n8n-cost-estimation

Automated Cost Estimation Pipeline

Business Case

Problem Statement

Traditional cost estimation requires:

• Manual work item lookup in price databases
• Time-consuming element classification
• Expert knowledge of pricing standards
• Repetitive data entry

Solution

Free open-source n8n pipeline that converts CAD (Revit 2015-2026) files into full cost and time estimates using AI (LLM) and vector database with 55,000+ work items.

Business Value

Traditional Role	Automated Alternative
BIM Manager manually exports data	Pipeline auto-classifies elements
Junior Estimator searches databases	Vector search finds matches in ms
Senior Estimator maps assemblies	LLM identifies quantity parameters
Foreman calculates labor hours	DDC CWICR contains documented norms
Project Manager aggregates costs	Pipeline outputs phased breakdown

Processing speed: 3-10 seconds per element group

Technical Implementation

Pipeline Architecture

┌─────────────┐    ┌─────────────┐    ┌─────────────┐
│ Revit/IFC   │───>│ CAD2DATA    │───>│ Structured  │
│ File        │    │ Converter   │    │ Excel/CSV   │
└─────────────┘    └─────────────┘    └─────────────┘
                                             │
                                             ▼
┌─────────────┐    ┌─────────────┐    ┌─────────────┐
│ Cost Report │<───│ Price Match │<───│ LLM Class.  │
│ HTML/Excel  │    │ DDC CWICR   │    │ + QTO       │
└─────────────┘    └─────────────┘    └─────────────┘

n8n Pipeline Steps

1. File Conversion Node

// Execute CAD converter
const filePath = $input.first().json.file_path;
const outputDir = filePath.replace(/\.[^.]+$/, '');

const command = `RvtExporter.exe "${filePath}" complete bbox`;

// Returns: { xlsx_path, dae_path }

2. Load Elements

// Read converted Excel into n8n
const xlsx = $node["Read Binary Files"].json;
const elements = xlsx.sheets["Elements"];

// Group by category for processing
const grouped = elements.reduce((acc, el) => {
  const cat = el.Category;
  if (!acc[cat]) acc[cat] = [];
  acc[cat].push(el);
  return acc;
}, {});

return Object.entries(grouped).map(([category, items]) => ({
  json: {category, items, count: items.length}
}));