You

Why build it?

I built this as a quick product probe for xFigura. (Self-initiated concept prototype. Not affiliated with or endorsed by xFigura.) It explores one idea:

turning prompts on the canvas into editable nodes, instead of leaving them as one-off text inputs.

What came out of it?

The canvas prototype

Finding the dots

Product Understanding

L1Layer
Canvas

Canvas-Based Interaction

The spatial workspace where users drop, arrange, and wire text, image, video, and 3D preview nodes.

L2Layer
Infrastructure

Infrastructure Layer

The desktop-to-cloud data pipeline managing the Rhino plugin, parameter inputs, Speckle integration, and the Revit connection.

L3Layer
Model Marketplace

Model Marketplace

The backend aggregator engine that routes and processes third-party and proprietary models, including Flux, upscalers, and the Nano Banana suite.

L4Layer
Human Connection

Human Connection Layer

The multiplayer environment hosting markup tools, team collaboration features, and text annotations for design redlines.

Early Design Development

P-01
Massing

Massing & Adjacencies

The geometry block handling spatial logic, bubble diagrams, volumetric configurations, and programmatic layouts.

P-02
Materiality

Surface & Materiality

The tactical block handling tectonic properties, surface textures, roughness, porosity, and material specifications.

P-03
Environmental

Environmental Values

The contextual data block tracking solar orientation, azimuth angles, time of day, and microclimate conditions.

P-04
Discourse

Markup & Discourse

The feedback block capturing sketch overlays, live review comments, annotations, and designer-to-principal team alignment.

Connecting the dots

Opportunities into UI

Active Focus: OP-1

Parametricizing
Text Inputs

Product
massing+canvas+infra
Workflow
material+environ

Async Context
Capture

Product
canvas+infra
Workflow
material

Parametric
Visualization

Product
canvas
Workflow
material+environ

The Core UI Elements & Interactions

The text-to-node interface relies on three core UI components that work together across the layout canvas:

Source Text Node

The entry point on the left of the canvas where you type the prompt. It tokenizes terms like /visualization, /deep, and /rotate into active pills. Clicking Parametricize kicks off the graph generation.

Decoupled Parameter Sliders

Independent control cards that spawn on the canvas with clear 20px vertical spacing. They map the parsed variables into manual controls with direct numeric readouts (20 mm, 44°, 70%, 5’).

Main Generation Hub

The central parent card positioned in the middle of the workspace. It features visual input sockets on the left edge to receive data wires from the parameter sliders, a reference image dropzone, and a Generate Visualization button at the base to render the final preview node.

The Core UI Elements & Interactions Diagram