HomeFrameworksSpatial Commerce & 3D Configurator
EnterpriseFeaturedNewv1.1L5 Semantic FrameworkUpdated July 2026

Spatial Commerce & 3D Configurator

AR-ready 3D product configurators with React Three Fiber, GLTF variants, and WebXR

4.9(203 reviews)3.1K installs50 prompts6 stages3D / Web3D
GPT-4Claude

Spatial Commerce & 3D Configurator is the definitive AI prompt framework for ecommerce teams, product designers, and agencies building the future of online shopping. As 3D and AR become table stakes for premium product pages — driven by Apple Vision Pro, WebXR, and consumer expectations set by Nike, IKEA, and Porsche — this framework gives you the complete technical system to build them. From GLTF material variant switching that lets customers configure color and finish in real time, to WebXR AR mode that places the product in their room, to the Zustand state machine that tracks every configuration choice and maps it to a cart SKU, every prompt is production-ready and ecommerce-aware.

Full Access Unlocked

All 50 prompts · All 6 modules

30-day money-back guarantee
Secure checkout via Stripe
Lifetime updates (currently v1.1)
Instant delivery after purchase

"The GLTF material variant switcher prompt built our sofa configurator in 2 days instead of 3 weeks. ..."

Head of Ecommerce · Premium furniture brand, $40M revenue

Need expert implementation?

Hire an Orchestrator

Connect with a certified Prompt.Doctor Orchestrator to deploy this framework for you.

How to use this framework

No coding required. You will use ChatGPT or Claude as your AI tool. Follow these steps in order — do not skip ahead.

1

Purchase & download the framework

Click the buy button on this page. After checkout, go to the and hit Download .zip. Unzip it — you'll get a .md file (the full framework) and a .pdf (easy to read reference). Keep both open.

2

Open your project — new or existing

This dashboard is designed to integrate into any existing project or be built as a standalone app. If you already have a site in Airo (or Cursor, Bolt, etc.), open that project. If you're starting fresh, create a new project. The Orchestrator Prompt handles both cases — it scans what's already there and adds only what's missing.

3

Paste the Orchestrator Prompt into your builder's chat

Open the on this page. Copy the Orchestrator Prompt and paste it into your AI builder's chat. It will scaffold the full admin system — secure login, email marketing module, booking engine, and CMS — on top of your existing codebase. This takes 2–5 minutes.

4

Add your API keys as secrets

Critical — Novice Users

In your builder, go to Settings → Secrets and add the keys your app needs. For this framework: STRIPE_SECRET_KEY (for booking payments — get it from your Stripe dashboard), ANTHROPIC_API_KEY (for AI-assisted content — get it from console.anthropic.com), and DATABASE_URL (your MySQL connection string). No key is needed for the admin login, CMS, or email modules — those run on your existing infrastructure.

Don't have a MySQL server?

You can purchase a shared hosting plan with cPanel and MySQL at host.esgwon.dev. Once your account is set up, follow the step-by-step guide to create your database and connect it to your AI website builder.

How to set up cPanel MySQL & connect to your AI website →

Need help with Stripe?

Get your STRIPE_SECRET_KEY and STRIPE_PUBLISHABLE_KEY from your Stripe dashboard. The guide covers test keys, webhook setup, and going live.

Stripe API keys — setup & testing guide →

Need help with Anthropic?

Get your ANTHROPIC_API_KEY from console.anthropic.com. The guide covers model selection, cost management, and troubleshooting.

Anthropic API key — setup & model guide →

Prompting Airo after setup — always name the file

When asking Airo to add tables, columns, or features to the admin dashboard, always include src/server/lib/admin-db.ts in your prompt. Without it, Airo may target the wrong database. Example: "Add a bookings table in the admin database (src/server/lib/admin-db.ts) — do not touch any other database connection in this project."

See safe prompting examples →
5

Run the framework prompts inside your live app

Your app is now running in the builder's preview panel. Open the on this page, copy each prompt one at a time, and paste it into your builder's chat. Replace every [BRACKET] with your real data before sending. Work through the stages in order — each stage output feeds the next.

6

Test end-to-end, then publish or hand off to your client

Walk through the admin as a real user: log in, create a booking, send a test email campaign, update a CMS image, and run the Safe-to-Publish gate. Once everything passes, click Publish in your builder. Because this is a white-label dashboard, your client accesses it at /admin on their own domain — no Prompt.Doctor branding, no third-party login required.

Who is this for?

Ecommerce teams building 3D product pages for furniture, fashion, automotive, or consumer electronics
Shopify and headless commerce developers adding 3D configurators to product pages
Product design teams building internal 3D configuration tools
Agencies building spatial commerce experiences for luxury and premium brands

Everything you get

50 production-ready prompts across 6 spatial commerce areas
GLTF KHR_materials_variants system for real-time color and material switching
WebXR AR mode integration for mobile "place in room" product preview
Zustand configuration state machine with undo/redo and URL state encoding
Annotation hotspot system for feature callouts on 3D product models
Ecommerce cart integration: configuration-to-SKU mapping and price calculation

What's Inside

6 modules · 50 prompts · 6 workflow stages

Modules(6 total)

GLTF Model & Variants

GLTFLoader with KHR_materials_variants extension, variant switching API, Draco compression, and progressive model loading with placeholder

9 prompts

Material Configurator

Real-time MeshStandardMaterial property editing (color, roughness, metalness, normalMap), texture swap system, and environment-aware material preview

10 prompts

WebXR & AR Mode

WebXR Device API session setup, hit-test for surface detection, model placement and scaling in AR, and model-viewer web component integration as fallback

9 prompts

Configuration State

Zustand store for configuration options, undo/redo history stack, URL state encoding (base64 config in query param), and configuration persistence to localStorage

9 prompts

Annotations & Hotspots

World-space hotspot anchoring to model vertices, Drei Html overlay for callout UI, visibility culling based on camera angle, and animated pulse indicator

7 prompts

Commerce Integration

Configuration-to-SKU mapping table, dynamic price calculation, add-to-cart with configuration payload, screenshot capture, and shareable configuration URL

6 prompts
Sample Prompts(50 total)
GLTF Material Variant Switcher·GPT-4

Write a React Three Fiber component that loads a GLTF model with KHR_materials_variants and provides a UI to switch between material variants in real time. Requirements: (1) Use useGLTF from @react-three/drei to load the model. After loading, read the KHR_materials_variants extension data from gltf.parser.json.extensions?.KHR_materials_variants — extract the variants array (each has a name). (2) Implement a switchVariant(variantIndex: number) function: iterate gltf.scene.traverse, for each Mesh check mesh.userData.gltfExtensions?.KHR_materials_variants?.mappings, find the mapping where mapping.variants includes variantIndex, then call gltf.parser.assignFinalMaterial(mesh, mapping.material) to apply the variant material. (3) Store the active variant index in a Zustand store (provide the store definition). (4) Render the model with ContactShadows and Environment preset="studio". (5) Outside the Canvas, render a variant selector UI: a row of color swatch buttons (one per variant), styled with Tailwind, that call switchVariant on click. Highlight the active variant. (6) Animate the material transition: on variant switch, briefly animate mesh.material.opacity from 0 to 1 over 300ms using useFrame. Full TypeScript. Explain the KHR_materials_variants data structure in comments.

WebXR AR Placement System·Claude

Write a React Three Fiber WebXR AR mode implementation that lets users place a 3D product model on a real-world surface using hit-testing. Requirements: (1) Use R3F's XR components: <XR> wrapper, useXR() hook, and ARButton from @react-three/xr (or write a custom AR session button using navigator.xr.requestSession("immersive-ar", { requiredFeatures: ["hit-test"] })). (2) Hit-test setup: on session start, request a hit-test source against the "viewer" reference space. Each frame, get hit-test results and extract the pose matrix. (3) Placement reticle: render a flat RingGeometry at the hit-test position/orientation to show where the model will be placed. Animate it with a subtle pulse scale. (4) Placement: on screen tap (select event), place the product model at the current hit-test position. Allow repositioning by tapping again. (5) Scale control: pinch gesture (two-pointer distance delta) to scale the placed model between 0.1x and 2x. (6) Exit AR: button to end the XR session and return to the 3D preview. (7) Fallback: if WebXR is not supported, show a <model-viewer> web component with the same GLTF. Full TypeScript. Include the XR session feature detection check.

Workflow Architecture(6 stages)

system

18 prompts

Stage 1

workflow

16 prompts

Stage 2

templates

9 prompts

Stage 3

prompts

7 prompts

Stage 4

Everything included

GLTF model loading with KHR_materials_variants for color/material switching
Real-time material configurator: color, roughness, metalness, and texture swapping
WebXR AR mode: model-viewer integration and WebXR Device API for mobile AR
Zustand state management for configuration state and undo/redo history
Annotation and hotspot system for feature callouts on 3D models
Screenshot and share: html-to-image canvas capture with configuration state URL encoding
Ecommerce integration: configuration-to-cart with SKU mapping and price calculation
Full Access Unlocked

What builders say

"The GLTF material variant switcher prompt built our sofa configurator in 2 days instead of 3 weeks. The KHR_materials_variants extension explanation — how the mapping array works, how to call assignFinalMaterial — is documentation that doesn't exist anywhere else in this clarity."

Ho

Head of Ecommerce

Premium furniture brand, $40M revenue

"The WebXR AR placement system is the most complete implementation I've seen in a prompt. The hit-test reticle, pinch-to-scale, and model-viewer fallback — it covers every edge case that makes AR actually work for real users, not just demos."

CT

Creative Technologist

Luxury automotive brand

You have full access

All 50 prompts across 6 modules are unlocked for your account.

$329$469

Lifetime access