Evaluation
AuraScore 81/100

Algorithmic Dynamic Pricing Agent Compliance Checklist

Audit autonomous retail pricing and markdown agents for margin floors, MAP compliance, and competitive safeguards.

Use this checklist when auditing the logic, regulatory compliance, and margin safety of automated pricing engines. It ensures autonomous pricing updates stay within brand agreements, avoid runaway repricing, and respect promotional calendars.

Template

Role: Senior Retail Revenue Operations & Algorithmic Pricing Auditor specializing in consumer goods market dynamics.

Context

  • Assortment scope: {{product_assortment_tier}}
  • Pricing engine platform: {{pricing_engine_framework}}
  • Minimum advertised price rules: {{map_compliance_rules}}
  • Scraping & competitor inputs: {{competitor_feed_frequency}}
  • Minimum margin thresholds: {{margin_floor_limits}}
  • Marketing events schedule: {{promotional_calendar_constraints}}

Task

Construct an end-to-end audit checklist to evaluate dynamic pricing and markdown agents for {{product_assortment_tier}}, ensuring strict margin protection, regulatory compliance, and brand equity defense.

Method

  1. Review {{product_assortment_tier}} and {{margin_floor_limits}} to set non-negotiable floor price barriers across all product sub-categories.
  2. Analyze {{map_compliance_rules}} to construct audit steps that catch unauthorized automated discounting on restricted vendor SKUs.
  3. Evaluate the integration of {{competitor_feed_frequency}} to design stress tests detecting algorithmic loops (e.g., race-to-the-bottom repricing).
  4. Cross-reference {{promotional_calendar_constraints}} to verify the agent accurately schedules, executes, and expires promotional markdowns.
  5. Establish latency and throughput verification steps for {{pricing_engine_framework}} during high-traffic flash sales and peak retail events.
  6. Design price elasticity anomaly checks ensuring sudden demand spikes do not trigger anti-consumer price gouging behaviors.
  7. Formulate rollback and circuit-breaker verification checks to immediately pause automated pricing if erroneous outputs exceed risk limits.

Constraints

  • Pricing actions MUST NEVER violate {{margin_floor_limits}} or {{map_compliance_rules}} under any competitive condition.
  • The audit MUST verify both batch repricing and real-time intra-day repricing cycles.
  • Checklist items MUST include specific detection methods for competitor data scraping failures or corrupted input data.
  • Remediation plans MUST define automatic circuit breakers that revert prices to the previous stable baseline.

Output format

  • Section 1: Pricing Engine Governance Framework (max 150 words)
  • Section 2: Margin & Contractual Compliance Checklist (table with Columns: Control ID, Risk Area, Test Method, Deterministic Pass Criteria, Impact Level)
  • Section 3: Algorithmic Feedback Loop & Competitor Response Checks (bulleted checklist with specific validation scripts)
  • Section 4: Emergency Failsafe & Kill-Switch Validation Protocol (step-by-step checklist)

Self-review

  • Are all 6 pricing and market variables directly evaluated in the checklist?
  • Does the checklist include protections against margin dilution and race-to-the-bottom pricing?
  • Are MAP compliance checks explicit enough to prevent legal or vendor contract breaches?
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-evaluation
retail-consumer-goods
dynamic-pricing
retail-operations
revenue-management