WelcomeEntrance
RésuméNow on view · Toronto, ON
Software engineer building AI tooling and ad tech at Zynga.
I'm a software engineer on Zynga's AdTech team in Toronto. I designed and led our internal tooling for ad-serving configurations, an MCP (Model Context Protocol) server and tools that let AI assistants work with ad-serving configuration, and a project that helps our games identify high-value ads. I also worked on an AI LiveOps agent that cut a 2–3 hour workflow to about 20 minutes.
Outside work, I automate things I'd rather not do by hand. My longest-running side project started in 2023 as a Playwright script that booked my parents' tennis courts the moment booking opened; it's now a TypeScript monorepo with a web app, an API and a bot that runs every morning on a Raspberry Pi. Right now I'm building a platform for delegating software work to coding agents, where results have to be verified independently instead of taken on the agent's word.
I studied Software Engineering (Co-op) at McMaster University. Along the way I interned at Hexagon Manufacturing Intelligence, Exchange Solutions and InsideDesk, was a teaching assistant for two engineering courses, and built projects at DeltaHacks, MacHacks and MEC.
Room 1
6 posts, hung newest first. Each label gives the post, the institution, the dates and the medium, and what Lucas made there.
LC.2025.1 · Current post
Lucas Chen
LC.2023.2 · Internship
LC.2022.3 · Teaching
LC.2022.4 · Internship
LC.2021.5 · Research
LC.2021.6 · Internship
Room 2
Three works made at Zynga AdTech, shown under glass. Two of them were designed and led by Lucas; one comes with a measured result.
LC.2025.M1 · Masterwork 1 of 3
Designed and led by Lucas Chen
Curator’s note
Internal tooling that lets AI assistants work with Zynga’s ad-serving configurations: a Model Context Protocol (MCP) server and its tools. Lucas designed it and led the work.
Artist’s statement
“I designed and led internal tooling for ad-serving configurations at Zynga: a Model Context Protocol (MCP) server and tools that let AI assistants work with ad-serving configuration.”
LC.2025.M2 · Masterwork 2 of 3
Lucas Chen, contributing engineer
Curator’s note
An AI agent for LiveOps work. One workflow that used to take two to three hours now takes about twenty minutes.
Artist’s statement
“I worked on an AI LiveOps agent that cut a workflow from 2–3 hours to about 20 minutes.”
LC.2025.M3 · Masterwork 3 of 3
Designed and led by Lucas Chen
Curator’s note
A project that helps Zynga’s games identify high-value ads. Lucas designed it and led the work.
Artist’s statement
“I designed and led a project that helps games identify high-value ads.”
Room 3
Side projects, hung salon-style: each painting is the product itself, drawn as a working screen. 5 works on the walls, 5 more in the archive.
LC.2026.1 · Tooling
A harness-agnostic platform for handing software work to coding agents in Cursor, Claude Code or any other harness. The goal, from my spec: maximize architecture-approved, verified engineering output per dollar and per minute of human attention.
LC.2026.2 · Product
Books tennis and pickleball courts the moment booking opens, every morning.
LC.2024.3 · Product
Mobile meal planner: pick meals, get a grocery list, track calories and protein.
LC.2023.7 · Product
Android app that matches riders headed the same way so they can share a taxi.
LC.2022.10 · Hackathon build
A workout planner that schedules rest days, not just workouts. Built at DeltaHacks 8.
From the archive · works on paper
LC.2024.4 · Product
StudySpot, Nov 2024
Find a place to study at McMaster: search, filters, ratings, favourites and a map.
LC.2024.5 · Hackathon build
UnPassword, Nov 2024
A password manager built in one day for the MEC 2024 programming challenge.
LC.2023.6 · Experiment
API Resume, Oct 2023
My resume as a REST API: Postman-only, rate-limited, with a joke for anyone who POSTs.
LC.2022.8 · Experiment
Ride Home, Jun 2022
Mix subway sounds, chatter and lo-fi music into your own TTC ride-home ambience.
LC.2022.9 · Hackathon build
Summary.io, Jan 2022
Upload a lecture video and get an AI transcript to study from. Built at MacHacks 2.
Room 4
The study collection: the 41 materials and techniques Lucas’s works are made with, sorted into 6 drawers.
Drawer 01Languages
Drawer 02Frontend
Drawer 03Backend & data
Drawer 04AI & agents
Drawer 05Testing & automation
Drawer 06Infra & tooling
The artist’s training
B.Eng., Software Engineering (Co-op)
Room 5
Exit through the gift shop. Everything on the shelf is free: take whatever helps you get in touch with Lucas.
Thank you for visiting.
Back to the entranceRemix the exhibition: describe another portfolio
The Museum exhibit edition: the same facts as every other version, in a different shape.
| Intro | Entrance wall |
|---|---|
| Experience | Wall panels |
| Impact | Masterworks |
| Projects | Gallery wall |
| Skills | Materials & Techniques |
| Contact | Gift shop |
Paper palette · Survey type · Subtle motion
How this site works →