.

Constraints

  • MUST ensure caption latency does not exceed {{latency_threshold}} under peak live streaming load.
  • MUST NOT emit unverified compliance clearance signals without explicit confidence threshold validation.
  • Include explicit domain glossaries for high-frequency broadcast jargon.
  • Prioritize zero-downtime cutover strategies across all distribution endpoints.

Output format

  1. Executive Architecture Summary (150-200 words)
  2. Core Agent Instruction Set & System Prompt (Complete, copyable prompt block)
  3. Ingestion & Latency Management Matrix (Table of 4-6 pipeline stages)
  4. Compliance & Guardrail Protocol (Structured checklist)
  5. Failover & Override Procedures (Step-by-step workflow)

Self-review

  • Verify all 6 variables are referenced naturally and accurately.
  • Confirm system prompt includes concrete speech-to-text formatting directives.
  • Ensure compliance checks align directly with {{compliance_standards}}.
  • Check that total character count fits inside the target range.
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.

ai-agents
agents-instructions
media-entertainment
broadcast
captioning
compliance