Skip to main content

Estimate Construction Costs from Revit/IFC Models with GPT-4 and Claude

Workflow preview

Workflow preview
100%
Estimate Construction Costs from Revit/IFC Models with GPT-4 and Claude preview
Open on n8n.io

Important notice

This workflow is provided as-is. Please review and test before using in production.

1. Workflow Overview

Estimate material price and total cost for grouped BIM/CAD elements using an LLM driven analysis. The workflow accepts an existing XLSX (from your model) or, if missing, can trigger a local RvtExpo...

Best for

  • AI Summarization automation workflows
  • Multimodal AI automation workflows
  • advanced n8n builders looking for reusable templates

Tools used

n8n-nodes-base.manualtrigger, n8n-nodes-base.code, n8n-nodes-base.set, @n8n/n8n-nodes-langchain.openai, n8n-nodes-base.if, n8n-nodes-base.splitinbatches, @n8n/n8n-nodes-langchain.agent, @n8n/n8n-nodes-langchain.lmchatanthropic

Source and attribution

This workflow is cataloged by N8N Workflows and links back to its original n8n.io source page by Artem Boiko.

Original n8n.io source

1.1 Workflow description

Title
Estimate Construction Costs from Revit/IFC Models with GPT-4 and Claude
Workflow name
Estimate Construction Costs from Revit/IFC Models with GPT-4 and Claude

Estimate material price and total cost for grouped BIM/CAD elements using an LLM-driven analysis. The workflow accepts an existing XLSX (from your model) or, if missing, can trigger a local RvtExporter.exe to generate one. It enriches each element group with quantities, pricing, confidence, and produces a multi-sheet Excel report plus a polished HTML executive report.

What it does

  • Reads grouped element data (from XLSX or extracted via RvtExporter.exe).
  • Builds enhanced prompts with clear rules (volumes/areas are already aggregated per group).
  • Calls your selected LLM (OpenAI/Anthropic/etc.) to identify materials, pick the pricing unit, and estimate price per unit and total cost.
  • Parses AI output, adds per-group KPIs (cost %, rank), and aggregates project totals (by material, by category).
  • Exports a multi-sheet XLSX and an HTML executive report (charts, KPIs, top groups).

Prerequisites

  • LLM credentials for your chosen provider (e.g., OpenAI, Anthropic). Enable exactly one chat node and connect credentials.
  • Windows host only if you want to auto-extract from .rvt/.ifc via RvtExporter.exe. If you already have an XLSX, Windows is not required.
  • Optional: Internet access on the LLM side for price lookups (model/tooling dependent).

How to use

  1. Import this JSON into n8n.
  2. Open the Setup node(s) and set:
    • project_file — path to your .rvt/.ifc or to an existing grouped *_rvt.xlsx
    • path_to_converterC:\\DDC_Converter_Revit\\datadrivenlibs\\RvtExporter.exe (optional)
    • country — used to guide price sources/standards (e.g., Germany)
  3. In the canvas, enable one LLM node (e.g., OpenAI or Anthropic) and connect credentials; keep others disabled.
  4. Execute workflow (Manual Trigger). It will detect/build the XLSX, run analysis, then write the Excel and open the HTML report.

Outputs

  • Excel: Price_Estimation_Report_YYYY-MM-DD.xlsx with sheets:
    • Summary, Detailed Elements, Material Summary, Top 10 Groups
  • HTML: executive report with charts (project totals, top materials, top groups).
  • Per-group fields include: Material (EU/DE/US), Quantity & Unit, Price per Unit (EUR), Total Cost (EUR), Assumptions, Confidence.

Notes & tips

  • Quantities in the input are already aggregated per group — do not multiply by element count.
  • If you prefer XLSX-only extraction, run your converter with a -no-collada flag upstream.
  • Keep ASCII-safe paths and ensure write permissions to the output folder.

Categories

Data Extraction · Files & Storage · ETL · CAD/BIM · Cost Estimation

Tags

cad-bim, price-estimation, cost, revit, ifc, xlsx, html-report, llm, materials, qto

Author

DataDrivenConstruction.io [email protected]

Consulting and Training

We work with leading construction, engineering, consulting agencies and technology firms around the world to help them implement open data principles, automate CAD/BIM processing and build robust ETL pipelines.

If you would like to test this solution with your own data, or are interested in adapting the workflow to real project tasks, feel free to contact us.

Docs & Issues:
Full Readme on GitHub

1.2 Logical Blocks

This catalog entry is organized from the workflow JSON. The node-level section below shows the executable blocks available for review before importing the template.

2. Block-by-Block Analysis

Block 1 - When clicking ‘Execute workflow’

Type / Role
n8n-nodes-base.manualTrigger - manualTrigger
Config choices
Version 1

Block 2 - Find Category Fields1

Type / Role
n8n-nodes-base.code - code
Config choices
Version 2

Block 3 - Apply Classification to Groups1

Type / Role
n8n-nodes-base.code - code
Config choices
Version 2

Block 4 - Non-Building Elements Output1

Type / Role
n8n-nodes-base.set - set
Config choices
Version 3.4

Block 5 - AI Classify Categories1

Type / Role
@n8n/n8n-nodes-langchain.openAi - openAi
Config choices
Version 1.3

Block 6 - Is Building Element1

Type / Role
n8n-nodes-base.if - if
Config choices
Version 1

Block 7 - Check If All Batches Done

Type / Role
n8n-nodes-base.if - if
Config choices
Version 2

Block 8 - Collect All Results

Type / Role
n8n-nodes-base.code - code
Config choices
Version 2

Block 9 - Process in Batches1

Type / Role
n8n-nodes-base.splitInBatches - splitInBatches
Config choices
Version 1

Block 10 - Clean Empty Values1

Type / Role
n8n-nodes-base.code - code
Config choices
Version 2

Block 11 - AI Agent Enhanced

Type / Role
@n8n/n8n-nodes-langchain.agent - agent
Config choices
Version 1.7

Block 12 - Accumulate Results

Type / Role
n8n-nodes-base.code - code
Config choices
Version 2

Block 13 - Anthropic Chat Model1

Type / Role
@n8n/n8n-nodes-langchain.lmChatAnthropic - lmChatAnthropic
Config choices
Version 1.3

Block 14 - Calculate Project Totals1

Type / Role
n8n-nodes-base.code - code
Config choices
Version 2

Block 15 - Enhance Excel Output

Type / Role
n8n-nodes-base.code - code
Config choices
Version 2

Block 16 - Prepare Excel Data

Type / Role
n8n-nodes-base.code - code
Config choices
Version 2

Block 17 - Create Excel File

Type / Role
n8n-nodes-base.spreadsheetFile - spreadsheetFile
Config choices
Version 2

Block 18 - Prepare Enhanced Prompts

Type / Role
n8n-nodes-base.code - code
Config choices
Version 2

Block 19 - Parse Enhanced Response

Type / Role
n8n-nodes-base.code - code
Config choices
Version 2

Block 20 - Generate HTML Report

Type / Role
n8n-nodes-base.code - code
Config choices
Version 2

Block 21 - Convert to Binary

Type / Role
n8n-nodes-base.code - code
Config choices
Version 2

Block 22 - Sticky Note

Type / Role
n8n-nodes-base.stickyNote - stickyNote
Config choices
Version 1

Block 23 - Group Data with AI Rules1

Type / Role
n8n-nodes-base.code - code
Config choices
Version 2

Block 24 - Extract Headers and Data

Type / Role
n8n-nodes-base.code - code
Config choices
Version 2

Showing the first 24 of 57 workflow blocks. Download the JSON for the full node graph.

3. Summary Table

Workflow Estimate Construction Costs from Revit/IFC Models with GPT-4 and Claude
Complexity advanced
Nodes 57
Categories AI Summarization, Multimodal AI
Author Artem Boiko
Published 20 Aug 2025

4. Reproducing the Workflow from Scratch

  1. 1. Download the workflow JSON

    Use the JSON export at /data/workflows/7652/7652.json as the source template for this automation.

  2. 2. Import the template into n8n

    Open n8n, import the downloaded JSON, and review each node before activating the workflow.

  3. 3. Configure credentials and variables

    Replace placeholder credentials, API keys, webhook URLs, account IDs, and environment-specific values with your own settings.

  4. 4. Test with sample data

    Run the workflow manually or in a staging workspace, inspect node output, and confirm downstream systems receive the expected data.

  5. 5. Activate and monitor

    Enable the workflow only after testing, then monitor executions, errors, and rate limits during the first production runs.

5. General Notes & Resources

Review imported nodes carefully before activation. This catalog entry is intended to help you inspect the workflow structure, understand required services, and find related templates faster.

Node names, credentials, schedules, webhook paths, and external service limits may need adjustment for your workspace.

Frequently asked questions

What does Estimate Construction Costs from Revit/IFC Models with GPT-4 and Claude do?

Estimate material price and total cost for grouped BIM/CAD elements using an LLM driven analysis. The workflow accepts an existing XLSX (from your model) or, if missing, can trigger a local RvtExpo...

What do I need before importing this workflow?

Review the workflow JSON, configure any required credentials in n8n, and test the automation in a safe workspace before using it in production.

Can I customize this workflow?

Yes. Use the block-by-block analysis and the downloadable JSON to inspect each node, then adjust credentials, prompts, schedules, filters, or destinations for your AI Summarization, Multimodal AI use case.