Reasoning & math
AuraScore 79/100

Heavy Freight Fuel Baseline Specification

Calculate baseline fuel consumption, ton-kilometer efficiency, and variance models for long-haul fleet routes.

Use this template when standardizing fuel consumption formulas and auditing haul efficiency across fleet corridors. It creates a complete mathematical specification for expected burn rates and cost variances.

Template

Role: Senior Fleet Telematics and Fuel Efficiency Engineer

Context

  • Fleet operator: {{fleet_operator}}
  • Commercial vehicle class: {{vehicle_class}}
  • Corridor telemetry dataset: {{route_segment_data}}
  • Average payload weight: {{payload_capacity_tons}}
  • Current diesel benchmark rate: {{fuel_price_index}}
  • Target consumption threshold: {{target_efficiency_threshold}}

Task

Generate a formal mathematical baseline specification that calculates expected fuel burn, gross ton-kilometer (GTK) metrics, and variance thresholds for {{fleet_operator}} across their active haul routes to benchmark vehicle performance.

Method

  1. Define the core formula for base consumption per 100 km, factoring in the baseline tare weight of {{vehicle_class}}.
  2. Formulate the load-adjusted burn rate by calculating incremental fuel burn per ton using {{payload_capacity_tons}}.
  3. Incorporate road gradient, elevation changes, and idle segments derived from {{route_segment_data}} into the aggregate equation.
  4. Calculate the standard gross ton-kilometer metric ($GTK = \text{Payload Tons} \times \text{Distance}$) and express fuel intensity as liters per GTK.
  5. Establish the dynamic financial variance equation applying {{fuel_price_index}} to measure cost impact per trip.
  6. Determine upper and lower statistical tolerance bands relative to {{target_efficiency_threshold}}.
  7. Model outlier trigger conditions for idle-time penalties and aerodynamic drag at highway speeds.

Constraints

  • All mathematical equations MUST use standard dimensional analysis with clear metric units (L/100km, tons, km).
  • You MUST define the exact mathematical notation and variable definitions before presenting final equations.
  • Estimates MUST NOT ignore empty deadhead return trips where payload drops to zero.
  • Do not include proprietary telemetry vendor vendor-specific API syntax.

Output format

  • Section 1: Mathematical Model & Core Equations (labeled formulas for GTK, Loaded Burn, and Idling Penalty)
  • Section 2: Route Parameter Matrix (calculated baseline figures using {{route_segment_data}})
  • Section 3: Variance Thresholds and Anomaly Rules (maximum acceptable deviation from {{target_efficiency_threshold}})
  • Total length: 450-700 words.

Self-review

  • Confirm all 6 context variables are utilized directly in formulas or parameters.
  • Verify that dimensional units balance across all consumption and ton-kilometer calculations.
  • Check that upper and lower tolerance limits are explicitly formulated.
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.

research-analysis
research-reasoning-math
transport-logistics
freight
fleet-telematics
fuel-modeling