A fun experiment with a serious question behind it: how far can the newest AI models take a complete game? Everything in Squadfather was built with AI, from the coach mascots and the gameplay to the achievements, the 1v1 multiplayer and the translations into 22 languages. I directed it, set the guardrails and shipped it to the App Store.
A football squad game with a simple loop and a lot underneath it.
Spin a wheel for a club, draft your XI from this season's squads across 18 leagues, then play out the whole season and chase an unbeaten record.
The Squadfather and his rival were designed with AI image generation as a layered set of outfits, glasses and whistles, giving 54 combinations that players unlock and customise.
Challenge a friend live with a six-character code, or get matched by rating and climb six tiers from Bronze to Elite.
Weekly ladders for every league, an all-time global board and a 1v1 board, with the game and the website in 22 languages.
Not a prototype or a demo: a live game on the App Store, built by AI agents working to a plan.
Every feature started as a written plan, with clear rules for the agents on how the game, the data and the brand should work.
AI agents built the app, the match engine, the multiplayer backend and the website, feature by feature.
The coach mascots, achievement badges, store listings and translations into 22 languages were all produced with AI.
Hundreds of automated tests and layout checks on phone sizes and languages gate every release.
A top-level look at how it's put together. AI agents did the building; the guardrails around them are what made it shippable.
A single TypeScript codebase for the iPhone and iPad apps and the browser game, with smooth native animation throughout.
1v1 rooms, matchmaking, leaderboards and scheduled jobs run on a serverless worker with an edge database. Updates ship over the air from a self-hosted, code-signed update server.
The match engine is a pure, seeded function, so the server re-runs every match and season and only its result counts. No result can be faked from the app.
Written rules for the agents, numbered plans for every feature and hundreds of automated tests, so each change the AI made had to prove itself before it shipped.
I've spent 7+ years in paid advertising, agency-side and in-house, most recently as Head of Paid Search for 3+ years at Soar With Us, a D2C agency, growing brands to 8+ figures. I've since started Pavegrowth to continue my love of building and growing brands with that expertise.
Alongside the ad accounts I build Shopify themes, iOS apps and software products, including my own. Growth marketing and development under one roof. I utilise AI workstreams to support moving faster & streamlining internal & client workflows to ensure efficiency, whilst the strategy, judgement and accountability are mine. You talk directly to the person doing the work.
Thirty minutes to get to know your brand, your goals and where the growth is. No pitch deck, just a straight conversation about where we'd take it next.
I'll get back to you shortly about your request. Looking forward to learning more about your project & goals!
