SBD+
AdminHelp
Dashboard1
Clipboard0
Drag and drop any screenshot, image, or exported file here to save it to your personal clipboard.

About

How the Pipeline Works

Smart Building Design+ is a six-agent AI pipeline that turns a map coordinate into a complete Revit BIM model. Each agent owns one transformation step and communicates via a central orchestrator.

1

Map → Image

Google Maps APIEasy

The Google Street View Static API captures 3–4 frames of the building at optimal headings, plus a satellite overhead image for footprint reference.

2

Image → 3D Model

Meshy AIEasy–Medium

Meshy's multi-view Image-to-3D API accepts up to four angles and produces a GLB mesh with PBR materials. Quality varies with occlusion and foliage.

3

3D Model → Semantic

Claude VisionEasy–Medium

Claude analyses the Street View frames and extracts structured JSON: storey count, floor heights, window positions, facade material, and roof type.

4

3D Model → 2D CAD

trimesh + SVGHard

The mesh is sliced at inferred floor heights to produce orthographic plan and elevation SVGs plus a DXF for Revit import. Falls back to schematic if mesh slicing fails.

5

CAD → Revit

Claude + Revit MCPHard

A Claude agent drives a C# MCP server inside Revit. It creates levels, floor plates, walls, and openings from the geometry. A self-correction loop handles Revit API errors.

Try the Pipeline