Claude Code Workshop · May 2026

The CEO Command Center

How a non-developer runs a marketing agency with Claude Code

0
Agents
0
Knowledge Frameworks
0
Automations
0
Weekly Review Questions
Scroll to explore

The CLAUDE.md Hierarchy

One root config. Every project inherits it. Each agent extends it with domain-specific instructions.

  • ●Identity & voice rules
  • ●Universal rules: never send without confirmation, never fabricate
  • ●Plugin profiles: web-app / coding / ceo-hub
  • ●Agent map: hub-and-spoke architecture
  • ●Accounts & integrations
  • ●Session title protocol
→

Key insight: Write it once. Every session inherits it. New agents get your voice, rules, and preferences automatically.

Here's what mine actually looks like

My actual CLAUDE.mdpatricksbuilds/CLAUDE.md
Patrick Gilbert's actual CLAUDE.md file showing identity, voice rules, agent map, plugin profiles, and universal rules

Hub-and-Spoke Architecture

The Assistant reads from everywhere. Each agent owns its domain. Hover to explore.

Assistant (Hub)

PPC Client Work

PPC Strategist

LinkedIn Content

Content Director

AMGfin

CFO

Roger

Business Development

Iggy

Front-End Builder

PSEO

SEO Content Factory

NANN

Book Project

About me

Voice Profile (291 lines)

⇄

Spoke-to-spoke flow: Roger (research) feeds directly into Iggy (site builds). The Assistant orchestrates but doesn't bottleneck.

Knowledge System

Your AI gets smarter over time, but only if you build the feedback loop.

Frameworks (6)

Reusable mental models for recurring situations

●
Client Strategy Principles — Core principles for managing client relationships
●
Strategy Pivot Framing — How to frame strategic pivots to clients
●
Client Persuasion Playbook — Techniques for guiding client decisions
●
AI Services Sales Playbook — Selling AI-enhanced services to prospects
●
Creative Quality Threshold — Standards for ad creative approval
●
COMPEL Business Model Evolution — Framework for business model iteration

Patterns (6)

Observed behaviors codified from experience

●
Client Personality Read — Identifying client communication styles
●
Difficult Client Escalation — De-escalation and resolution patterns
●
Pricing Negotiation — How Patrick handles pricing discussions
●
Team Transition — Managing account manager transitions
●
Dormant Warm Intro Revival — Re-engaging cold leads with warm touchpoints
●
Fact-Checking Claims — Verifying data before client-facing use

Playbooks (2)

Step-by-step protocols for specific workflows

●
Meeting Prep Protocol — Step-by-step meeting preparation workflow
●
Client Email Draft — Email drafting with voice matching

Decisions (3)

Past decisions with reasoning preserved

●
Ben Lee Transition — How the team transition was handled
●
Monday Renegotiation — SaaS contract renegotiation approach
●
Philly Office Sublease — Real estate decision and reasoning

Voice Profile

291 lines from structured interviews. Captures tone, beliefs, phrasing patterns, and preferences. Referenced by every content-producing agent. You don't prompt for voice. You document it once and every agent inherits it.

The Learning Loop

↻Learning LoopWeekly ReviewAnswersKnowledge EntryFuture Sessions

Weekly Review generates answers. Answers become knowledge entries. Knowledge entries inform future sessions. The cycle repeats.

Automated Workflows

It runs while you sleep. You reply from your phone.

📥

Meeting Ingest

Every 2 hours

Pulls Gemini notes from Gmail, converts to markdown, routes to client folders

💻

Command Listener

Every 15 min

Reads Patrick's Slack replies in #pg-agents, routes commands to the right agent

☀️

Morning Brief

Daily 8:00 AM

Calendar + unprocessed transcripts + open items synthesized into #pg-agents

📡

Intelligence Scan

Weekly Monday 7:30 AM

Scans email and Slack for new entities, emerging patterns, and opportunities

#

pg-agents

Central communication bus

All agents post here. Patrick replies from his phone. Commands get routed to the right agent automatically.

process [client]Run transcript optimization
prep [client]Get meeting prep
status [client]Quick status pull
draft [topic]Queue a LinkedIn post
yes / noApprove or dismiss queued actions
📱

Reply from anywhere. The agents process your commands. No laptop required.

The Friday Ritual

15 minutes on Friday. The AI gathers context. You just answer.

Weekly ReviewFriday 4:00 PM
1

What was the single most important thing that happened this week?

2

Which client got better this week? Which got worse?

3

What decision did I make that I want to remember in 6 months?

4

What did I learn this week?

5

What's still nagging me that I haven't dealt with?

6

Where did I spend time I shouldn't have?

7

What are the 3 things that actually matter next week?

How it works

1

Auto-gathers context

Before asking anything, the AI pulls your calendar, open action items, recent transcripts, and Slack threads from the past week.

2

7 questions, conversational

Asked one at a time. Each builds on the last. Short answers are fine. The AI captures nuance.

3

Writes to Obsidian

Structured weekly review saved to Daily/Weekly/ with decisions, learnings, and next-week priorities.

4

Offers knowledge promotion

"I noticed a pattern in how you handled the pricing discussion. Want me to save this as a framework?" Your choice.

Your Starting Point

You don't need 8 agents on day one. You need one prompt.

How this system was born

I watched a YouTube video about someone running their business with AI agents. I didn't understand the architecture. I didn't know what CLAUDE.md files were. I didn't have a plan.

I just copied the video transcript, pasted it into Claude Code, and said:

“Here's a transcription of a video. I want this setup. Organize all my files so I can manage a group of sub-agents through one single assistant agent. Build this for me.”

That's it. Claude created the folder structure, wrote the CLAUDE.md files, set up the hub-and-spoke architecture, and explained how to use it. Everything you've seen on this page grew from that one conversation.

You don't need to understand the architecture first. You just need to tell Claude what you want and let it build the scaffolding.

1

Build Your Agent Architecture

expand

Open a new Claude Code session in an empty folder. Paste this prompt. It creates your root CLAUDE.md, an Assistant hub, a knowledge system, and two starter sub-agents customized to your work.

2

Extract Your Voice Profile

expand

Open a new Claude Code session. Paste this prompt. It runs a 100-question interview that captures the DNA of how you think and write. The output is a voice profile every agent can reference.

3

Customize your CLAUDE.md

expand

The bootstrap prompt creates a starter. Now make it yours. Add your rules, your preferences, your hard nos. Here's the anatomy of a CLAUDE.md file.

4

Build your knowledge folder

Document your frameworks. Record decisions with reasoning. The AI compounds over time.

5

Add your first automation

A morning brief or meeting ingest. Something that runs without you. You'll never go back.

Context is the skill, not prompting.

The best prompt is the one you never have to write twice.