CASE STUDY • AI-ASSISTED DEVELOPMENT

Cosmic Quarry: a Microsoft Store game built with an AI coding agent.

Cosmic Quarry is a fast, arcade space-mining game — drill asteroids, dodge alien raiders, and dive deeper for richer ore. What makes it unusual isn’t just the gameplay: nearly every design decision and line of code was shaped in partnership with an LLM-powered coding agent.

Cosmic Quarry title screen

About the game

A pick-up-and-play arcade loop with just enough depth to keep you diving.

Cosmic Quarry combo multiplier and ore rush

Mine, survive, go deeper

Pilot a mining ship through an asteroid belt, break rocks for ore, and manage your hull against alien attackers. Fill your cargo and choose: cash in safely, or dive to the next depth for richer ore and tougher foes — with your health carrying over. Four distinct alien types, power-ups, a combo multiplier, upgrades, daily challenges and leaderboards round out the loop.

The tech stack

A lean, native Windows stack chosen for performance, Store packaging, and low overhead.

MonoGame 3.8 (WindowsDX) .NET 9 • C# GDK • MSIXVC packaging Azure Application Insights Vungle rewarded ads Microsoft Store • Partner Center Azure DevOps CI/CD GitHub Copilot CLI

The game itself is a single MonoGame project targeting .NET 9 on Windows, packaged as an MSIXVC with the Microsoft GDK for Store distribution. Telemetry flows to Application Insights, rewarded ads are served through the Vungle SDK (hosted in a WebView2 surface), and everything builds and ships through Azure DevOps pipelines. Store listing and add-on management are automated with Playwright scripts against Partner Center.

The role of the LLM

Not autocomplete — a genuine pair-programmer for decisions and implementation.

Cosmic Quarry was developed hand-in-hand with GitHub Copilot CLI, an agentic terminal assistant driving frontier models — primarily Anthropic’s Claude (Opus and Sonnet) and OpenAI’s GPT models. Rather than generating isolated snippets, the agent read the whole codebase, proposed approaches, wrote the changes, built and validated them, and opened pull requests — iterating on real feedback from playtests.

“The steering feels too sharp” became a tuning conversation. “The aliens fly onto my ship and shoot point-blank” became an orbiting-AI redesign. Plain-language intent went in; shipped, tested features came out.

— How most features in Cosmic Quarry were specified

Key decisions the LLM helped make

Design trade-offs, in plain English

Should low-health recovery cost ore or a rewarded ad? Should the tutorial be a passive slideshow or interactive? The agent laid out options with pros and cons, recommended one, and asked clarifying questions before writing a line of code.

Diagnosing the root cause, not the symptom

When asteroids “appeared out of thin air,” the agent traced it to a spawn radius smaller than the screen’s half-diagonal and fixed the math — rather than papering over it. A tutorial crash was tracked to a font that lacked em-dash glyphs.

Remembering how this project works

The agent retained project conventions — branch naming, the Azure DevOps PR flow, UI font rules, telemetry patterns — and applied them consistently across sessions.

Features shipped with AI pair-programming

Real gameplay and platform work, specified in conversation and implemented by the agent.

Cosmic Quarry flight and combat
Game feel

Progressive steering & orbiting enemy AI

A tap of the arrow keys keeps a tight turn radius; holding past half a second ramps the turn rate for quick reversals. Red “Marauder” aliens were rebuilt to circle the player at a preferred range instead of colliding and firing point-blank — giving players room to dodge and counter-attack.

Pause menu: watch an ad to restore full health
Systems & monetization

Watch-an-ad-to-heal & off-screen spawning

Running low on hull? The pause menu offers a rewarded ad (or an ore trade) to restore health — with the game correctly frozen while the ad plays. Asteroids now spawn beyond the visible viewport and drift into view, so the belt always feels continuous as you descend.

Interactive Player Guide: alien ship roster
Onboarding & data

Interactive Player Guide & telemetry

First-time players fly an interactive tutorial — a short course with turns and obstacles — then meet the asteroid belt and alien roster before the game begins. It’s skippable, replayable from the menu, and fully instrumented with Application Insights events so drop-off and completion can be measured.

The build-and-ship loop

How a plain-language request became a shipped, Store-ready update.

Describe the intent

A one-line request in the terminal — “make the aliens circle the ship” — plus any clarifying answers.

Explore & plan

The agent reads the relevant code, identifies the root cause or best insertion point, and proposes an approach.

Implement on a branch

Changes land on a dedicated feature branch, following the project’s naming and code conventions.

Build & validate

A clean dotnet build confirms zero new errors before anything is committed.

Open a pull request

The change is pushed and a PR is raised on Azure DevOps for review, playtest, and merge.

Iterate on feedback

Playtest notes feed the next round of tuning — steering feel, orbit range, spacing — until it’s right.

What we learned

Lessons from shipping a real Store game with an AI coding agent.

Intent beats syntax

The most valuable input was a clear description of the desired feel or behavior — the agent handled the how.

Humans still steer

Playtesting, taste, and product judgment stayed human. The agent accelerated everything in between.

Root-cause fixes

With the whole codebase in view, the agent traced problems to their source and fixed the underlying cause — not just the visible symptom.