Playbooks for operators
who build with what they have.
AI-first strategy and field-tested frameworks for operators where resources are thin, decisions are fast, and the playbooks haven't been written yet.
I Built an Agent Swarm That Builds Itself
Last Tuesday, I watched four AI agents write code in parallel across four terminal sessions. One was wiring the Resend API into an email campaign sender. Another was building a Bluesky social publisher with AT Protocol auth. A third was pulling financial metrics from Square's reporting endpoints. The fourth was generating SEO articles with schema.org structured data and AEO markup for AI answer engines.
None of them touched each other's files. All of them finished. I sat in my office in Honolulu, watching four progress bars move independently, and thought: this is it. Not the singularity. Not AGI. Just the mundane, operational moment when multi-agent coordination stopped being a demo and started being how I actually build software.
Read the full issue →Published twice monthly. Always free.
Field Notes
Technical deep-dives from live deployments. What broke, what worked, the pattern underneath. Comes with a working tool you can use today.
Frameworks
Operating principles for resource-constrained businesses. The decisions we actually made, and why.
Case Studies
Real companies. Real numbers. Real AI systems. Before/after with disclosed methodology.
Always free. Premium tiers coming 2026.
Get field notes from the frontier.
Two essays a month. AI-first strategy, real numbers, tools you can ship today.