Knowledge base
AuraScore 81/100

Omnichannel Return Policy Knowledge Base Gap Analysis

Identify discrepancies and customer friction points across retail return and exchange knowledge base articles.

Use this prompt when updating retail support content after policy shifts or channel expansions. It pinpoints knowledge gaps between digital self-service articles and physical store return workflows.

Template

Role: Principal Omnichannel Customer Experience Architect with fifteen years of retail operations expertise.

Context

  • Retail brand: {{retail_brand_name}}
  • Core product categories: {{product_categories}}
  • Existing policy documentation: {{current_kb_articles}}
  • Recent policy and operational changes: {{return_policy_changes}}
  • High-volume ticket themes: {{support_ticket_trends}}
  • Applicable commerce channels: {{target_channels}}

Task

Conduct a rigorous knowledge gap and friction analysis comparing current self-service articles with updated return policies across all retail channels, delivering prioritized recommendations to reduce support contact rates.

Method

  1. Map {{current_kb_articles}} against {{return_policy_changes}} to isolate outdated conditions, timeline discrepancies, and contradictory rules.
  2. Cross-reference {{support_ticket_trends}} to identify high-friction customer queries currently unaddressed by self-service documentation.
  3. Evaluate channel parity across {{target_channels}}, ensuring buy-online-return-in-store (BORIS) and mail-in rules are distinct and explicit.
  4. Analyze readability and jargon within the content for {{product_categories}}, highlighting restrictive terms that confuse shoppers.
  5. Score each article across four criteria: policy accuracy, channel consistency, findability, and dispute-prevention efficacy.
  6. Classify discovered documentation deficiencies by customer impact, contact deflection potential, and operational risk.
  7. Formulate specific copy corrections, layout adjustments, and new topic requirements for each flagged knowledge asset.

Constraints

  • Recommendations MUST directly cite contradictory phrasing between {{current_kb_articles}} and {{return_policy_changes}}.
  • MUST NOT suggest adding unstructured policy text that exceeds an eighth-grade reading comprehension level.
  • Findings must distinguish between physical retail rules and digital e-commerce workflows.
  • Prioritization must reflect ticket volume severity indicated in {{support_ticket_trends}}.

Output format

Provide an analysis document with the following structure:

  1. Executive Summary (under 200 words)
  2. Policy Inconsistency Matrix (markdown table: Article Title, Current Stated Policy, Actual Policy, Severity Score 1-5)
  3. Channel-Specific Friction Audit (detailed findings grouped by channel in {{target_channels}})
  4. High-Volume Inquiry Coverage Gaps (bulleted analysis linking to {{support_ticket_trends}})
  5. Remediation Roadmap (table: Topic, Action Required, Expected Deflection Lift, Implementation Effort)

Self-review

  • Confirm every channel in {{target_channels}} has dedicated analysis.
  • Verify that all identified policy contradictions cite exact snippets from {{current_kb_articles}}.
  • Check that the total remediation roadmap contains actionable, concrete article revisions.
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.

support-success
support-knowledge-base
retail-consumer-goods
returns
omnichannel
retail