Crafting Conversational Experiences: A Generative UI Portfolio Built with Gemini

This is a submission for the New Year, New You Portfolio Challenge Presented by Google AI

About Me

My name is Exson Joseph. I'm a AI Engineer and Full-Stack Developer with over 2 years of experience building AI-powered products from end-to-end. I'm skilled at turning ideas into working products, from problem definition and feature design to full-stack implementation and deployment. This portfolio is a showcase of my skills and projects, presented in a unique and interactive way.

Portfolio

How I Built It

This portfolio is a full-stack application designed to be an interactive and engaging.

Tech Stack

• Frontend:

  • Framework: Next.js (with React and TypeScript)
  • Styling: Tailwind CSS
  • Animations: Framer Motion
  • UI: A custom-built chatbot interface that allows users to ask questions in natural language.

• Backend:

  • Framework: Node.js with Express
  • Database: MongoDB with Mongoose for conversation history.
  • AI: Google's Gemini 2.5 Flash model through the @google/genai SDK.

This project consists of two services a Next.js frontend and a Node.js backend both are deployed in Google Cloud Run.

What I'm Most Proud Of

I'm most proud of creating a portfolio that goes beyond a static page. The chatbot interface, powered by Google's Gemini model, allows for a truly interactive and personal experience. I'm particularly excited about the "Generative UI" concept, where the AI has direct control over the user interface, making the portfolio feel alive and intelligent. This project was a great opportunity to combine my skills in full-stack development and generative AI to build something unique and memorable.