Work/Automation Fleet
Case Study
Automation InfrastructureLive2024 – present

Automation Fleet

55 live n8n workflows. 13 custom AI agents. A Qdrant vector context stack shared across every agent. This is the infrastructure that runs Fatboy Studios and every client engagement — daily, unattended.

55
Live n8n workflows
13
Custom AI agents
Qdrant
Vector context store
Daily
Runs unattended
n8n — active workflows list
Qdrant — vector collections UI
Workflow categories

Six workflow families. Every one running in production.

Blog Production (WF1)

1 primary + sub-workflows

Research → brief → draft (Claude API) → design → image generation → Sanity publish. GEO-optimized with per-client backlink index. Min 5 images per post.

WF1 — blog pipeline workflow graph

Design Pipeline

Template-swap system

Design agent clones Figma template → swaps text + images → exports to R2. 6 QC auto-fix passes per frame before export. Gap logging mandatory.

Design pipeline — Figma template-swap output

Client Portal Sync

Per-client data feeds

Portal metrics snapshots at 22:30 SAST daily. Google Ads API, GA4, GSC pulling into Supabase. Sparkline history for every KPI. 13 separate sync workflows.

Portal sync — metrics dashboard view

Lead Scoring (Upwork)

3× daily

n8n FanHemNwkwxVtcGV. 6 GraphQL queries → Claude scoring (P1/P2/P3) → ClickUp surface with AI-drafted proposal as comment. Fully automated intake.

Upwork pipeline — lead scoring output

Social & Doublespeed

Batched scheduling

Content calendar generation, Doublespeed post scheduling, image variant production. DC + Ryla retainer social automation.

Social pipeline — content calendar view

Observability + Alerting

Always-on

n8n health checks, circuit breakers, error escalation to ClickUp. Uptime Kuma monitoring 15+ services. Grafana dashboards for local infra.

Monitoring — Grafana / Uptime Kuma dashboard
Agent roster

13 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.

CTO — Fatboy

Fatboy infra only

Infrastructure, deploys, Vercel, Sentry, n8n health, Supabase migrations

CTO — ApeFX

ApeFX only

ApeFX platform deploys, incidents, costs, performance

PM

Full org

ClickUp sprint sync, workflow status, daily ops, cross-team routing

CMO

Per client

Marketing strategy briefs, content direction, campaign planning

PPC Specialist

Per client

Google Ads API, GA4, bid strategy, keyword expansion, offline conversions

SEO Brief

Per client

Blog brief generation, GEO keyword targeting, AIEO content structure

Social Brief

Per client

Social post copy, platform-specific formatting, hook library

Design Agent

Design pipeline

Figma template-swap, image generation routing, R2 delivery

Competitor Scan

Per client

Competitive intel gathering, positioning analysis

Client Report

Per client

Automated monthly reports from portal data

Ads Brief

Per client

Google Ads copy generation, task-specific

Campaign Research

Per service

Campaign concept development, creative direction, 3-concept output

Proof Agent

Content QC

Fact-check, citation extraction, claim verification

Context stack

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.

Qdrant — vector collections + context query
Context API — per-client state overview

Need this for your org?

Agentic systems and automation infrastructure is one of my three engagement types. Tell me what you need to automate.

See services