Using design and artificial intelligence tools to build a product aimed at replacing an uninnovated space
The process of designing and developing a web app using artificial intelligence
A web app platform bringing together UIUX, user testing, and artificial intelligence

Challenge
Speech therapists spend significant time searching for visuals, formatting worksheets, and manually matching images to therapy activities. Existing workflows are repetitive, fragmented, and slow – making resource creation a major bottleneck in session preparation.

Solution
An intuitive, easy-to-use app that allows speech therapists to generate visual resources tailored to the unique teaching materials and client needs.

What I delivered
  • Initial research with an industry end-users to understand the problem and validate the gap in market 
  • Designed screens and prototypes in Figma, including UX flows such as end-to-end worksheet creation experience and interaction flows for AI image generation
  • Developed and built features using Claude to accelerate creation of UI layouts and components
  • Prototyping, testing and iterating on features to aim for seamless user experiences
  • UX-first thinking through streamling complex user flows and needs into intuitive ‘field ready’ digital interfaces 
  • Deployed the prototype for beta testing with users for UI/UX testing, analysis and feedback for iteration
  • Created a component library to scale UI primitives simplifying flows and mitigating AI scope creep to scale and build sustainably
  • Integrated the AI build with Supabase, Google Gemini, and Vercel for deployment
  • Collaborated with engineering by working with a junior software developer during development. Tasks included hand offs of annotated flows and Figma screens, collaborative discussion on feasibility of features/timeframces, translating designed components into coded realities, communicating business vs. build decision-making, translating ideas into technical briefs

Timeline
Roughly 4 months so far.


Tools
Figma
GitHub
Claude
Initial prototype of swim lanes charting actions on canvases further detailing owner, frontstage, backstage, tools and support required. These user inputs became the basis for the next prototype.

Validating the tools to solve the limited ways to customise visual resources

Speech therapists  spend hours gathering visual resources on apps not built for their use. Further, most existing visual resources are not modern or engaging.

The result? Hours spent gathering mediocre-at-best visual resources that hardly engage their learners.

Using Google’s artificial intelligence models, I was able to prototype quickly to prove that AI had the capability to produce personalised visual resources based on specific words a speech therapist would want to teach to their clients.

Example Figma screens to quickly visualise and see key user flows for iteration and testing purposes.
Figma component library of UI primitives as a reference point for both the software dev and artificial intelligence agents – which are, in my experience, terrible at creating consistent on-brand UI elements unless specifically instructed to.