Holiday Returns Knowledge Base Gap Analysis
Evaluate retail return and exchange documentation to minimize seasonal ticket escalation.
Use this template following peak retail surges to analyze deflections, identify article ambiguities, and streamline customer self-service. It helps CX leaders align return policies, warranty guides, and refund workflows across all support tiers.
Role: Principal Customer Experience Knowledge Architect specializing in retail e-commerce workflows.
Context
- Retail brand name: {{brand_name}}
- Peak seasonal period evaluated: {{peak_return_period}}
- Dominant escalation drivers: {{top_escalation_topics}}
- Desired digital containment threshold: {{target_containment_rate}}
- Support channels currently deployed: {{channel_breakdown}}
- Active knowledge management stack: {{current_kb_platforms}}
Task
Produce an exhaustive audit report examining the self-service knowledge base coverage for post-purchase returns, exchanges, and warranty inquiries for {{brand_name}}, delivering concrete content revisions and search optimization tactics to achieve {{target_containment_rate}}.
Method
- Analyze the performance data across {{channel_breakdown}} during {{peak_return_period}} to identify drop-off points in self-service paths.
- Cross-reference documented return and refund policies against the recorded {{top_escalation_topics}}.
- Audit search keyword telemetry within {{current_kb_platforms}} to uncover high-volume zero-result search queries.
- Evaluate readability, policy clarity, and step-by-step instructions for top-trafficked customer-facing articles.
- Map internal agent macro responses to public-facing articles to surface discrepancies in guidance.
- Formulate restructured hierarchy rules for return eligibility, processing timelines, and exceptions.
- Develop actionable rewrites for underperforming articles with simplified decision trees.
- Establish continuous maintenance cycles and telemetry alerts for seasonal policy updates.
Constraints
- MUST anchor all recommendations in measurable metrics tied to {{target_containment_rate}}.
- MUST NOT introduce policy changes that conflict with retail consumer protection regulations.
- Technical suggestions MUST stay compatible with {{current_kb_platforms}}.
- Every identified content gap must include a corresponding root-cause diagnosis.
Output format
Provide a formal report structured into the following sections:
- Executive Summary (under 250 words)
- Policy-to-Article Alignment Matrix (table covering at least 5 critical return scenarios)
- Top 5 High-Impact Content Rewrites (showing before-and-after structural diffs)
- Search Intent and Taxonomy Overhaul (keyword mapping and navigation trees)
- Implementation Timeline and Governance Cadence
Self-review
- Ensure all variables ({{brand_name}}, {{peak_return_period}}, {{top_escalation_topics}}, {{target_containment_rate}}, {{channel_breakdown}}, {{current_kb_platforms}}) are directly referenced and addressed.
- Verify that recommendations specifically solve retail return frictions rather than generic support issues.
- Confirm clear distinction between customer-facing self-service and agent-facing reference materials.
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.