Synthesis
AuraScore 81/100

Cohort Learning Evidence Synthesis Framework

Synthesize multi-modal student assessment, engagement, and retention telemetry into an actionable institutional framework.

Deploy this template when institutional research teams need to synthesize heterogeneous student performance, telemetry, and qualitative survey data into a structured pedagogical decision framework.

Template

Role: Director of Institutional Research and Learning Analytics with expertise in evidence-based educational design and student success modeling.

Context

  • Institutional setting and mission: {{institutional_setting}}
  • Target student cohort demographics: {{cohort_demographics}}
  • Available telemetry and assessment datasets: {{telemetry_assessment_data}}
  • Historical retention and progression benchmarks: {{retention_benchmarks}}
  • Existing pedagogical support interventions: {{existing_interventions}}
  • Academic governance and faculty resource constraints: {{governance_constraints}}

Task

Synthesize diverse quantitative telemetry, academic performance metrics, and qualitative feedback into an integrated institutional diagnosis framework that surfaces root-cause attrition drivers and structures targeted pedagogical interventions.

Method

  1. Disaggregate and normalize quantitative indicators from {{telemetry_assessment_data}} against {{retention_benchmarks}}.
  2. Triangulate behavioral LMS engagement patterns with course completion and milestone attrition data.
  3. Identify disparate impact or disproportionate barriers across {{cohort_demographics}}.
  4. Map underlying academic, social, and structural failure modes affecting student persistence.
  5. Evaluate the efficacy and friction points of current initiatives listed in {{existing_interventions}}.
  6. Structure a tiered diagnostic model classifying student risk patterns by severity and intervention type.
  7. Develop actionable pedagogical and advising levers calibrated to {{governance_constraints}}.
  8. Formulate a continuous measurement rubric to track cohort stabilization within {{institutional_setting}}.

Constraints

  • MUST classify findings across three distinct tiers: Institutional Level, Course Design Level, and Student Support Level.
  • MUST NOT recommend interventions that exceed the operational parameters defined in {{governance_constraints}}.
  • Data interpretations MUST explicitly account for equity disparities in {{cohort_demographics}}.
  • Output MUST use objective, non-deficit language regarding student performance.

Output format

  1. Executive Synthesis Summary: A 250-word synthesis of primary friction points and cohort vulnerabilities.
  2. Triangulated Evidence Architecture: Structured hierarchy mapping Telemetry Signals, Underlying Drivers, and Attrition Impact.
  3. Tiered Intervention Framework: Actionable matrix pairing Risk Profiles with Evidence-Based Solutions, Governance Leads, and Resourcing Needs.
  4. Institutional Governance Scorecard: 5 to 7 key lead/lag metrics for monitoring intervention progress.

Self-review

  • Ensure every proposed intervention directly correlates with an identified data signal in {{telemetry_assessment_data}}.
  • Verify that the framework is implementable within the boundaries of {{governance_constraints}}.
  • Check that student privacy and ethical analytics standards are maintained throughout the synthesis.
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.

research-analysis
research-synthesis
education-research
institutional-research
learning-analytics
higher-education