This case study was originally published by Ergomania.
<aside>
Summary: Prefixbox is a Hungarian e-commerce scaleup. As a product and conversation designer, I helped them design an AI agent that gives more accurate product recommendations to shoppers with generative AI. The challenge was to design a product build with generative AI at a time when this technology was very new, and there weren’t many examples or design patterns we could use. Throughout the agile design process, the team has devised solutions based on field studies, competitor analysis, and market research to focus and iterate on the most essentail features in a rapidly evolving market segment.
</aside>
Client: Prefixbox
Year: 2023
Team Members: CEO, Marketing Officer, Chief Technical Officer, Technical Product Owner, 4 Developers, 2 Conversation Designers
Role: Product & Conversation Designer
Prefixbox’s product vision was to manage and enhance the shopping experience with better recommendations, lead generation, and customer support. The minimum viable AI agent solution we worked on aimed to recommend and suggest retail goods more accurately and naturally based on personal needs and preferences.
The challenge was to design the agent in an agile startup setting within a scarce competitor landscape. When we started working on this project, very few products used generative AI as their underlying technology. Building a white-label product from scratch with generative AI and finding user and business value use for it was a substantial challenge.
The challenge was to design a generative AI agent in a scarce competitor landscape.
We carried out shopping field studies to better understand retail customer journeys. We also analyzed direct and indirect competitors for potential market opportunities and best practices. We created a business model canvas and categorized features based on their impact and effort to have a clear vision for the minimum viable product. Based on these, we developed a chatbot persona and designed conversation flows and prototypes to have user feedback as soon as possible.
I worked on the initial discovery phase, took part in the business planning, and designed the conversation flows and prototypes based on the chatbot persona.