Automation Fleet
55 live n8n workflows. 65 AI agents across Claude and OpenClaw. A Qdrant vector context stack shared across every agent. This is the infrastructure that runs Fatboy Studios and every client engagement — daily, unattended.
Six workflow families. Every one running in production.
Blog Production (WF1)
1 primary + sub-workflowsResearch → brief → draft (Claude API) → design → image generation → Sanity publish. GEO-optimized with per-client backlink index. Min 5 images per post.
Design Pipeline
Template-swap systemDesign agent clones Figma template → swaps text + images → exports to R2. 6 QC auto-fix passes per frame before export. Gap logging mandatory.
Client Portal Sync
Per-client data feedsPortal metrics snapshots at 22:30 SAST daily. Google Ads API, GA4, GSC pulling into Supabase. Sparkline history for every KPI. 13 separate sync workflows.
Lead Scoring (Upwork)
3× dailyn8n FanHemNwkwxVtcGV. 6 GraphQL queries → Claude scoring (P1/P2/P3) → ClickUp surface with AI-drafted proposal as comment. Fully automated intake.
Social & Doublespeed
Batched schedulingContent calendar generation, Doublespeed post scheduling, image variant production. DC + Ryla retainer social automation.
Observability + Alerting
Always-onn8n health checks, circuit breakers, error escalation to ClickUp. Uptime Kuma monitoring 15+ services. Grafana dashboards for local infra.
Always-on monitoring
65 agents. Each scoped, each wired.
Every agent has a defined scope, a set of MCP tools, and access to the Qdrant context store. Context isolation is hard — each agent only reads what it needs. The 23 below run on Claude; another 34 run a parallel stack on OpenClaw.
CTO — Fatboy
Fatboy infra onlyInfrastructure, deploys, Vercel, Sentry, n8n health, Supabase migrations
CTO — ApeFX
ApeFX onlyApeFX platform deploys, incidents, costs, performance
PM
Full orgClickUp sprint sync, workflow status, daily ops, cross-team routing
CMO
Per clientMarketing strategy briefs, content direction, campaign planning
CFO
Kyle / APE AIPersonal finance, SA tax frameworks, entity-level state tracking
PPC Specialist
Per clientGoogle Ads API, GA4, bid strategy, keyword expansion, offline conversions
SEO Brief
Per clientBlog brief generation, GEO keyword targeting, AIEO content structure
AEO Specialist
Per clientAnswer-engine research, authoritative answers, schema markup
Social Brief
Per clientSocial post copy, platform-specific formatting, hook library
Design Agent
Design pipelineFigma template-swap, image generation routing, R2 delivery
Branding Agent
Per brandBrand asset variation, card injection, design-system enforcement
ApeFX Brand Designer
ApeFX onlyBrand assets and design content for the ApeFX platform
Creative Director
Per campaignMarket research, concept development, production-ready creative briefs
Image Gen Specialist
Image pipelineModel routing, production API calls, R2 storage, ClickUp feedback
Video Gen Specialist
Video pipelineModel routing, async generation + polling, R2 storage
Competitor Scan
Per clientCompetitive intel gathering, positioning analysis
Client Report
Per clientAutomated monthly reports from portal data
Data Analyst
Full orgReads Supabase pipeline data, surfaces what’s working and declining
Ads Brief
Per clientGoogle Ads copy generation, task-specific
Campaign Research
Per serviceCampaign concept development, creative direction, 3-concept output
Brand Voice Guardian
Content QCInline QA — scores drafts against brand guidelines, flags, doesn’t write
Proof Agent
Content QCFact-check, citation extraction, claim verification
Copywriter
Per pageWeb copy that converts, CRO-backed frameworks, first-principles rewrites
Vector memory that survives session restarts.
Every agent reads and writes to Qdrant. Per-client collections. Per-domain partitions. Context API on port 3457 — any agent can call GET /context/:clientId to pull relevant state before executing a task.
The difference between an agent stack that 'works' and one that operates in production is persistent memory. Without it, every session starts cold, every task restates the same context, and the system doesn't compound.
Qdrant vector store
Self-hosted Docker. Per-client collections.
Context API (port 3457)
GET /context/:clientId — used by all agents.
Ollama + Qwen local
Local LLM tier for high-volume routine tasks.
Claude API (Sonnet/Opus/Haiku)
Routed by task complexity and cost target.
Every channel, one control plane
Blog, social, ads, SEO, AIEO — all orchestrated, all observable.
Open metrics, live
Need this for your org?
Agentic systems and automation infrastructure is one of my three engagement types. Tell me what you need to automate.