This is a submission for the New Year, New You Portfolio Challenge Presented by Google AI
About Me
I’m Luke Ponga, a software developer and IT support specialist based in Hamilton, New Zealand.
My background in IT support and systems troubleshooting strongly influences how I approach AI. I build for real users, real constraints, and real workflows—not demos or novelty experiences.
My guiding principle for this portfolio:
AI should be pragmatic.
It should solve real problems.
It should be usable, explainable, and purposeful.
This portfolio was intentionally designed as an AI‑powered professional tool, not a static showcase. Every AI feature exists to improve communication, discovery, or career workflows in a grounded and transparent way.
Portfolio
--labels dev-tutorial=devnewyear2026
🔗 Live Deployment:
https://portfolio-luke-706599404958.us-central1.run.app/
AI at the Core (What Makes This Portfolio Different)
This portfolio treats AI as a first‑class system, not an add‑on.
Instead of embedding a generic chatbot, I used Google Genkit and Gemini models to build task‑specific AI flows that are:
- context‑aware
- grounded in real project data
- constrained to professional, explainable outputs
AI here acts as a guided assistant, not a black box.
Key AI Features
🤖 AI Project Matcher (Interactive Portfolio Guide)
This feature allows visitors to explore my work using natural‑language queries, such as:
- “Show me AI projects”
- “What experience do you have with Gemini or Genkit?”
- “Which projects are most relevant for backend roles?”
How it works:
- Implemented as a Genkit flow with structured context injection
- Uses curated project metadata rather than free‑form generation
- Responds only within known scope, reducing hallucinations
- Optimised for fast, low‑latency responses using Gemini 1.5 Flash
This turns the portfolio into an interactive knowledge interface, not just a list of cards.
🧠 Career Architect (AI‑Assisted CV & Cover Letter Generator)
The Career Architect demonstrates how AI can meaningfully support real professional workflows.
Capabilities:
- Accepts a user‑provided job description
- Generates tailored CVs and cover letters in Markdown
- Highlights relevant experience without fabricating claims
- Enforces professional tone and structure through middleware
AI stack:
- Gemini 2.0 Flash for deeper reasoning and content synthesis
- Genkit‑orchestrated prompts with explicit constraints
- Output formatting designed for immediate real‑world use
This feature reframes AI as a career support tool, not a gimmick.
How I Built It
Architecture & Performance
- Next.js 16 with server‑first rendering
- Standalone output optimised for performance and SEO
- Containerised and deployed on Google Cloud Run
- Designed for scalability without unnecessary complexity
AI Engineering
- Google Genkit for deterministic AI flow orchestration
- Clear separation between:
- data context
- prompt logic
- response formatting
- Middleware to:
- enforce professional tone
- reduce hallucinations
- maintain explainability
UX & Design
- Minimalist, Swiss‑inspired layout
- Tailwind CSS for accessibility and responsiveness
- Framer Motion for subtle, non‑distracting animations
- Motion used intentionally to support comprehension, not distract from AI output
What I’m Most Proud Of
I’m most proud that this portfolio treats AI as a tool with responsibility.
Rather than asking “What can Gemini do?”, I asked:
- Where does AI actually help users?
- Where should AI be constrained?
- How can outputs remain explainable and trustworthy?
The result is a portfolio that:
- communicates my work more effectively
- demonstrates applied AI engineering
- remains usable even without AI enabled
Attribution & Originality
This portfolio is built on established open‑source frameworks including Next.js, TypeScript, Tailwind CSS, Framer Motion, and Google Genkit, used in accordance with their respective licenses.
In line with my philosophy that AI should be pragmatic, usable, explainable, and purposeful, all AI workflows, prompt orchestration, application architecture, and interactive features—including the AI Project Matcher and Career Architect—are original implementations created specifically for this submission. This project is not a re‑packaged template or demo.
Technical Details
- Repository: https://github.com/lukeponga-dev/portfolio-luke
- Language: TypeScript
-
AI Models:
googleai/gemini-1.5-flash,googleai/gemini-2.0-flash - AI Orchestration: Google Genkit
-
Deployment: Google Cloud Run (
dev-tutorial=devnewyear2026)
Thanks to DEV and Google AI for encouraging portfolios that demonstrate responsible, real‑world AI use, not just experimentation.
Top comments (0)