Featured dispatch
Dispatches
The company I built without a payroll
Twenty-four people work here and none of them have bank accounts.
Thinking
Long-form exploration into the intersection of human agency and machine intelligence. Every argument is grounded in the operating system we are building in public.
Before a company adds AI agents, it needs clear work loops, permissions, memory, receipts, and human escalation paths.
In agentic product work, a PRD should be evidence for decision-making, not a static plan pretending the future is known.
The AI-native org chart is not just people and roles. It is humans, agents, systems, authority, memory, and receipts.
Chatbots can answer, draft, and summarize. Companies need AI systems that can move work through real operational loops.
An agent company still needs a human CEO. The job changes from carrying tasks to defining judgment, authority, and risk.
AI agents need receipts because useful autonomy depends on visible evidence, not trust in a black-box action.
Most workflow systems know a task was sent. The next generation has to know it was received.
An AI-native company is not a normal company with chatbots attached. It is a company designed around AI as an operating layer.
Working with agents does not reduce thinking. It forces better thinking, clearer direction, and sharper judgment.
A dispatch from the agent memory layer: what it is, what we broke, what we built, and why streaming agent work changes everything.
Twenty-four people work here and none of them have bank accounts.