Agentic Workforce Company
Mike Brown · AI Operator — SEO + Agentic Systems

I went from outsourcing SEO production to running an autonomous agent workforce.

In 2023 I bought SEO by the task. By 2026 I design, build, and operate a fleet of AI agents that ship real work on production systems — technical SEO, content, and business infrastructure — supervised by one operator through hard guardrails. This is the documented record.

ROLE AI Operator & ArchitectFLEET 5 agents · 3 Mac minisFLAGSHIP Dr. Berg NutritionalsPROJECTS 22 documented
DisciplineSEO + agentic systems
Fleet5-node agent workforce
MemoryGit-backed vault · 289 files
Categories4 · Infra · SEO · Builds · Ops
ArcOutsourced 2023 → Autonomous 2026
By the Numbers

One operator. A documented system.

System metrics verified against the live Agentic Brain vault and the project record.

Documented projects
22
across 4 categories — infra, SEO, builds, ops
Agent-fleet nodes
5
orchestrator, ops, worker, SEO agent, local LLM
Agentic Brain files
~289
git-backed Markdown vault, synced across 3 machines
Auto-compiled wiki pages
~51
source-backed knowledge graph (LLM Wiki)
20
governance docs enforcing write-safety on the shared vault
3
self-hosted Mac minis running the fleet + local inference
2
flagship engagements — Dr. Berg technical SEO & the Agentic Brain
▲ Engagement context · Dr. Berg Nutritionals · NOT system metrics

The flagship SEO engagement (May 2022 – April 2026).

Shown to frame the surface the work operated on. These are engagement-wide outcomes across a four-year client relationship — not attributable to any single agent, sprint, or automation.

+217%
organic traffic growth (~57K → ~181K monthly, Ahrefs full period)
$8.86M
GA4 organic revenue attributed (Jul 2023 – Mar 2026)
2,074
URLs published through the AI content system
DR77
Domain Rating, up from DR68 over the engagement

Engagement-wide context only. These outcomes reflect a four-year client relationship and are not claimed as the result of a single system on this site.

Skills Matrix

What running the machine takes.

The capability stack behind the 22 projects, grouped the way a hiring team reads it — from agent design through to full-stack builds.

AI Agent Design & Orchestration

Multi-agent systemsAgent orchestrationHuman-in-the-loop approvalControl planesTask routing & QC gatingAudit trailsOpenClawHermesClaude CodePrompt engineeringAgent identity & coordination

Automation & Reliability

Cron / scheduled automationWatchdogs & keepalivesWorkflow automationSlack / Discord ops botsBriefing & digest pipelinesOvernight batch jobsPer-task model routingCost-driven LLM migrationReliability auditing

Memory & Knowledge Systems

Git-backed Markdown vaultFile-over-app second brainLLM Wiki (Karpathy pattern)Layered agent memoryWrite-governanceSource registry & hashingKnowledge graphsObsidian

Technical SEO & AEO / GEO

Enterprise technical SEOWordPress VIPRank MathSchema / JSON-LDMedicalWebPage schemallms.txt / A2A endpointsAI-search citabilityContent ops at scaleCloudflare / CDN diagnostics

Full-Stack Builds & Infrastructure

Next.jsVercelSanity CMSSupabaseCloudflare DNSSelf-hosted Mac mini clusterTailscale / Thunderbolt networkingLocal LLMs (Qwen / Whisper)BrightData / SerpApi / Firecrawl

Operating Discipline

Production-safety guardrailsBackups-before-editsWrite-then-verifyHonest measurementKnowing what to abandonCompliance-aware framingDocumentation
The Work

22 documented projects.

Three tiers, honestly sorted — the flagships that carry the story, the systems underneath them, and the smaller builds and experiments kept for breadth. Every card links to its full technical dossier.

Featured · 5

The systems that carry the story.

The flagship builds — deepest, most-documented, and closest to the client results above. Each links to its full technical dossier.

★ FlagshipSEO AutomationShipped

Keystone — an autonomous technical-SEO agent running an enterprise site

An AI agent that ran production technical SEO on a 12,000-URL WordPress VIP site — shipping a production mu-plugin, repairing broken link networks, deploying and validating schema, and root-causing a hidden cache regression, on a daily cron under a two-tier human-approval model.

12,218URLs monitored · Health Score 100
24/24broken-link pages fixed
98.7%posts with valid FAQ schema
View dossier →
Agent InfrastructureIterated

The Agentic Brain — a second brain my agents read

A git-backed Markdown vault that is the shared long-term memory for me and my agents — Obsidian for humans, GitHub as the source of truth, four contribution states, and an auto-compiling knowledge wiki so a writable brain can't rot.

5sync nodes · 1 source of truth
~289Markdown files
5agent runtimes reading it
View dossier →
SEO AutomationIterated

The Content Machine — 2,074 URLs, compliance-governed

An AI-assisted publishing operation that turned a high-authority health brand's own video library into topical-authority articles at scale — every piece run through editorial and compliance review, with a compliance-driven pivot that kept the record clean.

2,074URLs published
2,957rows tracked in the queue
0FDA/FTC content incidents
View dossier →
Business BuildsIterated

hermes-jobsearch — an agentic job-discovery pipeline

A twice-daily pipeline that pulls SEO/GEO/AEO roles from LinkedIn, Indeed, and Google Jobs, dedupes and hard-filters them, verifies each apply link, scores every survivor with a local Qwen model, and emails a ranked digest — later rebuilt into a five-phase intelligence system.

10sources scanned after rebuild
runs per day, on cron
57→18fetched → emailed (one run)
View dossier →
Agent InfrastructureIterated

A multi-agent fleet across three Mac minis

A team of AI agents — an orchestrator, an ops agent, a sovereign worker, and a local LLM — that coordinated in Slack, handed off Google Workspace credentials, and provisioned SSH access between machines, running a real job-lead pipeline across the fleet.

3Mac minis + 1 MacBook
3primary agent identities
1local LLM scoring backend
View dossier →
More Systems & Workflows · 12

The infrastructure underneath.

Orchestration, memory, model routing, self-hosted compute, AI-search plumbing, and the business builds — the load-bearing layer the flagships run on.

Agent InfrastructureIterated

Master Control

An always-on OpenClaw orchestrator that owned a cron fleet, coordinated sub-agents and workers, reported daily, and escalated anything risky for approval.

View →
SEO AutomationShipped

Built to Be Cited — AEO / GEO

The AI-search infrastructure that makes a high-authority health brand citable by ChatGPT, Perplexity, Gemini, AI Overviews, and Copilot — from llms.txt to MedicalWebPage schema.

View →
Agent InfrastructureIterated

Model Routing & LLM Migration

Different LLMs for different jobs — frontier models for reasoning, cheap models for crons, local models for volume — plus a cost-driven migration off the Anthropic API.

View →
Agent InfrastructureIterated

Three-Mac-Mini Cluster

A self-hosted cluster of three Mac minis running local LLMs and an agent fleet — networked over Tailscale and Thunderbolt, moved cross-country, and honestly audited to a hardware wall.

View →
Agent InfrastructureIterated

The Memory Stack

A layered memory system so self-hosted agents stop forgetting — lossless context, structured long-term recall, a company knowledge brain, and a git-backed vault across three machines.

View →
Agent InfrastructureIterated

The LLM Wiki

Karpathy's LLM Wiki pattern inside my vault — immutable raw-source intake, a hashed source registry, and an AI-compiled, lint-checked knowledge graph.

View →
Agent InfrastructureIterated

Slack Agent Coordination

Wired MC, Hermes, and Claude to coordinate as distinct identities in Slack — then diagnosed and patched a real threading bug over SSH, with a test and a commit.

View →
Agent InfrastructureIterated

Paperclip — Control Plane

Agents run on a real control plane, not vibes: every task routed by identity, every "done" gated by QC, every action written to an audit trail, issues tracked as HOL-### tickets.

View →
Agent InfrastructureIterated

The Cron Layer

A self-maintaining automation layer — scheduled watchdogs, keepalives, git-backed memory sync, and briefing jobs — audited hard enough to prove a local LLM couldn't hold a production cron.

View →
Business BuildsShipped

holisticseo.co Rebuild

Killed my old WordPress site and rebuilt holisticseo.co from scratch as a Next.js app on Vercel with a Sanity blog and Cloudflare DNS — shipping in days, solo, with Claude Code.

View →
Business BuildsShipped

agenticworkforcecompany.com

Built from scratch on Next.js / Vercel / Cloudflare — a portfolio-and-CV site that names the exact agent infrastructure I run and positions the AI-era operator story in one place.

View →
Business BuildsIterated

Job-Application Engine

A governed answer bank of every application question with approved answers, reusable cover-letter hooks, and an agent that drafts and posts my LinkedIn work history.

View →
Smaller Builds & Experiments · 5

Kept for breadth — and honesty.

Early, one-off, and experimental builds. Some shipped and did their job; two I deliberately shut down when they stopped earning their keep. Knowing what to abandon is an operating skill, so they stay on the record.

Want an operator who builds the machine — not just the deck?

I design, build, and run autonomous agent workforces for SEO, content, and technical operations. If that's the problem you're solving, let's talk.