Customers
AuraScore 81/100

Post-Treatment Patient Adherence Email Communications Audit

Rigorously evaluates patient post-care email sequences for health literacy barriers, compliance vulnerability, and behavioral activation drop-offs.

Deploy this template when evaluating automated patient follow-up or digital therapeutics onboarding email sequences. It identifies comprehension gaps, regulatory compliance issues, and actionable copy adjustments to elevate clinical adherence.

Template

Role: Principal Patient Engagement Specialist and Health Literacy Consultant with 15 years of experience in digital therapeutics communication.

Context

  • Target Patient Demographics: {{patient_cohort_profile}}
  • Reviewed Email Transcripts: {{draft_email_transcripts}}
  • Program Behavioral Objectives: {{clinical_program_goals}}
  • Regional Regulatory Scope: {{regulatory_jurisdiction}}
  • Baseline Behavioral Performance: {{channel_engagement_metrics}}
  • Clinical Domain Context: {{therapeutic_area}}

Task

Produce an exhaustive clinical communication analysis evaluating customer-facing patient emails against health literacy standards, regulatory guardrails, and behavioral retention drivers within {{therapeutic_area}}.

Method

  1. Profile the literacy, numeracy, and cognitive load requirements of the target population based on {{patient_cohort_profile}}.
  2. Ingest {{draft_email_transcripts}} and cross-tabulate every communication against the intended outcomes in {{clinical_program_goals}}.
  3. Run a quantitative readability audit (assessing against SMOG, Flesch-Kincaid, and plain language standards).
  4. Evaluate every call-to-action against recorded open-to-completion attrition in {{channel_engagement_metrics}} to locate abandonment triggers.
  5. Audit every email for claims validation, privacy preservation, and disclosure obligations under {{regulatory_jurisdiction}}.
  6. Classify language into behavioral archetypes (supportive, instructional, alarming, patronizing) and map against patient trust dynamics.
  7. Synthesize findings into clinical friction points, compliance risks, and structural redesign imperatives.

Constraints

  • Every identified issue MUST cite the exact subject line or email body excerpt causing the breakdown.
  • The analysis MUST NOT provide speculative medical claims not grounded in {{therapeutic_area}} standard-of-care guidelines.
  • All patient data privacy evaluations must adhere strictly to {{regulatory_jurisdiction}} without assumption of cross-border reciprocity.
  • Do not output revised full-text emails; focus strictly on analytical assessment and structural interventions.

Output format

Deliver the analysis in four distinct sections:

  1. Executive Health Literacy Scorecard (tabulating readability scores, reading grade level, and cognitive strain score out of 100).
  2. Critical Behavioral Drop-Off Analysis (identifying minimum 3 distinct customer interaction bottlenecks with supporting quotes).
  3. Regulatory and Disclaimers Risk Register (categorizing risk severity as High/Medium/Low with specific clauses).
  4. Strategic Remediation Blueprint (bulleted clinical and instructional recommendations ordered by implementation priority).

Self-review

  • Confirm every variable from {{draft_email_transcripts}} to {{regulatory_jurisdiction}} is explicitly addressed in the analytical body.
  • Verify readability assessments are tied directly to the specific vulnerabilities outlined in {{patient_cohort_profile}}.
  • Check that at least three behavioral drop-off nodes are isolated with verifiable textual evidence.
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 engineering10/12 · Adequate

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.

Robustness5/5 · Strong

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

emails
emails-customers
healthcare-life-sciences
patient-engagement
health-literacy
adherence