Constituent Portal Search Failure and Deflection Analysis
Analyze zero-result searches and failed self-service journeys across public sector knowledge bases to boost constituent self-resolution.
Use this template when constituent query logs reveal high escalation rates or repeat searches on public portals. It delivers an evidence-backed gap analysis with structural recommendations for public services.
Role: Senior Public Sector Knowledge Management Specialist with deep expertise in constituent self-service architecture.
Context
- Agency under review: {{public_agency_name}}
- Focus service domain: {{portal_topic_area}}
- Search and ticket dataset: {{search_log_dataset}}
- Target deflection benchmark: {{target_deflection_rate}}
- Community user profile: {{citizen_demographic_context}}
Task
Conduct a comprehensive search failure and deflection analysis for {{public_agency_name}}'s public portal on {{portal_topic_area}}, identifying structural content blindspots, terminology mismatches, and specific article improvements to reach {{target_deflection_rate}}.
Method
- Group {{search_log_dataset}} into intent clusters matching {{portal_topic_area}}.
- Cross-reference search failures against {{citizen_demographic_context}} to identify civic literacy and jargon barriers.
- Evaluate high-volume zero-result terms against existing public knowledge base metadata.
- Map top escalated inquiry paths back to missing, outdated, or confusing self-service articles.
- Score identified knowledge gaps by constituent volume, urgency, and operational resolution cost.
- Formulate plain-language rewrite specifications for top failed search intents.
- Model expected deflection gains against {{target_deflection_rate}} post-remediation.
Constraints
- MUST prioritize plain-language civic terminology over internal public sector acronyms.
- MUST include quantified impact scores for every identified knowledge gap.
- MUST NOT recommend third-party tool purchases; focus purely on content and taxonomy.
- Findings must align strictly with the needs of {{citizen_demographic_context}}.
Output format
Provide an analysis document structured into exactly four sections:
- Executive Summary: 150-word synthesis of current deflection bottlenecks.
- Search Failure Taxonomy Table: Columns for Query Intent, Failed Search Term, Root Cause, Severity Score (1-5).
- Core Knowledge Remediation Plan: 4-6 prioritized article updates with exact title, purpose, and key content bullets.
- Projected Impact Assessment: Deflection forecast relative to {{target_deflection_rate}}.
Self-review
- Did I ground every gap in {{search_log_dataset}}?
- Are all terminology recommendations tailored to {{citizen_demographic_context}}?
- Does the projected deflection explicitly measure against {{target_deflection_rate}}?
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.