Build the application

## Build
Compare building management system operational logs against design-phase EnergyPlus simulation baselines during commercial closeout. Pinpoint subsystem energy divergence and quantify chiller plant performance gaps.

## User
Commissioning handover authority and facility engineer

## Workflow
1. Ingest 30-day post-occupancy hourly power and thermal meter readings alongside EnergyPlus epJSON baseline models.
2. Normalize measured energy consumption against actual ambient dry-bulb temperature and occupancy sensor headcounts.
3. Calculate normalized mean bias error and coefficient of variation between measured loads and design expectations.
4. Compile an engineering handover deficiency report detailing subsystems exceeding contractual energy allowances.

## Interface
A side-by-side dashboard comparing calibrated EnergyPlus baseline curves with BMS sub-meter feeds and defect tracking lists.

## Data
Construct mock epJSON building models with paired synthetic 30-day hourly CSV meters covering chillers, pumps, fans, and tenant plug loads.
Starter examples below are synthetic. They are not downloaded records.

## Source
[EnergyPlus](https://raw.githubusercontent.com/NREL/EnergyPlus/develop/README.md)
Extracts building envelope, HVAC sizing, and baseline operational consumption parameters from EnergyPlus epJSON schemas.

## Tools
dspy, pandas, fastapi.
Optimizes prompt signatures to consistently extract specific HVAC parameters and draft standardized engineering deficiency citations.
Local or hosted LLM with strong analytical reasoning over tabular engineering telemetry and schema parameters.

## Deliverables
Submit runnable source, pinned dependencies, setup commands, a working interface, example outputs, and a recorded end-to-end demo. Include tests and an action log.

## Acceptance
- Parses epJSON building models and extracts designated cooling setpoints, chilled water supply temps, and design COP.
- Computes ASHRAE Guideline 14 compliant statistical metrics (NMBE and CV-RMSE) across 720 consecutive hourly timesteps.
- Generates categorized snag tickets for any thermal sub-zone with sustained energy variance exceeding plus 15 percent.

## Starter Examples
```json
[
  {
    "input": {
      "subsystem": "Central Chiller 01",
      "measured_kwh_total": 84500,
      "baseline_kwh_total": 73200,
      "ambient_temp_avg_c": 39.5,
      "baseline_temp_avg_c": 38.8
    },
    "expected_output": {
      "variance_percent": 15.44,
      "nmbe_within_tolerance": false,
      "deficiency_flag": "excessive_lift_detected",
      "action_item": "Verify condenser water approach and refrigerant charge"
    }
  },
  {
    "input": {
      "subsystem": "Air Handling Unit 04",
      "measured_kwh_total": 12400,
      "baseline_kwh_total": 12100,
      "ambient_temp_avg_c": 39.1,
      "baseline_temp_avg_c": 38.8
    },
    "expected_output": {
      "variance_percent": 2.48,
      "nmbe_within_tolerance": true,
      "deficiency_flag": "none",
      "action_item": "Accept subsystem handover"
    }
  }
]
```

## Safety
Produces advisory closeout audit reports. Does not issue contractual defect certificates without certified commissioning agent approval.
Use mock external writes. Require human review before any real deployment.