Short books on building AI you can rely on
Written for people who have to make decisions about AI systems rather than train them from scratch. No prompt templates, no mathematics, no code. The mechanism, the failures it makes inevitable, and what actually reduces them.
Why AI Gets It Wrong
Understanding the machine before you build on it.
An airline was ordered to pay for a refund policy its chatbot invented. A legal brief cited six court cases that did not exist. Neither failure looked like a failure. Both read like every correct answer the system had ever produced.
This is a short book about why that happens, what it costs, and where the leverage actually is. Not prompts. Not tools. The environment you build around the machine.
- Why fluency tells you nothing about accuracy
- How language models work, without mathematics or code
- Six failure modes that look identical on the surface
- The Context Four, a diagnostic you can run in a minute
- What these tools do to the judgment of the person using them
What comes next
The first book is the foundation. The work that follows extends it into the parts that decide whether a system survives contact with real users.
The reader list
Told first when a new book is ready, alongside new writing on building AI systems that hold up in production.