Build
Hong Kong

I like building things
that actually work.

I'm Ellison Yeung. I make things across strategy, content, and tech. Some of them are campaigns. Some are AI tools. Some are just me seeing if I can automate something before my attention span runs out. The good news is, a surprising amount of it actually works.

See what I've been working on Say hello
Scroll
About

A bit of context.

I grew up in the UK, went to the University of Leeds, and spent a few years working across digital learning, content production, and SEO at a consumer electronics company. That's where I started getting into how automation and AI could actually make marketing work better. Not in theory, but in practice.

In 2025 I moved to Hong Kong and joined Publicis Groupe as a management trainee. It's a rotational programme, so I'm getting hands-on time across media planning, client servicing, and campaign execution. On the side, I've been building tools that help people work faster and skip the repetitive stuff.

Based in Hong Kong
Currently Publicis Groupe
Background Digital Media & Tech
Education University of Leeds
Right now

Management trainee at Publicis Groupe in Hong Kong. Rotating across departments, learning how media, creative, and strategy come together in practice. Building AI tools on the side.

Work

Things I've worked on.

2025
Side project
Competitor event tracker
n8n AI Web scraping Automation
+
Context

Tracking what competitors are doing is useful strategic intel. But doing it manually means hours of Googling and copying data into spreadsheets.

What I built

A multi-agent automation workflow using n8n, Perplexity AI, OpenAI, and web scraping. It queries competitor events, scrapes relevant pages, uses AI to parse and structure the data into clean JSON, and outputs everything to Google Sheets.

Outcome

What used to be a manual research task is now a single trigger. The workflow handles multiple brands in parallel.

2025
Side project
Meta Ad Library scraper & intelligence agent
n8n Meta API OpenAI Competitive intel
+
Context

Understanding how competitors run ads is genuinely useful for media planning. But pulling that information manually from Meta Ad Library is tedious.

What I built

An n8n workflow that connects to the Meta Ad Library API, scrapes ad creatives and targeting data, then pipes everything through OpenAI to summarize trends. Also built a chat agent layer for real-time queries.

Outcome

Tested with a major brand and pulling full demographic and creative data. Designed to extend to TikTok, Google, and LinkedIn ad libraries.

2025
Side project
LinkedIn competitor post scraper & comment intelligence
Apify n8n OpenAI LinkedIn
+
Context

Knowing what competitors post on LinkedIn, and how people respond, is useful for understanding positioning and audience sentiment.

What I built

A pipeline using Apify for LinkedIn scraping, n8n for orchestration, and OpenAI for summarization. Built a validation layer that normalizes data and falls back gracefully when parsing fails.

Outcome

A repeatable system that turns scattered LinkedIn activity into organized competitive intel.

2025
Framework
A practical blueprint for building AI agent teams
System design AI agents n8n
+
What I designed

A five-agent framework where each agent has a specific role: competitor intelligence, content repurposing, client onboarding, insight dashboards, and lead research. Designed to be built in order.

The thinking

Practical build order, realistic pricing, what to automate vs. keep human, and how the agents actually talk to each other.

2025
Client project
Competitive intelligence dashboard with AI insights
Lovable Google Sheets AI insights
+
What I built

A two-tab dashboard using Lovable, powered by Google Sheets. One tab analyzes competitor LinkedIn content; the other tracks competitor event participation. Both tabs have filters for date, competitor, content type, and full-text search.

The interesting part

Every AI insight references the specific posts or events that support it. Those references are clickable, opening a detail drawer with the full data.

2023
UG Electronics
SEO system design & digital content strategy
SEO Content strategy Video
+
What I did

Designed and implemented an SEO strategy across their website and YouTube. Keyword research, metadata optimization, content structuring, and internal linking.

Outcome

Website traffic increased around 50%, video engagement went up significantly, and the content system gave them a repeatable process.

Side projects

Things I've built.

Formless
Drop in any file and get it back restructured in whatever format you need. Built because I was tired of reformatting things.
HTML/CSS/JS Claude API
In progress
Competitive intel workflows
Structured AI research frameworks for tracking competitor campaigns, positioning shifts, and market gaps.
Prompt engineering Claude API
Live
Mind:Scape
Final year university project. An immersive XR experience that lets people revisit and reinterpret their memories. First-class result.
XR Unity University of Leeds
This portfolio
A 3D interactive portfolio built with Three.js. Because a flat page felt too boring.
Three.js CSS3D Claude
You're looking at it
Playground

Things I've built for work, things I've built for fun.

I like building interactive things — games, XR experiences, 3D scans, generative visuals. It's how I learn new tech. My university final project was an immersive XR memory experience built in Unity, and I'm always experimenting with what's possible in the browser.

Breakout
Canvas 2D
A classic reimagined. Break the bricks, clear the levels.
Score0 Lives3 Level1
Breakout
A classic, reimagined
Arrow keys or mouse to move · Space to launch
University of Leeds
Luma AI · 3D Scan
Gaussian splat capture of my university building. Orbit to explore.
University of Leeds, UK
Snake
Canvas 2D
The classic. Eat, grow, don't hit yourself.
Score0 Best0
Snake
A timeless classic
Arrow keys or WASD to move · Swipe on mobile
DOOM
js-dos · Shareware
The 1993 classic that changed everything. Shareware Episode 1 — Knee-Deep in the Dead.
💀
DOOM
Click to load
WASD / Arrows to move · Ctrl = Shoot · Space = Open · Click for fullscreen
More experiments coming soon
Thinking

How I see things.

I don't think of myself as just a "media person" or just a "creative person." I'm interested in the whole picture. How an idea starts, how it gets shaped, how it reaches people, and whether it actually lands.

What I keep coming back to is this: the best work happens when you close the gap between thinking and doing.

Making ideas useful

I'm less interested in ideas that sound good and more interested in ideas that work. Can this become a tool? A system someone actually uses?

AI as a practical tool

I use AI every day. Not because it's trendy, but because it genuinely makes my work better.

Understanding people

Good strategy starts with paying attention. What do people actually care about?

Systems over one-offs

I'd rather build something that works ten times than do the same thing manually ten times.

Scoping before building

Before I build anything, I run through: what triggers it, how does the data move, what actions need to happen, where do we need AI or APIs, and what integrations are involved.

AI in marketing Automation Competitor intelligence Social listening Content systems Prompt engineering Media + creative

Let's talk.

I'm always open to interesting conversations, whether it's about work, ideas, or something you're building.