← Back to Agents

Personal Systems

Level 1: How I orchestrate AI agents for my own productivity

The Architecture

Claude Code as Orchestrator

MCPs as Specialized Capabilities

No CrewAI. No LangChain. No complex frameworks.
Just Claude Code + MCPs + well-designed CLAUDE.md files.

My MCP Stack

Research

Firecrawl

Web scraping, search (with safety protocols)

Research

Context7

Library docs for current implementation

Data

Airtable

Structured data, CRM, tracking

Data

Filesystem

Local file operations

Comms

WhatsApp

Messaging integration (my own MCP!)

Media

ElevenLabs

Voice/audio for content creation

Media

Puppeteer

Browser automation, screenshots

Dev

IDE

VS Code diagnostics, Jupyter

Key insight: Claude Code + MCPs = Your agent architecture.
No separate framework needed—this IS the pattern.

Trust Patterns I Use Daily

READ FIRST, EDIT SECOND

Critical

Never work from assumptions about code. Always read actual files before suggesting changes.

Explicit File Staging

Critical

Never use git add . in parallel environments. Stage only the exact files you modified.

Scope Locks

High

Agents operate within defined file boundaries. Out-of-scope requests require explicit approval.

Firecrawl Safety Protocol

Medium

More than 10 URLs = script mode, not manual MCP calls. Prevents context overflow crashes.

CLAUDE.md as Orchestration

My CLAUDE.md files aren't just documentation—they're agent programming. They define:

  • Memory triggers - Short phrases that activate specific behaviors
  • Safety protocols - What agents can and cannot do
  • Trust boundaries - When to ask permission vs proceed
  • File dependencies - Exact deliverables, not vague completion states
# Example memory trigger:
"READ FIRST, EDIT SECOND, ALWAYS"
# This single line prevents hours of debugging

Want to build your own agent systems?