CASE STUDY
Insurance AI Specification-to-Prototype Platform
An AI-Prototyping workflow that turns written requirements into interactive, review-ready design prototypes.
Problem Solved
The existing design process was Figma-first, requiring designers to manually translate written specifications and domain data into screens, apply established design patterns, and connect interactions before a prototype was ready for stakeholder review. Even with a mature design system in place, each new prototype required dedicated setup and design time before stakeholders could interact with the proposed solution.
The objective was to reduce this repetitive overhead by enabling AI to work with existing product data, design rules, and components, shortening the path from written specification to a stakeholder-reviewable prototype while maintaining UI/UX designer oversight.
Problem Solving Approach
The solution connects AI to four separate context sources: live Figma design files, the component library, the product codebase, and the project management tool. Each connection accesses the relevant system of record directly, eliminating manual copying and summarisation. As a result, domain object’s data was extracted directly from source code, removing the manual copy-from-documentation step that design-development handoffs typically require.
At the same time, design decisions, layout patterns, and component rules were encoded into a reusable knowledge base, so AI output reflected accumulated team expertise and remained consistent across tasks. Components were drawn directly from the established project design system, so generated output required no corrections before stakeholder review.
A pre-configured project environment removed manual setup between a written specification and a working prototype, compressing the time from requirement to reviewable output. UI/UX designer oversight was maintained throughout.
Outcome
As a result, a fully interactive prototype was built on real product data and correct design system components, without running a dedicated design sprint. A stakeholder estimated that the approach enabled the desired prototype to be reached 24x faster than the standard process.
24x estimated speed-up to a reviewable prototype, vs. the standard process
0 corrections needed to generate design system components before stakeholder review
Key Features Implemented
AI-assisted design and wireframe generation
AI agents work alongside the design team in Figma, using the codebase as the source of truth for the product’s domain model and generating interactive wireframes directly from written specifications.
Machine-readable design rules and governance
Skill files encode component rules, layout patterns, interaction standards, and UX writing guidelines, applying established patterns consistently across user-facing product surfaces.
Code-based component library and wireframe scaffold
Storybook provides a single coded reference for designers, engineers, and agents, while a pre-configured Angular application enables agents to produce browser-based, clickable prototypes using the same components as the real product.
Automated design compliance and documentation
Continuous design compliance review is integrated into the delivery pipeline, replacing manual environment checks, while user documentation and in-app assistance are generated from the codebase and embedded in the product.
Code-first feature delivery and migration readiness
Designers build directly in Angular on a design layer built to survive migration.
Technologies
Development
Design
Project Timeline and Team Structure
The ongoing collaboration is led by an Atlantbh Lead UX/UI Designer, who owns the design stream and design governance within the AI-driven SDLC framework. The team also includes UX/UI Designers supporting product design and day-to-day delivery across active services.
UX/UI Designers
Methodology
The project follows an Agile Scrum methodology, enabling iterative design and development, continuous feedback, and close collaboration across teams.
With decades of experience driving success for industry leaders, we’re ready to help you turn challenges into opportunities.
Related case studies
Gain hands-on insights from our team's expertise.
Advanced Geospatial Insights with Applied AI/ML
PoC designed to improve GIS data analysis, automate report summarization, and accelerate data quality operations.
GIS
NDA
AI/ML
Data Science & Analytics
Transforming Customer Service Using AI
Automated support ticket classification using ML, increasing accuracy to 98% and reducing time spent reclassifying by 70%.
NDA
AI/ML
Data Science & Analytics
DevOps
Software Development
Ready to Achieve More?
We’ll help you reach your goals quickly with an easy and straightforward process to kick off our collaboration. Here’s what happens next.
STEP 1
Discovery Call
Let’s chat to understand your company, project needs, and answer any questions along the way.
STEP 2
Free Consultation
Work closely with our experts to explore the right solutions for your business.
STEP 3
Collaboration Proposal
We'll recommend the best strategy for your goals, ensuring you get the most from our expertise.
STEP 4
30-Day Cancellation
Policy Contract
Spoiler: It’s Never Been Used
Enjoy peace of mind while we deliver excellence from day one—our track record speaks for itself.
