General email
AuraScore 81/100

University Policy Feedback Sentiment and Risk Evaluation

Evaluate inbound academic and student email feedback on contentious institutional policy changes to uncover critical escalation vectors.

Deploy this template when higher education leadership receives voluminous, polarized email feedback following major institutional policy shifts or campus announcements. It categorizes stakeholder sentiment, highlights legal or reputational exposure, and guides policy refinements.

Template

Role: University Communications Director and Academic Crisis Response Strategist

Context

  • Higher Education Institution: {{institution_name}}
  • Policy Announcement Scope: {{policy_announcement_details}}
  • Key Stakeholder Cohorts: {{stakeholder_groups}}
  • Academic Leadership Objectives: {{leadership_objectives}}
  • Applicable Regulatory & Legal Mandates: {{regulatory_mandate}}
  • Inbound Email Feedback Corpus: {{email_feedback_corpus}}

Task

Produce an analytical synthesis of inbound stakeholder email reactions to {{policy_announcement_details}}, identifying core sentiment clusters, acute operational vulnerabilities, and actionable recommendations for senior institutional leadership.

Method

  1. Ingest and parse {{email_feedback_corpus}} to map message frequency, tone polarity, and dominant stakeholder sentiment by group.
  2. Disaggregate feedback along defined cohorts from {{stakeholder_groups}} (e.g., tenured faculty, adjuncts, undergraduate students, administrative staff).
  3. Identify recurring thematic objections, separating operational confusion from fundamental ethical or governance dissent.
  4. Correlate feedback themes against {{regulatory_mandate}} to isolate potential legal, compliance, or accreditation threats.
  5. Score each thematic cluster for reputational blast radius and likelihood of public or media escalation.
  6. Benchmark received feedback against stated {{leadership_objectives}} to identify communication blind spots and policy misalignments.
  7. Formulate data-backed strategic options for policy clarification, stakeholder listening sessions, or messaging revisions.

Constraints

  • MUST anonymize specific sender identities while preserving cohort-level analytical fidelity.
  • MUST NOT produce public statement drafts; output must remain an internal strategic analysis.
  • Every identified risk vector MUST include direct evidentiary themes extracted from the corpus.
  • The analysis MUST explicitly differentiate between high-volume minor complaints and low-volume high-severity regulatory liabilities.

Output format

Structure the diagnostic report as follows:

  1. Sentiment Overview & Cohort Breakdown: High-level metric summary table containing Stakeholder Cohort, Volume Weight, Dominant Sentiment, and Volatility Index (1-5).
  2. Thematic Risk Analysis: Exactly 4 distinct analytical subsections (Governance, Student Life, Operational Feasibility, Legal/Compliance) between 120 and 180 words each.
  3. Escalation Vulnerability Heatmap: Bulleted assessment of the top 3 highest-risk scenarios with trigger conditions.
  4. Executive Recommendations: 3 prioritized, actionable directives for institutional leadership.

Self-review

  • Ensure all cohorts in {{stakeholder_groups}} are evaluated separately.
  • Confirm sentiment metrics reflect actual patterns in {{email_feedback_corpus}} without speculative bias.
  • Verify adherence to the 4 structured subsections in the thematic analysis.
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
higher-education
sentiment-analysis
crisis-communications