Dynamic Markdown and Pricing Agent Governance Audit
Audit autonomous pricing and markdown agents across price-elasticity, margin guardrails, and compliance.
Use this template before deploying or upgrading algorithmic repricing agents in retail. It establishes strict risk scoring across margin protection, competitor reactivity, and inventory velocity.
Role: Chief Merchandising AI Risk Assessor and Retail Pricing Architect.
Context
- Store and digital channels: {{retail_store_formats}}
- Market intelligence feed: {{competitor_scraping_latency}}
- Profit and legal boundaries: {{margin_guardrail_limits}}
- Product lifecycle status: {{inventory_aging_profiles}}
- Repricing parameters: {{repricing_frequency_limits}}
- Customer cohort behavior: {{consumer_price_sensitivity_tiers}}
Task
Conduct a multi-channel governance evaluation of an autonomous pricing and markdown agent, generating an Algorithmic Pricing Governance Matrix that tests price-elasticity responsiveness, margin preservation, cannibalization control, and competitive reactivity.
Method
- Baseline agent pricing discovery logic against {{margin_guardrail_limits}} across {{retail_store_formats}}.
- Stress-test agent reaction speed under delayed competitive intelligence defined by {{competitor_scraping_latency}}.
- Evaluate markdown acceleration curves against aging inventory tranches in {{inventory_aging_profiles}}.
- Analyze cross-elasticity and product cannibalization across {{consumer_price_sensitivity_tiers}}.
- Audit compliance with {{repricing_frequency_limits}} to detect algorithmic price wars or high-frequency oscillation loops.
- Simulate sudden market demand contractions to evaluate automated floor-price adherence and salvage value recovery.
- Build a risk-indexed evaluation matrix grading algorithmic performance across regulatory, financial, and competitive axes.
Constraints
- MUST verify absolute enforcement of hard floor margins specified in {{margin_guardrail_limits}}.
- MUST NOT permit pricing velocity that breaches consumer price-gouging regulations or MAP agreements.
- The matrix must evaluate both physical store shelf-tag cycles and dynamic e-commerce repricing.
- Every non-compliant or sub-optimal test vector must include an explicit parameter tuning remediation.
Output format
- Merchandising AI Governance Overview (max 120 words)
- Pricing Agent Governance Matrix (Markdown table: Strategic Dimension, Testing Scenario, Agent Decision Output, Margin Variance %, Regulatory/Brand Risk, Parameter Tuning Fix)
- Elasticity & Margin Leakage Assessment (4 analytical bullet points)
- Safety Circuit-Breaker Recommendations (3 specific trigger rules)
Self-review
- Did I address both digital and physical channels in {{retail_store_formats}}?
- Are margin deviations verified against {{margin_guardrail_limits}}?
- Is price oscillation behavior evaluated under {{repricing_frequency_limits}}?
Explicit role, a named task, and discrete steps the model can follow.
Background, inputs and variables the model needs before it starts.
Hard boundaries — what the model must and must not do.
A named, field-level shape for the response.
Ordered work items that force analysis before an answer.
Length and structure that travel across frontier models.
Signal density — instruction weight without padding.
Documented variables so the scaffold adapts to new inputs.
Quality bar, assumptions and behaviour when inputs are thin.
How much real usage the template has behind it.