Agent instructions
AuraScore 81/100

Music Synchronization and Media Rights Clearance Agent Instruction Architecture

Formulate robust decision instructions and risk scoring protocols for autonomous licensing and intellectual property clearance agents.

Use this template when deploying legal-tech media agents that review sync requests, cue sheets, and talent contracts across global media territories. It structures deterministic verification logic and contractual edge-case escalation rules.

Template

Role: Senior Director of Entertainment Business Affairs and Legal Automation Architect.

Context

  • Studio Entity: {{production_studio}}
  • Distribution & Territory Scope: {{licensing_territory_scope}}
  • Windowing Rules: {{distribution_window}}
  • Contract Database Structure: {{contract_database_schema}}
  • Legal Exception Thresholds: {{fair_use_exception_thresholds}}
  • Mandatory Escalation Triggers: {{legal_escalation_triggers}}

Task

Develop a comprehensive agent instruction architecture report that configures an autonomous music clearance and rights verification agent, enabling deterministic contract ingestion, risk scoring, MFN compliance verification, and human legal handoff.

Method

  1. Define the legal-operational scope, domain boundary, and precision requirements for the clearance agent at {{production_studio}}.
  2. Structure parsing directives for extracting cue sheet data, master recordings, publisher splits, and PRO affiliations from {{contract_database_schema}}.
  3. Formulate logic gates that verify territorial coverage and distribution term alignment against {{licensing_territory_scope}} and {{distribution_window}}.
  4. Draft strict instruction rules for detecting Most Favored Nations (MFN) clauses, sync fee parity violations, and uncredited interpolations.
  5. Establish decision trees for incidental background audio assessment in accordance with {{fair_use_exception_thresholds}}.
  6. Embed deterministic escalation rules that route high-liability scenarios to human legal counsel based on {{legal_escalation_triggers}}.
  7. Detail the risk-assessment output schema, calculating a composite clearance confidence index for each cue.
  8. Formulate audit-logging instructions to maintain defensible evidentiary chains of custody for production insurance audits.

Constraints

  • MUST enforce deterministic 'CLEAR', 'FLAGGED', or 'BLOCKED' statuses for every reviewed cue.
  • MUST NOT permit the agent to execute binding legal settlements or sign off on missing master rights.
  • Instructions must account for split-publishing ownership disputes.
  • Specification must adhere to corporate entertainment legal compliance standards.

Output format

Deliver an Agent Instruction Architecture Report formatted as:

  • System Scope & Legal Operations Framework
  • Verbatim Agent Instruction Prompt (the operational prompt containing all logic gates and constraints)
  • Clearance Decision Matrix (table detailing input cue parameters, matching criteria, and status outcomes)
  • Risk Scoring Model & Escalation Protocol (weights, trigger thresholds, and human routing)
  • Standardized Output Contract (JSON schema containing cue metadata, status, risk score, and rationale)

Self-review

  • Confirm that {{production_studio}}, {{licensing_territory_scope}}, and all other variables are actively integrated.
  • Verify that MFN violation checks and split-publishing risks are explicitly handled in the system instructions.
  • Ensure the agent is barred from granting final clearance on missing or disputed publisher shares.
AuraScore breakdown
81/100Provisional
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.

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.

ai-agents
agents-instructions
media-entertainment
licensing
music clearance
agent instructions