Reasoning & math
AuraScore 87/100

Production Inventory Buffer Sizing and Safety Stock Framework

Size raw material buffer inventories and dynamic safety stock levels using demand and lead-time stochastic models.

Use this template when supply chain disruptions or production scheduling volatility cause stockouts or excess holding costs. It provides a deterministic and probabilistic safety stock framework for production inventory planners.

Template

Role: Senior Supply Chain Quantitative Modeler and Production Planning Engineer with specialization in stochastic inventory optimization.

Context

  • Raw material SKU: {{raw_material_sku}}
  • Annual production requirement: {{annual_demand_units}}
  • Carrying cost rate per unit: {{unit_holding_cost}}
  • Purchase order procurement cost: {{ordering_setup_cost}}
  • Supplier average lead time: {{lead_time_days}}
  • Supplier lead time standard deviation: {{lead_time_std_dev}}

Task

Design a mathematically rigorous safety stock and reorder point (ROP) sizing framework for {{raw_material_sku}} that balances stockout risk against carrying costs at target service levels.

Method

  1. Formulate the classic Wilson Economic Order Quantity (EOQ) equation using {{annual_demand_units}}, {{ordering_setup_cost}}, and {{unit_holding_cost}}.
  2. Compute the deterministic base lead time demand (LTD) using {{lead_time_days}} and average daily production consumption.
  3. Formulate the stochastic safety stock equation accounting for combined demand uncertainty and lead time variance ({{lead_time_std_dev}}).
  4. Calculate the safety stock buffer volume across three standardized service level z-scores: 90% (z=1.28), 95% (z=1.65), and 99% (z=2.33).
  5. Compute the composite Reorder Point (ROP = LTD + Safety Stock) for each service level tier.
  6. Evaluate annual holding cost implications for each safety stock tier versus potential downtime financial penalties.
  7. Construct a dynamic adjustment modifier that scales buffer requirements during supplier shutdown seasons.
  8. Specify standard inventory trigger rules for automated ERP purchase requisition generation.

Constraints

  • MUST compute exact numerical formulas for EOQ, Safety Stock, and ROP with step-by-step variable substitution.
  • MUST evaluate safety stock specifically against supplier variability defined by {{lead_time_std_dev}}.
  • MUST NOT recommend static buffers without demonstrating the statistical confidence interval.
  • Exclude speculative market pricing fluctuations; focus strictly on inventory mechanics.

Output format

Provide the output structured under these four required sections:

  1. Mathematical Formulas & Variable Mapping (EOQ, Combined Variance Safety Stock, and ROP equations)
  2. Service Level Buffer Trade-off Table (columns: Service Level %, Z-score, Safety Stock Units, Total ROP Units, Annual Holding Cost)
  3. Sensitivity Analysis Narrative (2 paragraphs examining impact of supplier lead time volatility on working capital)
  4. ERP Integration Logic (exact logical conditions for triggering PO generation and buffer revisions)

Self-review

  • Did I apply the combined variance formula correctly when lead time itself is stochastic (sigma_LT > 0)?
  • Are {{raw_material_sku}}, {{annual_demand_units}}, {{unit_holding_cost}}, {{ordering_setup_cost}}, {{lead_time_days}}, and {{lead_time_std_dev}} completely integrated?
  • Are the calculations fully reproducible by a material requirements planner using standard math tools?
AuraScore breakdown
87/100Provisional
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 specification14/14 · Strong

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-reasoning-math
manufacturing-industrial
inventory-optimization
safety-stock
eoq