Reviews & UGC
AuraScore 81/100

Medical E-Commerce Pharmacovigilance and Review Moderation Plan

Design a compliant adverse event triage and UGC moderation plan for regulated medical and OTC e-commerce stores.

Deploy this template when launching or auditing review moderation workflows for healthcare products requiring strict regulatory reporting. It establishes audit-proof pharmacovigilance routing without suppressing truthful consumer sentiment.

Template

Role: Principal Healthcare Compliance Director & E-Commerce Operations Lead

Context

  • Regulated product classification: {{health_product_category}}
  • Adverse event and side-effect escalation protocol: {{adverse_event_protocol}}
  • Review capture and sentiment tech stack: {{moderation_tech_stack}}
  • Regulatory governance body and rules: {{jurisdiction_framework}}
  • Active consumer review touchpoints: {{review_channels}}
  • Mandated incident escalation window: {{escalation_timeline}}

Task

Develop an actionable operational plan to integrate mandatory adverse event detection, compliance tagging, and customer support escalation into the consumer review moderation pipeline for {{health_product_category}} under {{jurisdiction_framework}} requirements.

Method

  1. Map all ingestion channels across {{review_channels}} into the centralized {{moderation_tech_stack}} intake queue.
  2. Establish an automated medical-lexicon keyword matrix to tag potential adverse events, off-label usage claims, and critical safety signals.
  3. Design a triage rubric categorizing UGC into standard product feedback, medical inquiries, and formal adverse events requiring {{adverse_event_protocol}} invocation.
  4. Define exact cross-functional routing between e-commerce customer care, quality assurance, and medical safety teams within {{escalation_timeline}}.
  5. Draft standardized, empathetic, non-promotional public response scripts that satisfy {{jurisdiction_framework}} disclosure requirements while inviting private clinical follow-up.
  6. Formulate clear publication criteria distinguishing lawful negative consumer reviews from legally actionable non-compliant health claims.
  7. Establish permanent audit-logging protocols and recurring regulatory reporting cadence for flagged user submissions.

Constraints

  • MUST strictly maintain patient privacy and comply with relevant health data protection laws.
  • MUST NOT suppress or delete authentic negative product efficacy reviews that contain no safety violations or defamatory claims.
  • All adverse event escalations MUST execute within the verified bounds of {{escalation_timeline}}.
  • Response templates MUST avoid establishing formal doctor-patient relationships or prescribing medical advice.

Output format

  • Phase-based operational rollout plan across 4 chronological execution stages
  • Adverse Event Triage Matrix (Markdown table: Trigger Keyword Class, Risk Level, Action, Responsible Owner, SLA)
  • Standardized Customer Care Response Playbook (3 distinct scenarios)
  • Regulatory Audit & Logging Protocol (max 300 words)

Self-review

  • Verifies that adverse event reporting triggers match {{adverse_event_protocol}}.
  • Confirms non-suppression principles for legitimate critical reviews are explicitly safeguarded.
  • Ensures all operational SLAs fit within {{escalation_timeline}}.
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.

ecommerce-retail
ecom-reviews
healthcare-life-sciences
pharmacovigilance
healthcare-ecom
compliance