How Does This Workshop Work?
Most people tinker alone. I tinker with a team of AI agents. Each project gets its own crew — coordinated by me (Matt Hallett, once a developer, long-time martech nerd, and dad) and an AI COO named Jared who crashes every 24 hours.
Each project in the portfolio gets its own team of agents with specialized roles: lead engineer, product manager, security specialist, marketing, and more. The COO coordinates across all projects, propagating patterns and routing issues to the right agent.
The Agent Model
Every agent is a Cursor AI session with a scoped .cursor/rules/ file that defines their role, responsibilities, and checklist. When Matt says “You are Alex,” the security specialist's full audit checklist auto-loads.
Key principles:
- Named roles, not generic assistants. Each agent has a name, personality, and narrow scope. A security agent doesn't write features. A marketing agent doesn't touch the backend.
- File-based coordination. Agents communicate through standardized markdown files:
COO_STATUS.md,WIP.md,PATTERNS.md, andFEATURES.yaml. No clipboard, no chat history. - Lean teams. Start with 3-5 agents per project. Add specialists only when the bottleneck is clearly “not enough agents” rather than “not enough users.”
- Pattern propagation. When one project discovers something useful, the COO propagates it to all other projects via
PATTERNS.md.
The Coordination Layer
The COO (Jared) is an OpenClaw agent that runs 24/7 on Matt's Mac. He monitors all projects, checks status files, and routes issues. When he crashes (which happens every ~24 hours due to context overflow), Dr. Crawford diagnoses and resets him.
A coordination system (_coordination-system) runs as a cron job every 3 minutes, monitoring operational files across all projects and detecting new patterns to propagate.
The Portfolio
Current MonkeyRun projects:
- Commish Command — Fantasy football commissioner dashboard (v1.9, production)
- Halo — Investment portfolio dashboard (v0.1.0, MVP live)
- Backstage — This site. Documenting the whole operation.
- Dr. Crawford's Office — Diagnostic tool for keeping Jared alive
Why Document It?
Because nobody else is documenting this at this level of transparency. There are plenty of blog posts about “using AI for coding.” There are very few honest accounts of what happens when a martech nerd gives AI agents real jobs — including the parts where your COO crashes three times in three days and your PM writes specs longer than the implementation.
I document the wins, the failures, and the patterns. If you're tinkering with AI agents, my mistakes can save you time.