David MonsonTalk to me

One person and a team of AI agents built a live arcade of learning games in five months.

Mastery Arcade is two games on one learning engine: Times Machine, with 17 levels and 4 boss fights for your times tables, and the Lab, with 22 hands-on 3D science experiments. I built it alone from May 30, 1,069 commits, for web, iPhone, iPad and Android from one codebase. Here's how I did it, and the decisions that made it work.

Mastery Arcade. Founder and only builder. Product, design, code, AI media, growth. May 2026 to now. Live on the web, App Store launch planned for Nov 3, 2026.

Two games, three platforms and 1,069 commits, from one builder.

Five months, May 30 to October 31. I decided what to build and made the taste calls. AI agents wrote most of the code. The second game, the Lab, reached production with 11 experiments built in one day.

These count what exists in the repo today. I'm leaving out reach and revenue until there's something to report. The web version is live, and the App Store launch is planned for November 3.

1,069Commits on main, May 30 to Oct 31, all under my name
1Person building it, directing AI agents
22Hands-on 3D experiments in the Lab
3Platforms from one codebase: web, iOS, Android

Games you want to keep playing, with real practice inside.

Kids and adults practice facts with flashcard apps that bore them, or with games that teach very little. Mastery Arcade is my answer: a growing set of learning games, built on one learning engine, with the feel of a real arcade.

The first game is Times Machine. A giant machine has come to optimize Earth, and the only way to beat it is multiplication. You practice each table, earn a medal, then fight bosses named BYTE, MEGA and GIGA before facing the Times Machine itself.

The second is the Lab, where you pick up a question like "how do planes fly?" and test it with your hands in a 3D room. One family pass covers everything, with up to six Players.

It started on May 30 as one multiplication app. By June 27 I had rebuilt it as a monorepo around a shared engine, so a second game wouldn't mean starting over.

The Times Machine, the final boss. The only way to beat it is multiplication.
17Levels in Times Machine, from the 1x table to squares and cubes
4Boss fights, each with its own film
11Lab experiments built in one day by about 15 parallel agents
Up to 6Players on one family pass
The 26-second launch cut. Sound on. Made from the game's own footage and captures.
The arcade on a laptop: a Times Machine card with the giant robot, and a Lab card with the cartoon scientist and robot arms.

Two worlds. The arcade on desktop: Times Machine at night, the Lab in daylight.

A BYTE fight on a phone: 6 times 3 equals 18 glowing over the machine, its health bar half gone, a keypad below.
Fights that drillEvery right answer drains the machine's power.
The x8 level screen, Figure Eight, with a Start Practice button and a grid of facts colored by how well each is known.
Every fact, visibleEach level shows which facts you've mastered.
Level mastered: a gold x3 medal over a glowing globe, with accuracy and time below.
Medals on speedA level is mastered when the facts come fast.

Real captures of the app on a phone and a laptop, from a local test account. The Players are an invented demo family with helmet avatars.

Spaced repetition
FSRS, through the open-source ts-fsrs library, picks what comes next. Missed facts come back often. Mastered ones return for a check about a week later.
A four-second line
A clock on every question rewards quick recall over working it out. Under four seconds counts as known. That line is my own design choice, and the site says so.
Cover-Copy-Compare
When you miss a fact, you see it and retype it from memory.
A page that admits what's unknown
The evidence page sorts every choice into what research supports and what's my own bet. It says plainly that I haven't run my own study. I wrote it to be read by a skeptical parent.

One engine, so the game can't drift away from the learning.

Practice, level drills, every boss, the challenges, the first-run drone mission and the free speed check on the website all ask questions through the same state machine. Each surface sets its own knobs, like the retry on a miss or the clock. Nobody gets to write a second one, because a boss fight that grades differently from practice would quietly break the promise of the product.

Boss fights as a layer on top
The boss owns health and drama. The engine owns the question, the timer and the grade.
Three.js where it earns its place
Characters, the trophy case and hero moments run in WebGL. Everything else stays light, so a phone keeps up.
Haptics scored from the picture
Each boss film has its own haptic score. I rebuilt it around an onset detector gated against the measured speech, replacing a flat threshold.
Tokens, medals, trophies, certificates
A free daily token economy with a real spend moment, a coin that drops as you start a level. Medals you earn on speed. Certificates you can print, and share cards for every win.
A GIGA fight on a laptop: 15 times 7 over the machine with the glowing cube on its chest, a keypad below, a burning harbor behind. A MEGA fight on a phone: 8 times 9 equals 72 over the machine with X12 on its chest.
The same fight on a laptop and a phone: GIGA on desktop, MEGA on iPhone.

The product is the output. The way I run the agents is what I'd bring to your company.

I don't write most of the code by hand. I decide what to build, I make the taste calls, and I check the result by using it on a real phone. Agents do the rest. That only works with a system around them, and most of that system came from something breaking.

On September 2, I filed nine epics and about 108 issues and let the agents go. They started around 6:15 pm and were still merging past 3 am. Over that four-day arc, 47 PRs landed, along with one production incident and one forced hosting upgrade.

47PRs landed in one four-day arc of agent work
About 12,300Automated tests in late October
74 KBRulebook every agent reads, most rules next to the incident that caused them
About 108Issues filed on September 2 before I let the agents go
Issues are the coordinator
Small work lives in GitHub Issues, never in a chat. One issue, one worktree, one branch, one PR. Assignment is the lock. Any session on any device can pick up where another stopped.
Labels decide who has to look
Ready for an agent. Can merge on green tests. Needs me. Money, auth and anything a kid sees default to needing me, however green the tests are.
"Green CI is not evidence of correctness"
That's in the rulebook. Every serious finding so far passed CI. So auto-merge is a decision someone made in advance, never just a passing build.
Ratchets in CI
Tests fail the build on a typed-in price, a stray icon, or a second learning engine. Rules I care about become tests, so I don't have to catch them in review.
A model for each job
The main session plans and reviews. Every dispatched agent names a cheaper model. That rule exists because eight agents once inherited the most expensive one in a single day.
A 74 KB rulebook
CLAUDE.md, with most rules next to the incident that caused them. Every agent reads it, so a lesson learned once applies to all of them.
Scheduled agents that review the business
Routines for profitability, growth and security. They're read-only, and each ends in one issue, one PR or one comment. A Control Center I built shows their findings next to a stamp for whether I read them. Most of them were written long before they were ever scheduled, and the doc says that too.
I review by using
I test on a real phone, so agents give me a link to tap, never a diff. Sound gets my ear. Art gets my eye.

A character pipeline, down to about 25 minutes.

I make and approve the character art myself in Midjourney. Agents run everything after that: Meshy turns the image into a 3D model, it gets rigged and animated, and it lands in the game as a GLB file in Three.js. I proved the whole path on one pilot, VEX, on August 23: 62 credits and about 25 minutes.

The steps are simple to list. The rules around them are what cost me. They're written into the pipeline doc, each with the measurement that earned it.

25 minTime for one proven character run, approved art to game-ready model
62Credits for that run, mesh to nine clips
24Playable pilot characters, rigged and animated
About 30Credits a failed pilot costs now, down from about 72
VEX source art: a red armored pilot on white, arms held clear of the body. VEX as a 3D mesh on black, in an A pose. VEX portrait as it appears in the game's character picker.

VEX: the approved art, the free mesh check, and the portrait in the game.

Check the free thumbnail before buying the clips
One pilot reached the game deformed because nobody looked at its mesh. I ruled out the rig with measurements first. The skeleton was fine and the mesh wasn't. The check moved the cost of a failure from about 72 credits to about 30.
What makes a good source image
Armor as real shapes rather than painted lines. Strong contrast. Flat light. Arms clearly away from the body, because that's the one that broke a pilot.
Restore what rigging throws away
The rigging step silently dropped two texture maps and made the model fully self-lit, so no light in the scene touched it. A script puts them back.
Ship the textures you paid for
My first builds looked blobby next to the same character in the vendor's viewer. Geometry was never the issue. It was texture resolution. Delivery went to 4096 maps at about 4.2 MB a pilot, which works because the picker only loads one at a time.
Repaint without a rebuild
A torn visor is a texture fault. Repainting takes 15 credits against about 60 for a rebuild, and I repaired a batch this way. But one repaint came back identical, because that source helmet had no visor to repaint. Check the source before spending.
Three idles, on purpose
A character spends most of its time idle. One looping idle reads as a mannequin. So every pilot cycles through three, plus a shared set of moves, and any pilot can do any of them.
Gold needs something to reflect
Gilded boss statues are a referral prize. Tuning the lamps didn't work, because metal only shows what it reflects. It needed an environment.
The pilots The pilot roster in three rows on a dark blue floor: red, sky blue, orange, magenta, white, green, yellow and pink armor in front, more behind, with the Times Machine and its glowing X looming at the back.
The roster. My approved character art for the pilots, lined up in the game's own night, with the Times Machine behind them.
The machines The machines from smallest to largest over a stormy blue city: the recon probe, BYTE with X6, MEGA with X12, GIGA with a glowing cube, and the Times Machine with its glowing X.
Smallest to largest. The recon probe, BYTE, MEGA, GIGA and the Times Machine, from their model sheets.
The pilot picker on a laptop: LYRA, a white armored pilot, standing as a 3D model on the left, a grid of helmet portraits on the right. The pilot picker on a phone: NOVA, an orange pilot, as a 3D model above a grid of helmet portraits.
The pilot picker on desktop and phone. Each pilot in it is a rigged 3D model.

I directed the films like films, then measured what the models really do.

Each boss has its own encounter: it arrives, taunts you, fights, and falls apart when you win. I made stills in Higgsfield with GPT Image 2, then video with Seedance. A captain named Reyes talks to the player between fights. "Identity is won or lost in the still" became a rule, because the video reproduces every flaw in its first frame.

Every prompt and start frame for the four encounters took about 2,700 credits of directed work. Then I found out it all lived in a temporary folder the operating system could wipe. So now a ledger records each render's exact inputs. A vertical version of a film is a loop over that ledger, not a dig through old chats.

BYTE's encounter, 38 seconds, vertical. Sound on.
Reyes in the Victory Hall. A generated character, a designed voice and measured lip sync. Sound on.
An incoming transmission screen: Captain Reyes on the left, a map behind her, with her line as text below.

The transmission screen, where Reyes talks to you between fights.

Tell the model what's true, don't forbid
"No push-in" got ignored. "The camera is bolted to the floor and NEVER moves" worked. These models have no negative prompt, so a "no" is only more words about the thing you don't want.
Extract the join, never recreate it
Shots chain end frame to start frame. One loop started from a hand-made lookalike instead of the real last frame. It looked close enough until someone drew a center line on it. Measured, the mismatch was 14.37, where two neighboring frames sit at 1.34. A tool now extracts every join and checks it by hash.
Always render with sound
Muting later is one flag. Adding sound later is a whole render. And the generated sound lands on its own picture: the loudest moment fell on the frame of the biggest visual event.
Two tests for lip sync
Sync and stillness are separate problems. A clip passes on both measures, or it doesn't ship. I also learned to measure inside a shot, never across a fade, after a "fix" for a 79 ms offset created the drift I then complained about.
Tag how sure you are
Every rule in my film skill is tagged: measured by us, from documentation, general craft, or a bet. A bet can't become a rule until it's measured.
A rule with a date on it
A finding about audio on one Seedance version didn't hold on the next one. So rules now record what was measured, on which version.
Draft cheap, price it, then ask
A finished 14-second scene is about 180 credits. Composition gets settled in drafts. No video gets generated until I approve the spend.
The Times Machine in searchlights, a bright burst at its shoulder as it starts to fall.

The final boss starting to fall. A still from the defeat film.

The biggest sound fix was a default nobody had chosen.

The soundtrack is my own Suno tracks, switched by scene. Reyes' voice is one I designed in ElevenLabs, cloned into Higgsfield, with a vibe note on every line.

One lesson was bigger than audio. Her voice ran on one engine for a month until I asked why we weren't using ElevenLabs through Higgsfield. Side by side, the same intro ran 24.85 seconds against 18.24, and a laugh got performed where before it was spoken as syllables. Nobody had chosen the old engine. It was a default no one had decided, and that went into the brief.

The voice ships inside the clip
A separate voice track started alongside a silent video was two clocks aligned once, and it drifted. Now they're one file. The price is on iOS: the element has to be primed by a real tap beforehand, and volume can't be set in code, so levels get baked in when it's encoded.
About 300 recorded sounds in one night
I played ten new experiments and told the agents "the sound effects all suck." They were stand-ins nobody had replaced. Now a new sound ships recorded: several takes from ElevenLabs, measured and ranked, with a check for what a phone speaker can even play. My ear is the last gate, because the builders can't hear.
Two audio paths, one lifecycle owner
Effects and music use different browser systems with different unlock rules. Mixing them up was the top cause of mobile audio bugs. One module owns all the recovery logic.

Then I built a second product in about a day.

In mid-October I pointed the same system at physics. The first 11 experiments reached production on October 15, built in one day by about 15 parallel agents working from shared briefs for UX and art. By the end of October there were 22: smoke tunnels, Build an Atom, a roller coaster, orbits you can crash a moon through.

Each one has a question, things to try, clues and a short quiz, and you earn a patch. Your own pilot from Times Machine shows up in eight of them. These clips are real captures of the app.

Roller Coaster on desktop, in follow view. Height energy turns into motion as the car drops.
Orbits. Crash the Moon into the Earth.
Momentum Crash Lab. A city bus against a toy car, with the ledger to prove it.
Smoke Tunnel on a phone: the player's pilot holding a pole in the wind, with push, speed and weight readouts.
Smoke TunnelYour pilot holds on until drag beats weight.
Pendulum Wave on a phone: a row of colored balls on strings of different lengths swinging out of step.
Pendulum WaveDifferent lengths, one moving wave.
Build an Atom on a phone: a hydrogen atom in a glass jar, with counters for protons, neutrons and electrons.
Build an AtomAdd a proton and it becomes a new element.
The Lab's hub on a laptop: Pick an experiment, with cards for Smoke Tunnel, Sand Music, Orbits, Pendulum Wave, Magnet Forge, Light and Color Studio, Ripple Tank and Roller Coaster over a bright lab. The Lab's hub on a phone, with experiment cards in two columns.
The Lab's hub on desktop and phone. Each experiment earns patches for your lab coat.

A real app on Apple and Google, from one codebase.

I was an iOS developer before I was a designer, so I knew the danger: an app that's only a website gets rejected. The apps are Capacitor shells around the live product, with native features a reviewer can find and use. Most of the store work was paperwork. I turned that into tested files, so the listing can't drift from the code.

iPhone and iPad
Native Apple and Google sign-in on system sheets, haptics during play, seven app icons, a native launch animation, an offline screen, a rate-us prompt after a win, in-app account deletion, and separate iPad layouts.
TestFlight since August 29
A one-command pipeline builds and uploads. On one user-testing day I ran eleven device findings through eight merged PRs before the day ended.
App Store machinery
Screenshots from a repeatable pipeline in three complete directions, on real captures. Safe uploaders for screenshots and preview videos. Review notes pinned by tests. A demo family with every boss ready, so a reviewer can see it all.
A new Apple rule, written into my process
On October 16, Guideline 2.5.19 banned hidden or undocumented features. Since the app loads the live site, a flag could put a new game in front of families without Apple seeing it. So my rule is now written down: a new game reaches iOS only through a reviewed app version, even if the binary is identical.
Android
Same shell, native Google sign-in through Credential Manager, and a paste-ready submission pack for Play Console. It sells nothing in the app, which keeps Google's cut at zero. Families buy on the web.
Kids and privacy
No ads and no chat. The apps run no analytics on the Player's screens. A grown-up gate protects money and account moves. The privacy labels are pinned to the code by a test.
Training Grounds, the practice home, on a phone: Smart Practice, Level Drill and level tiles in neon blue. GIGA's entrance on a phone: the machine with a glowing cube on its chest, and the line Thirteen through fifteen, squares and cubes. A demo Player's field report on a phone: facts locked in, answers, streaks and a grid of every fact. The family picker on a phone, Who's playing?, with helmet avatars for six demo Players.

The iPhone app: practice home, a boss entrance, a Player's field report and the family picker. Demo family.

Money gets the strictest rules in the repo.

I priced one family pass and one solo pass, sold on the web through Stripe. I planned Apple in-app purchase, then cancelled it. The iOS app is US-only for version one, and it opens Stripe in a browser sheet. The prices will change as new games arrive, so I built the system to make a stale price impossible to type.

One file holds every price
A CI test fails on any dollar amount typed into the UI. Stripe prices are created from that file by a script, and a drift test checks that the two agree.
A locked price for early families
Stepped prices, where a subscriber keeps the price they joined at. Even the strikethrough can only show the next step I've committed to.
I asked for spoof testing
"Make sure you can't spoof through paying." An audit listed 13 ways to try it. Each one now has an executable test or a written verdict, and three got fixed.
A purchase ends in the game
A new buyer lands on a celebration and the game, never on an identity check.

Growth is built into the product, ready for launch.

All of this is in code. None of it has real volume behind it yet, so I can tell you what I built and nothing about how well it works. I also read my own weekly memo the same way: the first one found a real checkout that started and never finished, and showed a referral factor of zero.

The public Times Machine page: Beat the Times Machine, in neon blue on black.
The game's pageBoss fights and the story, in the game's look.
The free speed check, showing 8 times 4 with a keypad and a timer bar.
A free speed checkNo sign-up, nothing saved, on the same engine.
The evidence page: What the research says, and what we haven't measured.
The evidence pageSources, bets and limits, for parents and for search.
Technical SEO
One metadata helper for every public route, a sitemap, robots rules, and JSON-LD structured data. Every public link unfurls with a proper image.
Answer engines
An llms.txt file, and a written GEO strategy that labels each claim as measured, vendor or academic before anything got built. It was written to discount vendor hype.
Pages people search for
A free speed check with a shareable result, and a standards page that maps multiplication practice to Common Core, Texas and Florida, fact by fact, with sources.
Lifecycle emails
Welcome, checkout left behind, out of tokens, and after purchase, all from one branded shell with sending caps. A claim is recorded before each send, so a retry can't double-mail anyone.
A launch email that can't fire by accident
It has no route and no cron. A person types the command. It looks first, tests next, sends 5, then the rest. It refuses to send without a live store listing.
Loops
Two-sided referral credit, trophy and certificate share cards with their own images, a challenge at every win, and family invite links. A designed classroom loop isn't built, so I don't count it.
A social kit
A cut for each platform from one master, each with captions clear of the platform's buttons.

I turned the expensive lessons into skills that any agent can load.

The biggest is a 153 KB skill on directing AI film, written from my own tests. A skill is a written playbook an agent reads before it starts a job. Some of these I wrote from scratch, and some I brought in and changed. Here's which is which.

What it costs, as far as I can honestly say.

My cost sheet has one rule: a blank means unknown, never zero. So it refuses to give a total while lines are missing. In September, I could price five of twelve lines. The rest stayed blank, so I don't have a true all-in number, and I won't estimate one here.

Known monthly vendor spend, Sept 4 (Vercel, Supabase, Apple, Claude Max, iCloud+)$253.25
Vendor lines still unknown then7 of 12
One character, mesh to nine clips62 credits
Seedance at 1080p, per secondAbout 9 credits
Finished 14-second sceneAbout 180 credits
Directed work in four boss encountersAbout 2,700 credits
CI minutes used in OctoberAbout 6,400
Time per test run, before and after my fixUp to 25 min, then 11.5

Most of what broke was silent. Here's the list.

Many of these were silent. Nothing errored, and nothing looked wrong until someone checked.

The list

Live on the web, with the App Store launch planned for November 3.

The web version is live at masteryarcade.com. The App Store launch is planned for Tuesday, November 3. Apple hadn't received the app for review the last I checked, on October 31, so that date depends on review. If Apple runs late, the plan is to launch on the web on the 3rd and let the store follow.

The launch is the real test, and I'll put the results here, good or bad.

WebLive
iPhone and iPadTestFlight now, App Store planned Nov 3
Google PlayWon't make Nov 3
Android families on launch dayPlay on the web
Why Google Play is later
A new personal developer account has to run a closed test with at least 12 testers for 14 straight days before it can publish. The shell and the submission pack are prepared. I put the test on the back burner to focus on launch.
Still in progress
A first-run cutscene for Times Machine. Spellwright, a spelling game, is built but isn't part of launch. Worldsong, a music and geography game, is next.
What I can't tell you yet
Whether it teaches better than other ways of practicing. I haven't run that study, and the product's own evidence page says so.

Everything it took, from Midjourney to the App Store API.

I can run this system inside your company.

Agents, rules, evals, skills and a person making the calls. I've done it alone, from the first commit to a live product, and I can teach your teams to work this way.

Start a conversation