Feng Shui — Spatial AI | An App Idea LLC

From hand-drawn floor plan to furnished 3D model and AI layout guidance.

Skia drawingThree.js sceneFirebase functionsReanimated previews
10 stepsWorkflow
69 itemsCatalog
2-3 layoutsAlternatives
Timeline10-step guided workflow
TeamFounder-led spatial UX
PlatformMobile · 3D canvas
Impact69 items · AI layout options
Problem

The challenge

Most AI room tools ask for a photo and return generic advice. This product needed a workflow that let users describe a room precisely, understand why the guidance mattered, and compare alternatives before rearranging anything in the real world.

Approach

How we built it

I designed a 10-step flow from freehand drawing to simplified geometry, room naming, wall and fixture annotations, furnishing, 3D preview, AI analysis, and animated optimization. Skia handles the drawing surface, Three.js renders the space, and Gemini returns structured evaluations across bagua zones, element balance, chi flow, command position, and ranked recommendations.

Outcome

What shipped

The result is a spatial AI product with real depth: users can annotate walls and fixtures, place from a 69-item catalog, preview recommendations in motion, and choose between scored layout alternatives instead of guessing at a text-only suggestion.

Results

Outcomes

  • Built a full pipeline from freehand drawing to simplified geometry, room annotation, furnishing, and 3D preview.
  • Created a 69-item furniture catalog across 11 categories plus detailed wall, floor, and ceiling annotation systems.
  • Added AI layout optimization that presents 2-3 animated alternatives with score comparisons before the user applies changes.
Engineering

Tech stack

React NativeSkiaThree.jsexpo-glGemini 2.0 FlashFirebaseReanimatedsimplify-js
Spatial AI3DMobileDesign Systems
← All workSpatial AI