The first Goal-Native Anticipatory AI platform

How I redesigned interaction paradigms to turn multi-agent AI creation from a months-long struggle into a five-minute task.

Creatink is a bold, modern agency site built on Framer CMS, designed to showcase strong visuals and smooth UX.

How I redesigned interaction paradigms to turn multi-agent AI creation from a months-long struggle into a five-minute task.

Overview

As AI adoption accelerates, integrating AI has become a major competitive advantage businesses. Our initial research revealed that in practice, companies struggle to integrate AI because:

  • There’s a severe talent and skills gap

  • AI integration is complex

  • One AI model rarely meets all needs

  • AI space evolves extremely fast

  • People who actually need AI are often non-technical

Dragonscale's mission was to make multi-agent AI widely accessible to SMEs by providing a full-stack framework for quick and easy multi-agent AI adoption. 

Role:

UX/UI Designer ->
Sole lead UX/UI designer

Team:

Date:

2023 - 2025

Status:

Shipped V3 MVP (as of Jan 2026)

Role:

UX/UI Designer ->
Sole lead UX/UI designer

Team:

Date:

2023 - 2025

Status:

Shipped V3 MVP (as of Jan 2026)

Overview

As AI adoption accelerates, integrating AI has become a major competitive advantage businesses. Our initial research revealed that in practice, companies struggle to integrate AI because:

  • There’s a severe talent and skills gap

  • AI integration is complex

  • One AI model rarely meets all needs

  • AI space evolves extremely fast

  • People who actually need AI are often non-technical

Dragonscale's mission was to make multi-agent AI widely accessible to SMEs by providing a full-stack framework for quick and easy multi-agent AI adoption. 

Phase I: Building the MVP

UX problem

How do we design a platform UX for SMEs that empowers even non-technical users to assemble multi-agent AI applications that automate critical workflows, without writing any code?

UX problem

How do we design a platform UX for SMEs that empowers even non-technical users to assemble multi-agent AI applications that automate critical workflows, without writing any code?

  1. Defining the design language

Discovery

What approach could make the experience so intuitive that even a business professional with minimal technical expertise can design and deploy a multi-agent AI solution?

Research goal

Determine the most intuitive and scalable interaction model for non-technical users to configure AI systems.

Methodology

  • Comparative analysis of existing B2B and B2C AI interfaces

  • Competitive landscape review

  • Internal stakeholder interviews

Key insight

Multi‑agent orchestration is a systems‑level, intent‑driven, multidimensional problem. Traditional point-and-click interfaces are step‑driven, parameter‑centric, and fragmented. They force people to think in UI terms instead of intent and outcomes. For nontechnical users, the constant mental translation between those worlds is the bottleneck.

Ideation

Creation of Rustic UI

Based on the research and market analysis findings, I co‑developed Rustic UI — a UX framework with a design system and an open‑source component library that enables rich multimodal conversational experiences for multi‑agent AI.

This “multi-modal” feature means this framework designed to handle flexible input (text, voice, gesture, data uploads) and rich, non-text output (interactive charts, media, live components).

Read the Rustic UI case study to learn in more detail on how it reduced cognitive load, cut developer handoff time by ~40%, and ensured pixel‑perfect visual consistency across all surfaces.

Creation of Rustic UI

Based on the research and market analysis findings, I co‑developed Rustic UI — a UX framework with a design system and an open‑source component library that enables rich multimodal conversational experiences for multi‑agent AI.

This “multi-modal” feature means this framework designed to handle flexible input (text, voice, gesture, data uploads) and rich, non-text output (interactive charts, media, live components).

Read the Rustic UI case study to learn in more detail on how it reduced cognitive load, cut developer handoff time by ~40%, and ensured pixel‑perfect visual consistency across all surfaces.

Creation of Rustic UI

Based on the research and market analysis findings, I co‑developed Rustic UI — a UX framework with a design system and an open‑source component library that enables rich multimodal conversational experiences for multi‑agent AI.

This “multi-modal” feature means this framework designed to handle flexible input (text, voice, gesture, data uploads) and rich, non-text output (interactive charts, media, live components).

Read the Rustic UI case study to learn in more detail on how it reduced cognitive load, cut developer handoff time by ~40%, and ensured pixel‑perfect visual consistency across all surfaces.

  1. Defining the scalable B2B architecture

Discovery

How do we create a single UX framework that is: 

  • scalable, 

  • adaptable to every business’s unique AI solution,

  • and capable of serving the diverse needs of multiple organizational layers?

Research goal

Map the typical multi-level organizational structure in target SMEs and identify persona-driven feature needs across layers.

Methodology

  • User research (quantitative survey + 8 qualitative interviews with IT/ops managers and CFOs)

  • Information hierarchy mapping

Key insight

A single, undifferentiated interface will confuse and overwhelm users from different organizational levels - features critical to one persona are a noise for another.

Design decision

Establish clear personas groups, user journeys to major interactions and challenges, and a robust information architecture (IA).

Ideation

Creation of Rustic UI

Based on the research and market analysis findings, I co‑developed Rustic UI — a UX framework with a design system and an open‑source component library that enables rich multimodal conversational experiences for multi‑agent AI.

This “multi-modal” feature means this framework designed to handle flexible input (text, voice, gesture, data uploads) and rich, non-text output (interactive charts, media, live components).

Read the Rustic UI case study to learn in more detail on how it reduced cognitive load, cut developer handoff time by ~40%, and ensured pixel‑perfect visual consistency across all surfaces.

Creation of Rustic UI

Based on the research and market analysis findings, I co‑developed Rustic UI — a UX framework with a design system and an open‑source component library that enables rich multimodal conversational experiences for multi‑agent AI.

This “multi-modal” feature means this framework designed to handle flexible input (text, voice, gesture, data uploads) and rich, non-text output (interactive charts, media, live components).

Read the Rustic UI case study to learn in more detail on how it reduced cognitive load, cut developer handoff time by ~40%, and ensured pixel‑perfect visual consistency across all surfaces.

Things I Did

I designed and implemented the website structure and layout using Framer’s visual canvas and CMS features. I customized components for blog entries and testimonial displays and built responsive sections tailored for performance across devices. I was also responsible for integrating animations that improved user engagement without compromising performance. The final product was delivered on time with a lightweight, future-ready architecture — ready to scale as the brand evolves.