AI-NATIVE GAME STUDIO

Games Built by AI,
Played by Humans

Fundy Digital runs the entire game development lifecycle — design, code, test, deploy — using AI agents. Every game you play was conceived, built, and shipped by Claude Code.

7 Games in Production iOS & Android 100% AI-Agentic
OUR GAMES

A Studio Full of Ideas, Built by AI

Productivity & Family

Chore Quest

AVAILABLE

Kids earn rewards by completing family chores. Parents set tasks and approve completions — kids track earnings and level up.

iOSAndroid

Focus Bun

AVAILABLE

Task prioritization for teens with ADHD. Calm, distraction-free design that helps users identify and act on what matters most.

iOSAndroid
Party & Social

Emoji Whisper

COMING SOON

Encode a secret phrase using only symbols. Your partner decodes it. AI scores how close they get — zero to one hundred.

iOSAndroid

Dual Draw

NEW BETA

Two players each receive half of a hidden prompt and draw independently. Their canvases combine at reveal — chaos and creativity guaranteed.

iOSAndroid

What Did We Draw

LIVE EVENT

Pass your drawing around the group. Everyone guesses what it was. The results are always better than expected.

iOSAndroid
Skill & Puzzle

On The Dot

COMING SOON

A pure precision timing game. Tap at exactly the right millisecond. Deceptively simple, endlessly replayable.

iOS

SyncShape

AGENT FAVORITE

Rotate your phone to align a 3D puzzle piece with your teammates'. Each player holds one fragment of the same object — designed, coded, and debugged entirely by AI agents.

iOSAndroid
HOW WE BUILD

Fully AI-Agentic.
Every Step.

Fundy Digital runs its entire SDLC through a custom multi-agent system built on Claude Code. Every game goes from idea to App Store without a human writing a single line of code — the agents plan, design, build, test, review, and document everything.

The system connects to Stitch MCP for UI design generation and XcodeBuildMCP for live iOS simulator control — giving the agents eyes and hands on the actual device.

TECHNICAL ARCHITECTURE

The Multi-Agent Engine

A purpose-built orchestration layer routes every task to the right specialist agent. No agent acts alone — the orchestrator enforces the full workflow on every run.

hub ORCHESTRATOR LAYER

Orchestrator Agent

The top-level coordinator. Reads docs/current-architecture.md and CLAUDE.md on every task, enforces the planning gate before any code is written, routes to the correct specialist, and runs a token-efficiency review at the end of every session.

claude-sonnet-4-6 Planning Gate enforced Token cost reporting Living docs rule
Delegates to specialist agents
architecture

Architect

Opus 4.6

Produces a structured implementation plan — files to change, invariants in scope, risk assessment, blast radius — before any code is written. No plan, no coding.

Feature design Data flow Service boundaries
palette

UI Designer

Sonnet 4.6

Outputs a full layout spec — widget hierarchy, interaction states, iOS & Android device constraints, safe areas, touch targets, and spacing tokens — before handing off to the Coder.

Stitch MCP Widget hierarchy Device constraints
code

Coder

Sonnet 4.6

Implements the minimal safe change from the Architect's plan. Never touches business logic without a test. Reads the actual source files before suggesting any change.

Flutter / Dart Minimal changes No scope creep
bug_report

Tester

Sonnet 4.6

Writes a failing test before any fix. Runs flutter test test/ — must show all passed. Owns regression coverage and overflow checks via XcodeBuildMCP screenshots.

Test-first XcodeBuildMCP Golden tests
rate_review

PR Reviewer

Sonnet 4.6

Reviews every diff for correctness, regressions, security (OWASP top 10), invariant violations, and test coverage before merge. No review, no merge.

Security review Invariant check Coverage gaps
description

Docs

Sonnet 4.6

Keeps docs/current-architecture.md accurate after every task that touches architecture, flows, or invariants.

security

Cyber Security

Sonnet 4.6

Scans for OWASP vulnerabilities, credential leaks, insecure storage, and platform-specific attack surfaces across every PR.

MCP Tool Integrations
brush

Stitch MCP by Google

The UI Designer agent calls Stitch to generate high-fidelity screen designs from text prompts. Outputs production-ready HTML with Tailwind — no Figma, no handoff.

smartphone

XcodeBuildMCP iOS Simulator

Gives agents direct control of the iOS simulator — build, launch, screenshot, and read the result. The Tester agent sees the actual rendered screen, not just code output.

Mandatory Workflow — Every Task, No Exceptions
1
Read Docs
architecture.md + CLAUDE.md
2
Architect Plans
Files · risks · sequence
3
UI Spec
Widget hierarchy + Stitch
4
Failing Test
Written before any code
5
Implement
Minimal safe change
6
All Tests Pass
flutter test — zero failures
7
PR Review
Security · coverage · diff
8
Docs Updated
Architecture stays current

The Future of Game Development is Agentic

We believe AI agents won't just assist developers — they'll replace entire workflows. Fundy Digital is proving this today: every commit, every screen, every test is AI-authored. We're not using AI as a tool. AI is the team.

Meet the Humans Behind It
THE HUMANS

Who's Running Fundy Digital

Named for the Bay of Fundy — one of the most powerful, dynamic forces in the natural world. That's the energy we bring to building games.

👩‍💻

Belinda M.

Founder & Builder

Over 20 years in the tech trenches — surviving VB 6.0 and Assembly through Java and Python, architecting systems at every layer of the stack. Belinda has coded in more languages than most people have debugged in, and she built Fundy Digital to prove that the next evolution isn't a language — it's an agent.

VB 6.0 Assembly Java Python Claude Code
💡

Lillian K.

Visionary & Market Strategist

Lillian is the creative force behind Fundy Digital's game ideas — with a sharp eye on the teenage market and an uncanny ability to spot what young people actually want to play. She turns cultural moments into game mechanics, and keeps the studio pointed at the generation that will define the next decade of mobile gaming.

Teen Market Game Design Gen Z Trends Product Vision
🔍

Renee K.

Head of Testing

Renee leads the QA layer that sits above the AI agents — defining the coverage standards the Tester agent must meet, hunting edge cases machines overlook, and validating real-device behaviour beyond what any simulator can catch. Nothing ships without her sign-off.

QA Standards Edge Cases Device Testing Release Sign-off
🌊

"The Bay of Fundy has the highest tides in the world — raw, unstoppable, and awe-inspiring. That's the energy we named this studio after. Every game we ship is built with that same force."

— Belinda M., Founder