I build with AI. For real, in production.
Agents with roles, routing, skills and memory.
Claude Code for the orchestration. MCP to reach the tools that matter.
Real auth - SSO, SCIM - because serious software needs it.
A human approves anything public, money, or irreversible.
This is where I write about how it's built.
Why I built it
I wanted leverage without headcount. Real work done by a system I could reason about, not a pile of one-off prompts. So I built an agent OS from scratch - routing, roles, skills, memory - on Claude Code. Small enough to hold in my head, serious enough to run in production.
How it works
- Routing
- Work lands in the right place. The system knows which agent, which skill, which repo - without me routing every task by hand.
- Roles
- Each agent has a seat with a boundary. Vault editor, product reasoning, code review - defined roles, not one blob of AI doing everything and doing none of it well.
- Skills
- Repeatable playbooks encoded once and invoked on demand. Draft the post, run the audit, commit and open the PR - the work that used to need a hire becomes a command.
- Memory
- Context persists across sessions in plain markdown - facts, decisions, daily logs, three tiers deep. The system remembers, so it never starts from a blank page. This is the part most people get wrong.
Claude Code, plugins and MCP
Claude Code runs the orchestration. The repeatable work is packaged as plugins and skills, so a job that used to take a person becomes one command that any agent in the system can call.
MCP is how it reaches the real world. I build MCP servers so an AI can drive live tools directly - create records, move money, touch the systems a business actually runs on. Not a chatbot that answers. Software that acts.
When a new capability ships, I turn it into something working in days, not quarters. That gap - between a release note and a tool you can actually use - is where most of the value is, and it is the part I enjoy most.
Auth that holds up
Here is the half that makes AI software safe to hand to a business: real identity. SSO, SAML and OIDC. SCIM provisioning. Roles, seats and spend limits.
It is the plumbing nobody demos and every serious deployment needs. I build it in, because software that touches other people's data and money has to be accountable before it is clever.
A human stays in the loop
One rule I never relax. Anything public, anything involving money, anything you cannot undo, waits for a person. The agents do the work. I sign it off.
That is not caution for its own sake. Leverage without control is just a faster way to break things. The approval gate is the design, not a limitation on it.
In production
This is not a lab experiment. It runs in production - live users, real billing, real consequences. Built, shipped and maintained end to end.
I even pulled the engine out of my own setup and it stood up as a product of its own - Corey. It built its own website and wired its own checkout with barely a hand on the wheel. If a system can build and sell itself, it can do the day job. Proof, not a promise.
The writing is where I work it out in the open - articles and notes on what I am building and what it is teaching me.
Principles
- Leverage beats headcount.The repeatable work should not need another hire.
- A human stays in the loop.The system does the work; a person approves what ships. Always.
- Your stack, not mine. It reaches into the tools you already use over MCP. Not another platform to migrate to.
- Ship small, ship often. Trust is earned one real task at a time.