Static context vs. engineered context. The 5-layer architecture that makes your AI actually know you — and the technical details for those who want to look under the hood.
Most AI setups rely on a single system prompt that you copy-paste and hope for the best. Second Brain uses a 5-layer context engineering stack — from project instructions down to tool integrations — that runs locally on your computer and compounds over time. No cloud platform owns your context. You do.
Static Context
Engineered Context
Setup
You copy-paste a system prompt
AI builds your profile from a questionnaire
Memory
Remembers what you wrote down — forgets what it learned
Captures patterns automatically, detects decay, compounds over months
Tools
Copy data in and out of AI
AI reads Gmail, Calendar, CRM directly
Quality
Hope the output is good
Validation rubrics score every output
Maintenance
Breaks when something changes
Health checks detect decay automatically
Ownership
Locked in vendor platform
Your database, your infrastructure, your rules
This is why ChatGPT Memory, Notion AI, Cowork, and DIY setups all hit the same wall.
Personalized
not templated
Connected
not isolated
Measured
not guessed
Compounding
not static
Owned
not rented
Context engineering isn't one thing — it's a stack. Each layer makes AI smarter about you and your work.
A file at the root of your workspace that Claude reads on every conversation. Your preferences, rules, writing style, tool conventions — loaded automatically, every time.
# CLAUDE.md ## Voice: Direct, no fluff. Never use "leverage" or "synergy." ## Clients: Enterprise SaaS, 50-200 employees ## When writing proposals: Use the 3-part framework from /templates
AI learns from every conversation and stores patterns, client details, and decisions in a local SQL database with 12 queryable collections and confidence scoring. Month 1: knows your name. Month 6: knows your client's pricing objections, when the last interaction was, and which proposals need updating.
The Model Context Protocol lets AI read and act on your real tools — Gmail, Calendar, LinkedIn, CRM, Stripe. Instead of telling AI about your schedule, it reads your calendar directly. Instead of copying client data, it queries your CRM.
Reusable commands like /daily-briefing or /draft-proposal that combine multiple tools and context sources into one action. Type one command, get a complete output that would've taken 30 minutes manually.
This is where context engineering gets powerful. Hooks are shell commands that fire automatically at specific points — before a tool runs, after a file is saved, when a session starts. They don't rely on AI judgment. They always execute.
PreToolUse
Block edits on protected files
Fires before any tool runs — can prevent the action
PostToolUse
Auto-update CRM after outreach
Fires after a tool succeeds — sync external systems
SessionStart
Load today's priorities
Fires when you open Claude — inject daily context
Stop
Verify tests pass before finishing
Fires when Claude finishes — enforce quality gates
# Example: Auto-track every email send in your CRM
{
"hooks": {
"PostToolUse": [{
"matcher": "Bash",
"hooks": [{
"type": "command",
"command": "./track-outreach.sh"
}]
}]
}
}The system configures your hooks automatically. You don't write JSON — you tell it what you want enforced.
Most "AI setups" only use Layer 1.
A Second Brain uses all 5 layers working together. That's why the output quality is fundamentally different.
The Guide is a remote plugin that reads your local brain structure to give guidance. Your actual content, client data, and personal information never leave your computer. We only see which tools you call and how often — for product improvement.