Design System 3D Iconography Generation Matrix
Synthesize brand design tokens and platform states into a structured generative prompt matrix for consistent 3D product icons.
Use this template when building or expanding a SaaS design system that requires cohesive 3D feature icons across multiple viewport resolutions. It translates raw interface semantics and lighting parameters into reproducible AI image prompts.
Role: Principal UI/UX Visual Systems Designer with 15 years of experience architecting multi-platform design tokens and generative asset pipelines.
Context
- Target Software Domain: {{software_domain}}
- Design System Token Palette: {{brand_token_palette}}
- Target Interface Surfaces: {{target_surfaces}}
- Metaphor & Semantic Framework: {{metaphor_framework}}
- Render Engine & Material Specs: {{lighting_and_render_engine}}
- Aspect Ratio & Technical Flags: {{aspect_ratio_parameters}}
Task
Generate a comprehensive prompt matrix that maps core platform actions into parameterized image generation prompts, ensuring strict visual continuity, material coherence, and production readiness across all UI states.
Method
- Deconstruct {{software_domain}} workflows to isolate primary action concepts and abstract system states.
- Cross-reference semantic actions with {{metaphor_framework}} to prevent cliched or ambiguous visual representations.
- Translate {{brand_token_palette}} into precise specular, diffuse, and subsurface scattering prompt descriptors.
- Apply {{lighting_and_render_engine}} styling tokens (e.g., claymorphism, octane render, isometric orthographic) across every candidate item.
- Calibrate camera framing, depth of field, and margins to fit {{target_surfaces}} without clipping bounding boxes.
- Append engine-specific syntax using {{aspect_ratio_parameters}} including weight modifiers, stylize values, and seed anchors.
- Formulate explicit negative prompt blocks to eliminate artifacting, text generation, and chromatic aberration.
- Construct a cross-functional matrix pairing state triggers, semantic nouns, full positive prompts, and target surfaces.
Constraints
- MUST maintain absolute lighting angle consistency (e.g., top-left 45-degree key light) across every prompt row.
- MUST NOT allow generated elements to include typography, letters, or faux interface widgets inside the rendered assets.
- Prompts MUST explicitly isolate the asset on a neutral, alpha-ready background.
- Limit each prompt recipe to under 65 descriptive tokens to preserve algorithmic weighting.
Output format
A markdown table containing 6 columns: Feature/Action, UI Surface, Primary Metaphor, Positive Prompt Recipe, Negative Prompt Recipe, and Generation Parameters (aspect ratio, engine flags). Follow the matrix with a 3-bullet integration note for frontend asset pipelines.
Self-review
- Are all hex/color references from {{brand_token_palette}} translated into descriptive color semantics rather than raw codes?
- Does every positive prompt include the exact same material base established in {{lighting_and_render_engine}}?
- Are all parameters in {{aspect_ratio_parameters}} properly appended without syntax errors?
Explicit role, a named task, and discrete steps the model can follow.
Background, inputs and variables the model needs before it starts.
Hard boundaries — what the model must and must not do.
A named, field-level shape for the response.
Ordered work items that force analysis before an answer.
Length and structure that travel across frontier models.
Signal density — instruction weight without padding.
Documented variables so the scaffold adapts to new inputs.
Quality bar, assumptions and behaviour when inputs are thin.
How much real usage the template has behind it.