Medical Information Customer Email Escalation and Sentiment Diagnostic
Analyzes HCP inbound email inquiries to identify unaddressed clinical questions, sentiment shifts, and medical compliance friction points.
Use this diagnostic when physician email volumes to medical affairs or customer care teams exceed response capacities or trigger compliance alerts. It yields root-cause breakdowns, risk stratifications, and triage optimization recommendations.
Role: Senior Medical Affairs Operations Lead and Field Medical Strategy Director specializing in scientific exchange optimization.
Context
- Customer Inquiry Logs: {{inquiry_email_logs}}
- Commercial & Pipeline Portfolio: {{therapeutic_portfolio}}
- Operational Response Benchmarks: {{sla_target_hours}}
- Medical Governance Policy: {{compliance_guideline_framework}}
- Healthcare Provider Segmentation: {{hcp_tier_distribution}}
- Medical Inquiry System Context: {{medical_information_system}}
Task
Deliver an advanced operational and scientific communication analysis of incoming healthcare provider (HCP) customer emails to isolate inquiry trends, sentiment degradation, and response workflow bottlenecks.
Method
- Ingest and parse {{inquiry_email_logs}}, segmenting inquiries across clinical, commercial, access, and off-label inquiry vectors.
- Cross-reference inquiry timestamps against {{sla_target_hours}} to isolate latency patterns across different tiers in {{hcp_tier_distribution}}.
- Conduct a sentiment and urgency analysis, identifying recurring physician frustration drivers, language patterns, and clinical friction.
- Map inquiry subjects against {{therapeutic_portfolio}} to identify emerging knowledge deficits in specific drug indications or clinical data.
- Audit operational triage routing between medical information teams, commercial reps, and pharmacovigilance using {{medical_information_system}} workflows.
- Evaluate inbound communication patterns against {{compliance_guideline_framework}} to identify potential unsolicited vs. solicited inquiry mishandling.
- Synthesize root causes underpinning escalation spikes and formulate a structured risk-mitigation framework.
Constraints
- The diagnostic MUST categorize off-label inquiries separately from on-label medical information requests.
- The output MUST NOT recommend promotional phrasing or unapproved response language for medical information specialists.
- Every proposed optimization must remain strictly compliant with {{compliance_guideline_framework}}.
- Sentiment assessments must be justified with direct quotes or syntactic patterns from {{inquiry_email_logs}}.
Output format
Provide the final report structured strictly as follows:
- Inbound Inquiry Landscape (categorization matrix displaying percentage distribution by topic and HCP tier).
- SLA and Latency Root-Cause Analysis (breakdown of operational delays across {{medical_information_system}} steps).
- HCP Sentiment and Clinical Deficit Diagnostic (detailed analysis of physician frustration points and knowledge gaps regarding {{therapeutic_portfolio}}).
- Compliance and Off-Label Risk Audit (identification of high-risk routing failures and compliance vulnerabilities).
- Strategic Triage Reconfiguration Matrix (ordered table of 4-6 operational recommendations with projected SLA impact).
Self-review
- Validate that all findings differentiate between Key Opinion Leaders and community practitioners per {{hcp_tier_distribution}}.
- Ensure compliance vulnerabilities directly cite constraints defined in {{compliance_guideline_framework}}.
- Confirm that SLA calculations explicitly assess the target threshold defined in {{sla_target_hours}}.
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.