iGaming · Design + AI Tools2026

MYBC

A creative department of one — built out of AI tools instead of hires

MYBC is an international online casino and sportsbook. I run its creative side alone: the brand, the performance ads, the campaign banners, the promo landing pages, a sports news site’s social feed, fifteen thousand game thumbnails. That is a department’s worth of output, so instead of hiring a department I built a stack of AI tools that do the repetitive part — and kept the taste part for myself.

Role

Design Lead · Creative Technologist

Timeline

2026 · ongoing

Scope

Brand · Campaigns · AI tools

Year

2026

A grid of 21 game cards in one unified style — 3D hero characters on flat colour gradients with centred titles
01The problem

A casino needs more design than one person can draw.

Game cards for a catalog of fifteen thousand titles. Performance ads for every match, in every market. Campaign banners for every final. A landing page for every promotion. A news site posting daily. Support questions arriving around the clock, in nine languages. And one designer.

15,451

games in the catalog — each wearing its maker’s art

The games come from more than a hundred studios, and every studio ships its own thumbnail style. Put them on one grid and it reads like a flea market, not a brand.

The insight

Wherever the work repeats, build a tool. The tool does the hands. I keep the taste.

02Thumb2Hero

A pipeline that redrew the whole game catalog.

Thumb2Hero is a tool I built that turns any provider’s thumbnail into a card in our house style. It looks at the original art, writes down what the game is actually about, redraws the hero as a single 3D character, cuts it out, picks a colour gradient from the original, and checks its own work. Anything it isn’t sure about lands in a review queue for me.

01

One grid, one brand.

The top row is what six different studios shipped us — six art styles, six kinds of baked-in text. The bottom row is the same six games after the pipeline: one character, one gradient, the platform’s own typography. Multiply by fifteen thousand.

SolvesA flea-market grid

Six provider thumbnails in clashing styles above, the same six games redrawn as unified hero cards below
Before and afterTop: what the providers ship. Bottom: the same games after the pipeline.
02

A review room, not a render button.

The pipeline is a state machine — every game moves through analyse, generate, cut out, quality-check — and this screen is where I watch it. Doubtful cards queue for a human verdict: approve, reject, or regenerate. The finished set leaves through an export API the developers pull from directly.

SolvesTrusting 15,000 generations

Thumb2Hero web interface — a filterable grid of 15,451 games with pipeline states and provider filters
Thumb2HeroThe tool I review the catalog in — every game, its pipeline state, and the card as the player will see it.

98/100

of the first live sample came out usable

I ran a 100-game sample before committing to the full catalog. 98 generated clean, and every cutout passed. Only then did the other fifteen thousand go in — at roughly four to seven cents of model fees per finished card.

03Quality control

Then the cutouts started eating people.

The background remover hollowed out dark clothing on dark backgrounds — black suits and dresses came back as outlines. By the time I caught it, 950 of the first 8,276 cutouts were broken. Eleven and a half percent, and no human was ever going to eyeball fifteen thousand images to find them.

So the pipeline got an auditor: a check that flags any cutout with transparent holes inside the subject, plus a colour audit that compares each cutout against its own generation. Both run on every card, and flagged ones re-cut automatically — for free, since the art already exists.

At fifteen thousand images you don’t check quality. You build the thing that checks quality.

04Automato

An ad factory that turns a fixture list into finished campaigns.

Automato makes the performance ads. Give it a match and an offer, and it produces finished Meta creatives. Every ad is two layers: an AI-painted scene that is banned from containing any text, and a precise template on top that owns the logo, the odds, the headline and the responsible-gambling chrome. The AI never touches the typography, so nothing ships with melted letters.

03

The picture is AI. The words never are.

One quarter-final, three markets. The copy is translated and overlaid at render time, never baked into the pixels — a new language is a re-render, not a redraw. Club crests come from a sports database rather than the model’s imagination, and a roster guard flags any player named in the copy who isn’t actually in the match.

SolvesMatch-day ads in every market

Automato Meta ad — Argentina vs Switzerland head-to-head with crests, odds chips and a freebet button
English
Crests and odds pulled from data.
Automato Meta ad in Norwegian — an England player mid-run, headline De Tre Løvene Brøler
Norwegian
Same campaign, another market.
Automato Meta ad in German — Argentinien vs Schweiz head-to-head with odds
German
Copy overlaid, never baked in.
04

One creative, every size Meta asks for.

The hero is generated once, then re-framed into story, feed and landscape. The template re-lays itself out per size using safe areas measured from the real rendered layout, so the subject never hides behind an odds widget. A batch queue renders whole campaigns end to end — a sixty-ad run is a button press, and the finished set exports as Meta-ready bulk files.

SolvesThe format matrix

The same Automato ad rendered as a 9:16 story, a 4:5 feed post and a 1.91:1 landscape banner
One creative, three canvasesStory, feed and landscape from one generated hero — the template re-lays itself out per size.
05Campaigns

One locked template, a new story every match day.

Campaign banners run on a design system I locked after eleven rejected versions: dark navy, hex grid, one cinematic object in the middle, the quiz tag, the orange claim button. Only the story changes — the AI renders the scene, the system holds everything else still.

05

The banner tells the story. The template sells the offer.

Three banners from one Champions League final week. A scarf on a bench for the fans coming back after twenty years; a number nine in light for the striker chasing his twenty-first; the shirt numbers of the Portuguese quartet. Different stories, same skeleton — recognisably one brand at feed speed.

SolvesA team’s output on match-day deadlines

MYBC quiz banner — an Arsenal scarf on a stadium bench at night, headline Back in Budapest
Match-day banner
Story first: a scarf, a bench, a final.
MYBC quiz banner — a glowing number 9 made of red and blue light trails, headline Twenty Goals One More
Match-day banner
Same template, different story.
MYBC quiz banner — chunky 3D numerals 1, 7, 8, 9 on a dark pitch, headline Quatro Em Budapeste
Match-day banner
The system holds even in Portuguese.
06MYBC News

A newsroom that posts itself — with a human holding the button.

MYBC also runs a sports news site, mybc.news, publishing in seven languages. I built its social pipeline: every half hour it reads the newest stories, an AI scores them — flagging legal risk and stale news on its own — and writes the Facebook caption in the page’s measured voice. Hook line in caps, one line of context, no hashtags, because the real captions it studied had none.

mybc.news homepage — dark sports news site with top stories, quiz and leaderboard modules
mybc.newsThe news site the pipeline feeds from.
Auto-rendered share card for a Liverpool transfer story — photo, club crest and headline on a dark plate
Share card, rendered by codeEvery article gets one in four sizes — about half a second, no model cost.
Auto-rendered share card for a tennis story about Aryna Sabalenka
Any sport, same systemComposited from the article’s own photo.
06

Nothing posts without a human tap.

Each candidate lands in a Telegram room as a ready-to-post card with four buttons: approve, cancel, swap the copy, or have AI redraw the card in the editorial style the team used to make by hand — the article’s own photo recomposed to 4:5 under a huge condensed headline, about 13 cents a card. The logo is stamped on afterwards as a real vector, because model-drawn logos are never acceptable. One tap publishes to the Facebook page.

SolvesDaily social output, zero unreviewed posts

AI-generated 4:5 editorial card — the article photo recomposed under a huge condensed headline with the MYBC News logo
The AI editorial card
Drawn in the style of the cards the team used to make by hand; the logo is stamped on as a real vector afterwards.
07Landing pages

Seven promo pages that know who’s looking at them.

Every promotion gets a landing page, and every page knows your state: logged out, logged in, bonus claimed, first deposit made. The hero, the copy and the button all change with it — a visitor is asked to sign up, a player is asked to claim. The pages are generated from Python assemblers, so a fix to one component propagates to the whole set on the next build.

MYBC sign-up landing page — a gold star trophy scene above an orange call-to-action button
Sign-up
The welcome offer.
MYBC triple deposit landing page — giant gold 3D numerals reading $1,500 and 1,500 FR on a velvet pedestal
Triple deposit
The number is modelled into the art.
MYBC wager race landing page — a podium with trophy and medals, referral code KORVINA with a copy button
Wager race
A tournament with a live leaderboard.
MYBC house edge landing page — a giant gold 48% on a velvet pedestal with coins
Rakeback
Four kinds of cashback, one page.
08Support

An AI support agent that writes like the team — because it studied the team.

Support runs on LiveChat, in nine languages, around the clock. I built an assistant for it the same way I built the art pipeline: from the client’s own data. It mined 10,606 archived conversations into a 70-topic knowledge base, reads the customer’s real account state before answering, and every draft is reviewed by a second AI before anything is sent. When it isn’t sure, it hands the chat to a human — with a briefing note, so the customer never repeats themselves.

My first version wrote 230-character customer-service lectures. Then I measured the real team: median reply, 40 characters, and one message in seven carries an emoji. The bot was polite. The humans were fast. I rewrote it to be fast.

Measured across 36,874 real agent messages
07

Five gates between the model and the customer.

Scan the topic — sensitive ones go straight to a human. The AI drafts with the knowledge base and the live account in view. A rule guard screens the draft. A second model approves, rewrites or rejects it. Only then does it send. On a 37-scenario test battery it answers 35 and hands off the rest — with zero unnecessary transfers. It runs in shadow today; the team decides when it goes live.

SolvesWrong answers about money

MYBC support assistant demo — a chat answering a withdrawal question, with the five-step reply pipeline diagrammed above it
The support assistant, in its test harnessEvery reply travels: scan the topic → AI drafts → rule guard → a second AI approves → send, or hand to a human.
09Results

What it did.

14,960

Game cards shipped

Generated, QC’d, human-approved

~5¢

Model cost per card

Measured 4–7¢ across the runs

6

Tools in the stack

Cards · ads · banners · landings · news · support

35/37

Support test battery

0 unnecessary human handoffs

The tools don’t have taste. That part is still my job — it’s just the only part left.

Next case study

Goldmarket

A Georgian marketplace for gold and jewellery — designed, coded, tuned and shipped to web, iOS and Android by one person.