Work

Systems still running.

Every project here is either live in production or actively maintained. No decks, no concepts. Real systems with real numbers.

ApeFX — platform UI
Zeramental — character
Agents

55 workflows, not 55 people

Trigger
Fetch brief
Research
Draft
QC
Publish
55
Live workflows
30/wk
Briefs shipped
99.2%
Run success
6 min
Avg cycle
Pre-AI Proof2022

Klasha

20,000 to 280,000 users in under a week. Head of Marketing at a cross-border payments platform — before Fatboy, before any of this was AI.

14x
User growth in a week
1,700+
Merchants signed
20%
Avg. MoM growth
150K+
Transactions processed
Klasha — output sample

What was built

Two-track campaign — B2C led with the virtual-card story and a referral mechanic tuned to local consumer psychology, B2B ran an education-first outbound motion, one shared messaging framework across both.

PR across Nairametrics, Businessday, and regional tech press.

Payment Links positioned as international revenue without a dev team or weeks of integration.

Gaming CommunitiesActive

Bloxflip

A presence built from scratch specifically for gaming communities — Bloxflip, Gamegrid, and Bloxgame, one umbrella. Most agencies don't actually understand how these communities work.

Bloxflip — output sample

What was built

"Kyle gets gaming communities in a way most marketers just don't. He built our presence from scratch and the numbers showed it." — Shane, Founder

Fractional CMO + AI SystemsSwitzerland

Creatio

Marketing leadership and the AI systems build behind it, in one engagement — lead qualification, content, outreach, and automated property valuation built on real land indexing data.

Creatio — output sample

What was built

Automatic lead qualification and scoring.

AI-generated content built into the marketing motion.

Automated outreach on a lead-stage cadence.

Automated property valuations from real land and property indexing data.

AI PlatformOwned + Built

ApeFX

An AI cinematic content platform built from scratch. Product, infrastructure, brand, model integrations, and the mass automation pipeline producing every image and video on the platform.

Live
Real, paying users
Solo
Built by one person
8+
Model integrations
100%
Automated pipeline
ApeFX — output sample

What was built

Full-stack platform — Next.js, Supabase, Vercel. Auth, payments, API routes, consumer scale.

Mass automation pipeline — n8n workflows handle character batches, generation queues, QC passes, CDN upload. No human per asset.

Multi-model routing — FAL, Replicate, ByteDance Seedance, Kling, Higgsfield, Google Veo. Routed by task and quality target.

Character development — sheets + turnarounds: end-to-end concept → character sheet with turnarounds → generation → QC → delivery.

Automation InfrastructureLive

Fatboy Studios — Automation Fleet

55 live n8n workflows covering blog production, design pipelines, client portal data sync, error handling with circuit breakers, Upwork lead scoring, and ad generation. 65 AI agents sharing a Qdrant vector context store.

55
Live workflows
13
Custom agents
Qdrant
Vector context store
Daily
Runs unattended
Agents

55 workflows, not 55 people

Trigger
Fetch brief
Research
Draft
QC
Publish
55
Live workflows
13
Custom agents
Qdrant
Vector context store
Daily
Runs unattended

What was built

n8n fleet — 55 active workflows. Blog pipeline (research → draft → design → publish), portal data sync, error escalation, lead scoring, circuit breakers.

65 AI agents — CTO, CMO, PPC, design, content, social, competitor, client report. All wired to MCP servers.

Context stack — Qdrant vector store. Per-client collections. All agents read and write state. Context survives session restarts.

Observability — Grafana local dashboards, Sentry on the web platform, Uptime Kuma monitoring 15+ services.

AI Film PipelineIn production

Zeramental — Character Production Pipeline

Dark fantasy AI production project. End-to-end character pipeline: concept, character sheets with turnarounds, dual-reference injection, multi-model image generation, and video sequencing across Kling 3.0 and Seedance 2.0.

NB2
Primary image model
Kling 3
Video generation
Sheets
Character turnarounds
Automated
Brief to CDN
Zeramental — Character Production Pipeline — output sample

What was built

Character consistency — character sheets with multi-angle turnarounds per character. Dual reference images + SAME anchor mechanic for lighting and shot consistency.

Image generation — NB2 (thinking_budget 1024) + GPT Image 2 as production models. Photography-language prompt vocabulary.

Video production — Kling 3.0 Omni + Seedance 2.0 via direct ByteDance API partnership. Multi-shot sequencing with 180° rule and blocking spec.

Pipeline automation — generation → QC → CDN delivery via n8n. Character brief → rendered output without manual intervention.

Working on something similar?

If the brief fits any of what you see above, reach out directly. I respond fast.