Building an AI System That Works for You

Chuck Blake // ERA // March 2026

Meet Gomez.

My AI chief of staff. Lives on a Mac mini. Has opinions.

Built on OpenClaw — an open source local AI agent platform
Connected to Telegram, my calendar, my code, my tasks
Painful to build. It did not go well at first.

Gomez

Building a System, Not Just Using a Tool

The model is a starting point. What you add is what makes it yours.

You install OpenClaw and you have a model — a commodity
Then you give it a soul: identity, personality, preferences, knowledge
Every customization turns a generic harness into something uniquely yours

The model doesn't know who you are. You have to tell it. That's the work — and that's the moat.

Three Ways to Build That System

Not a framework. Just what's been working.

Memory
Context
Principles

1. Memory

Give your AI a memory it can rely on

Identity, errors, long-term memory, daily log
Semantic search via local vector DB (Mem0 + Qdrant)
Key insight: this is YOUR thinking, not the model's

The agent wakes up fresh every session. The files are the memory.

How Memory Works

One portable brain

EVERY SESSION

Daily Log

Raw notes — what happened, what was decided

AS IT HAPPENS

errors.md

Mistakes logged in real time. Don't repeat.

STABLE

IDENTITY.md

Who I am, how I communicate, hard rules

→

WEEKLY DISTILLATION

MEMORY.md

Curated long-term memory — decisions, patterns, preferences

ONGOING

Mem0 + Qdrant

Semantic vector search — finds relevant context by meaning

↓

EVERY BOOT

Agent loads context

Identity → errors → long-term memory → today's log → semantic search

Wakes up knowing who it is and what matters

Example: Memory

        
📌  SECTION
Every session, Gomez queries his local vector DB with the
session topic. These are memories retrieved before any
conversation started.
⚙️  COMMAND
python3 mem0_session_start.py "ERA presentation"
📤  OUTPUT

          • Giving a presentation this week for ERA about OpenClaw

          • Found value in reflecting on the work and what transfers

          • Stores presentation files in master branch of chuckblake.github.io

          • Hates Slack

          • Uses GitHub

          • Never builds PPTX — always edits HTML directly for presentations

2. Context

Organize your personal context into a searchable vault

Curated context (your vault, your errors, your preferences) gets your output
Build a personal knowledge base — notes, highlights, decisions
Your context is the moat.

What's In The Vault

An Obsidian knowledge base — personal, structured, searchable

📁 People

Contacts, bios, relationship notes, birthdays

📁 Journal

Daily logs — what happened, what was decided

📁 Decisions

Architectural and product decisions with rationale

📁 Health

Sleep, exercise, mood — logged daily

📁 Meetings

Notes, action items, follow-ups

📁 Knowledge

Ideas, research, reading notes

📁 Projects

GetMusic, SonicSift, IndieCrates — context + status

📁 Readwise

Highlights from books, articles, podcasts

🔍

QMD — the entire vault is indexed and vectorized. Hybrid search: keyword + semantic. Ask a question, get the right note. bash qmd-search.sh query "What is Murat's degree in?"

This is not a notes app. It is the context layer that makes every AI interaction personal.

Example: Context

        
        
        
      
📌  SECTION
Personal knowledge vault — looking up a contact in
chuck-vault. Same question, every time: if I onboarded
a new assistant tomorrow, what would they need to know?
That's what goes in here.
⚙️  COMMAND
search chuck-vault → "What is Murat's degree in?"
📤  OUTPUT

          MS Computer Science — Neural Networks + Machine Learning.
ERA co-founder. 400+ investments since 2011. $10B+ portfolio.
Chuck is presenting to him on March 27.
        

3. Principles

Scale your taste, not your attention

Most people direct every AI interaction individually
Principles embed your judgment into the system itself
You stop being in every loop — your standards are

The bottleneck used to be execution. Now it is judgment. That is the right problem to have.

What A Principle Looks Like In The Repo

CLAUDE.md — committed to git, read by the agent every session

THE PRINCIPLE (in CLAUDE.md)

# Architecture

API-first: any functionality that exists
in the UI must also exist in the API.
No UI-only features.

All new endpoints require RSpec tests
before merge.

CHUCK ASKS: "Add bulk tag filtering to search"

Agent's plan:

Step 1: Add GET /api/v1/tags/filter
Step 2: Write RSpec tests
Step 3: Build UI against the API

Chuck never mentioned the API.
The principle did.

Write it once. Commit it. Every agent that touches the repo inherits your judgment.

The Model Is Replaceable. The System You Build Around It Is Yours.

The model is a commodity. What you build around it isn't.

Everyone has access to the same AI — GPT, Claude, whatever comes next
Nobody else has your memory, your context, your judgment in the system
That gap compounds. Every skill you build, every correction you log, every principle you embed — it widens.

These ideas aren't OpenClaw-specific. Build your memory in files. Build your context in a vault. Build your skills as text. Any platform that reads them inherits your system.

chuckblake.com/presentations/getting-ai-to-work-for-you/

Find Me

Website: chuckblake.com
X: @chuckblake
LinkedIn: /in/chuckblake
Slides: chuckblake.com/presentations/getting-ai-to-work-for-you/