Tag
#artificial-intelligence
Four Levels, Three Cliffs
Teams do not adopt AI. They climb four levels, and each step moves the context and the blast radius somewhere new. Most companies stand on three levels at once.
The Model Grades Its Own Homework
Sorting changes by risk is the right idea. Letting the agent's confidence set the class is the one input that turns every gate behind it into decoration.
Nobody Resisted
We planned for skeptics and got 1,372 skill files in eleven weeks. Notes on an AI adoption that went too well.
Every Approval Is a Missing Rule
If the architects do not write the rules the agents read, the person who writes the template does. Notes from reviewing an operating model for agentic delivery.
Turn the Sequence Diagram on Its Side
The people who can tell you a boundary is wrong were never going to read UML. Turn the sequence diagram on its side and they do not have to.
The Bottleneck Moved
AI made writing code cheap. Our squad reports show where the queue went next: to the people who have to read it.
The Model Is the Easy Part
I put an MCP server in front of a production API. The hard parts were tokens and state, not the model.
Multi-Agent Is an Org Chart
I designed a multi-agent AI system and accidentally rebuilt the org chart, failure modes included.
Probabilistic Metrics
Why the most useful numbers in our AI transformation were never in a database.
A Company of One, Staffed by Agents
Four shipping products, one person, and a field report on what AI actually changes about building software.
Diagrams Are Conversations, Not Documentation
The most useful diagram of my career was ugly, partially wrong, and deleted within a week.