Designing the system behind the experience.
Product Designer | UI/UX | Design Systems | AI Product Architecture.
Human–AI Interaction | Information Architecture | Figma Systems | Scientific UX
STATUS | Under development
I work across product design, UI/UX, information architecture, design-system architecture, system logic, Figma component architecture, agent-readable specifications, API integration, and controlled AI execution, translating human design intent into structured, machine readable standards for emerging AI-driven systems.
Create a scalable, AI-centered design system that connects regional workflows through shared standards, APIs, structured component logic, and machine-readable rules—without sacrificing local flexibility, accessibility, or scientific integrity.
SERVIR serves a highly diverse global network whose languages, cultures, geographies, technical needs, and goals vary by region. Research revealed the need for a system that can maintain shared standards while adapting its content, interface, and workflows to local context.
AI creates the opportunity to make that adaptability dynamic prioritizing relevant information and configuring the experience around regional conditions and objectives, with the ultimate goal of supporting faster, better-informed decisions for people and ecosystems.
Every component must communicate with both a human and a machine.
Designers need visual guidance, recognizable patterns, and understandable rules. AI systems need structured naming, metadata, properties, constraints, and predictable relationships. I designed both layers together so they remain manifestations of the same source of truth.
Balanced regional monitoring
A light interface exploring a clear, accessible workspace for broad regional analysis. The AI recommendation emphasizes map visibility, decision clarity, and multi-layer monitoring.
High-contrast regional monitoring
A dark interface designed for sustained analysis across a large geographic area. The layout keeps the map dominant while giving analysts quick access to forecast focus, active modules, and priority layers.
Hazard & exposure analysis
A region-specific workspace focused on ecological risk and decision support. The AI recommendation prioritizes hazards, contextual layers, exposure analysis, and regional monitoring needs.
The goal is not simply to produce interfaces faster. It is to create a system that can scale knowledge, design quality, and regional decision support at the same time.
The system is designed to reduce the time between a regional question and a usable decision-support interface. By combining reusable components, AI-assisted recommendations, shared standards, and structured system logic, SERVIR could accelerate data selection, dashboard and report creation, and production across regional hubs while reducing duplicated work and implementation cost.
Faster production is only valuable if quality is preserved. The architecture also embeds rules for accessibility, evidence, citations, uncertainty, component behavior, and validation so that increased speed can be paired with stronger consistency and scientific integrity rather than simply generating more output.
Alongside the visual and interaction system, I am developing the AI/API Design-System Specification with an AI design collaborator. The specification translates the human-facing design system into machine-readable rules for components, metadata, variables, states, accessibility, evidence requirements, API behavior, controlled execution, and validation.
Its purpose is to create the technical bridge between design intent, AI reasoning, APIs, and Figma execution—so the system can scale without losing governance or human oversight.
Designing the system behind the experience.
Product Designer | UI/UX | Design Systems | AI Product Architecture.
Human–AI Interaction | Information Architecture | Figma Systems | Scientific UX
STATUS | Under development
I work across product design, UI/UX, information architecture, design-system architecture, system logic, Figma component architecture, agent-readable specifications, API integration, and controlled AI execution, translating human design intent into structured, machine readable standards for emerging AI-driven systems.
Government agencies, regional organizations, NGOs, Indigenous peoples, communities, decision-makers, private-sector partners, and households relying on trusted, locally relevant information.
SERVIR serves a highly diverse global network whose languages, cultures, geographies, technical needs, and goals vary by region. Research revealed the need for a system that can maintain shared standards while adapting its content, interface, and workflows to local context.
AI creates the opportunity to make that adaptability dynamic prioritizing relevant information and configuring the experience around regional conditions and objectives, with the ultimate goal of supporting faster, better-informed decisions for people and ecosystems.
I analyzed users, workflows, design-system architecture, scientific communication requirements, accessibility standards, Figma structure, and API constraints to define how the system must work for both humans and AI.
AI cannot reliably interpret visual design alone. Design intent must become explicit, structured, and machine-readable through rules, metadata, states, constraints, and governance.
Every component must communicate with both a human and a machine.
Designers need visual guidance, recognizable patterns, and understandable rules. AI systems need structured naming, metadata, properties, constraints, and predictable relationships. I designed both layers together so they remain manifestations of the same source of truth.
Component intelligence is embedded directly into the design system through structured IDs, purpose, defaults, variants, constraints, geometry, and usage rules, giving AI structured information beyond the visual object itself.
Balanced regional monitoring
A light interface exploring a clear, accessible workspace for broad regional analysis. The AI recommendation emphasizes map visibility, decision clarity, and multi-layer monitoring.
High-contrast regional monitoring
A dark interface designed for sustained analysis across a large geographic area. The layout keeps the map dominant while giving analysts quick access to forecast focus, active modules, and priority layers.
Hazard & exposure analysis
A region-specific workspace focused on ecological risk and decision support. The AI recommendation prioritizes hazards, contextual layers, exposure analysis, and regional monitoring needs.
The goal is not simply to produce interfaces faster. It is to create a system that can scale knowledge, design quality, and regional decision support at the same time.
The system is designed to reduce the time between a regional question and a usable decision-support interface. By combining reusable components, AI-assisted recommendations, shared standards, and structured system logic, SERVIR could accelerate data selection, dashboard and report creation, and production across regional hubs while reducing duplicated work and implementation cost.
Faster production is only valuable if quality is preserved. The architecture also embeds rules for accessibility, evidence, citations, uncertainty, component behavior, and validation so that increased speed can be paired with stronger consistency and scientific integrity rather than simply generating more output.
Alongside the visual and interaction system, I am developing the AI/API Design-System Specification with an AI design collaborator. The specification translates the human-facing design system into machine-readable rules for components, metadata, variables, states, accessibility, evidence requirements, API behavior, controlled execution, and validation.
Its purpose is to create the technical bridge between design intent, AI reasoning, APIs, and Figma execution—so the system can scale without losing governance or human oversight.