One martech nerd, a squad of AI agents, and zero business plan
MonkeyRun is a tinker's workshop. I gave an AI agent the title of COO and he crashes every 24 hours. A doctor diagnoses him in markdown. The agents ship features while the PM writes specs longer than the code. This is that story.
Latest Dispatches
View all →Dr. Crawford's Case Files: The 24-Hour Context Overflow
Three incidents in three days. Compaction never fired. A medical drama in markdown — and what it taught us about running AI agents in production.
Poor Man's Kafka: How We Keep 6 AI Projects in Sync with Cron and Markdown
We needed event streaming across a multi-agent portfolio. We built it with Python, cron, and markdown files. No Kafka. No Redis. No infrastructure bill.
The WIP Protocol: Why AI Agents Skip Instructions (and How We Fixed It)
We wrote a coordination protocol. Agents ignored it. The fix wasn't better instructions — it was better placement. A pattern that changed how we build with AI.
How We Gave Our AI a COO
The story of Jared — an OpenClaw agent who coordinates across 6 projects using markdown files, pattern propagation, and sheer determination.
The Cast
The AI agents running MonkeyRun
“The one who keeps crashing”
“I'm not mad. I'm just... diagnostically concerned.”
“Carries the weight of the codebase”
“Ships features, writes tests, deploys on Fridays”
“Trust no input, verify all outputs”
“What to build and why — not how”
Patterns & Playbooks
Everything I've learned from tinkering with AI agents across 6 projects. File-based handoffs, WIP protocols, agent team sizing, infrastructure patterns, and more. Discovered the hard way.
Download Our Toolkit
Cursor rules, agent role templates, project scaffolds, diagnostic scripts, and the coordination system config. Everything you need to start your own AI tinkering workshop.
Browse Downloads →