7 min read
Requisite Variety: Why One AI Agent Cannot Run a Company
Ashby's law explains why reliable AI operations need roles, tools, constraints, and escalation instead of one general agent.
Read post
Agents
Practical posts on turning recurring work into controlled Task Machine workflows with approvals, checks, agents on your own machines, and a history you can read.
8 min read
The Viable AI-Native Company: Stafford Beer's Five Systems for Human-Agent Teams
Stafford Beer's Viable System Model clarifies operations, coordination, control, audit, intelligence, and policy for human-agent teams.
Read post
11 min read
AI Agents for Agency Delivery
How small agencies use AI agents to prepare recurring client work while preserving review quality, context boundaries, and trust.
Read post
10 min read
How Indie Hackers Use AI Agents
A practical way for indie hackers to delegate recurring marketing, support, research, and operations while keeping control.
Read post
11 min read
How to Take AI Agents From Demo to Production
A production-readiness model for AI agents covering state, retries, permissions, verification, observability, and recovery.
Read post
10 min read
What Is an AI Agent and How Does It Work?
A practical guide to how AI agents observe, decide, act, verify results, and stop safely while doing real work.
Read post
11 min read
Which Software Development Tasks Should AI Agents Handle?
A decision framework for delegating software development tasks based on clarity, verification, blast radius, and reversibility.
Read post
7 min read
A Self-Improving Company Is a Loop You Can Trust
The self-improving company is the right idea. Without verifiers, ownership, and durable history, the loop drifts instead of improving.
Read post
6 min read
A Week Inside the One-Person Billion-Dollar Company
Sam Altman's friends are betting on a company with one employee. Here's what an actual week running one looks like.
Read post
7 min read
Botsitting Is Eating the Hours Agents Were Supposed to Save
Workers spend hours a week botsitting AI agents: feeding context, catching mistakes, cleaning up. Autonomy levels and one inbox fix why.
Read post
8 min read
Set Up an Autonomous Developer That Fits Your Workflow
A step-by-step operating model for running a coding agent through your existing tracker, repo, and review step, gated by planning and risk scoring.
Read post
7 min read
Failed Checks Belong in Your Inbox, Not Your Notifications
When an agent's work fails a check, it needs an owner, the evidence, and a next action. That is inbox work, not another alert to scroll past.
Read post