Reporting
AuraScore 79/100

Cloud Infrastructure Spend Variance and Utilization Diagnostic

Analyze cloud infrastructure cost reporting to diagnose resource waste, compute variance, and budget attribution gaps.

Use this template when monthly multi-cloud infrastructure bills exceed planned engineering budgets. It generates an analytical diagnostic identifying idle resources, unit economic drift, and cost center anomalies.

Template

Role: Senior FinOps Analytics Specialist with deep expertise in cloud cost intelligence, Kubernetes workload economics, and cloud financial reporting.

Context

  • Cloud Architecture Provider: {{cloud_provider_environment}}
  • Audited Billing Cycle: {{billing_cycle_period}}
  • Cost Allocation Dataset: {{cost_attribution_dataset}}
  • Baseline Unit Economics: {{unit_metric_baseline}}
  • Budget Variance Threshold: {{budget_variance_threshold}}
  • Responsible Engineering Department: {{engineering_team_division}}

Task

Deliver an exhaustive cloud spend diagnostic analysis evaluating financial reporting across {{billing_cycle_period}}, determining drivers of budget overruns beyond {{budget_variance_threshold}}, and quantifying optimization levers across {{cloud_provider_environment}}.

Method

  1. Normalize spend logs across {{cost_attribution_dataset}} to identify top compute, storage, and egress spending categories.
  2. Compare actual expenditures against {{budget_variance_threshold}} to calculate absolute and percentage variances by service.
  3. Correlate total infrastructure expenditure against {{unit_metric_baseline}} to establish whether cost spikes reflect legitimate product scaling or infrastructure inefficiency.
  4. Analyze compute utilization reports to detect over-provisioned node pools, idle database instances, and orphaned volumes.
  5. Audit unallocated or improperly tagged cloud assets within {{engineering_team_division}}.
  6. Evaluate pricing model coverage, identifying potential savings from commitment discounts, reserved instances, or spot instance re-architecting.
  7. Calculate cost avoidance projections for top identified waste patterns over a forward-looking 12-month horizon.

Constraints

  • MUST express all financial figures in exact dollar amounts and percentage changes.
  • MUST NOT recommend cost reductions that compromise system reliability or violate application SLAs.
  • MUST evaluate spending efficiency using {{unit_metric_baseline}} rather than raw top-line spend alone.
  • Restrict recommendations to operational, architectural, and financial commitments within {{cloud_provider_environment}}.

Output format

Provide the complete analysis organized under these mandatory headings:

  1. FinOps Executive Variance Summary (max 250 words)
  2. Service-Level Cost Breakdown (table detailing Service, Allocated Budget, Actual Spend, Variance %, Primary Driver)
  3. Unit Economic Efficiency Assessment (analysis of cost per unit metric relative to {{unit_metric_baseline}})
  4. High-Yield Rightsizing & Architectural Interventions (3-5 ranked cost optimization measures with estimated monthly savings)

Self-review

  • Are all cost spikes explicitly compared against {{budget_variance_threshold}}?
  • Did I analyze utilization metrics alongside financial billing data?
  • Does the unit economic analysis account for business growth in {{engineering_team_division}}?
AuraScore breakdown
79/100Provisional
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.

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.

data-analytics
data-reporting
technology-software
finops
cloud-analytics
spend-reporting