General email
AuraScore 81/100

At-Risk Student Early Warning Email Diagnostic and Intervention Strategy

Evaluate student retention outreach and construct an actionable early-alert email intervention report for advising and student success teams.

Use this template when designing or revamping early-alert and retention email campaigns for academically vulnerable students. It outputs an evidence-backed diagnostic report with behavioral email nudges, response tracking metrics, and advisor intervention playbooks.

Template

Role: Executive Director of Academic Advising and Retention Analytics with expertise in behavioral nudging and student persistence.

Context

  • Academic division or program: {{academic_unit}}
  • Student population characteristics: {{student_demographics}}
  • Historical email engagement benchmarks: {{current_open_rates}}
  • Early warning academic criteria: {{intervention_trigger_criteria}}
  • Available campus academic support resources: {{support_resource_inventory}}
  • Critical intervention and withdrawal deadlines: {{response_deadline_window}}

Task

Produce an early-warning student communication diagnostic report that redesigns notification workflows into high-converting, supportive, and behavioral-nudged email interventions to maximize student advising appointments and academic recovery.

Method

  1. Analyze {{student_demographics}} and {{current_open_rates}} to diagnose why existing warning notifications fail to generate student engagement.
  2. Apply behavioral economics frameworks (e.g., choice architecture, loss aversion framing, social proof) to reduce cognitive overload and defensive avoidance.
  3. Map {{intervention_trigger_criteria}} into three distinct urgency tiers (Tier 1: Minor dip/Midterm check; Tier 2: Multiple course alerts; Tier 3: Immediate probation risk).
  4. Cross-reference {{support_resource_inventory}} to embed frictionless, single-click booking links for tutoring, writing centers, and peer mentoring.
  5. Draft fully realized email variants for each tier, calibrated to overcome fear and promote growth-mindset self-efficacy.
  6. Construct micro-copy components (preview text, sender display names, button text) optimized for mobile reading habits.
  7. Establish a multi-step follow-up cadence leading up to {{response_deadline_window}} for students who do not open or click initial emails.

Constraints

  • MUST NOT use punitive, stigmatizing, or shaming language in any email copy.
  • MUST craft complete, un-redacted email drafts for all 3 designated urgency tiers.
  • MUST include explicit instructions for calendar scheduling calls-to-action within the first 100 words of each email draft.
  • MUST cite specific institutional resources from {{support_resource_inventory}} in each template.

Output format

Deliver an academic retention report structured as follows:

  1. Engagement Diagnostic & Behavioral Framing Analysis (max 300 words)
  2. Tiered Early-Alert Intervention Matrix (Table: Alert Tier, Trigger Metric, Urgency Level, Sender Alias, Primary Action)
  3. Tier 1-3 Email Nudge Blueprints (Complete copy for 3 tiers with Subject, Preheader, Personalized Body Copy, Direct Action Link, Resource Sidebar)
  4. Non-Responder Follow-up and Re-engagement Cadence (Sequence of 2 automated follow-up messages)
  5. Advising Operations Workflow & Outcome Metrics (max 250 words)

Self-review

  • Confirm that every email draft sounds empathetic, non-judgmental, and genuinely supportive.
  • Ensure each draft contains a singular, frictionless call-to-action that respects {{response_deadline_window}}.
  • Verify that mobile display constraints (character limits on subject lines and preview text) are strictly observed.
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.

emails
emails-general
education-research
student-retention
academic-advising
nudge-strategy