Build with a little more restraint
Useful experiences can begin by asking what actually needs to be sent, stored, and run.
Thoughtful essays on prompts, models, evidence, and the decisions around everyday AI use.
Browse the notebook
An independent journal about practical, bounded AI use. We explore clear requests, useful examples, and the checks that help a generated result become working material.
Get to know usAn independent journal about practical, bounded AI use. We explore clear requests, useful examples, and the checks that help a generated result become working material.
Why we writeChoose a purpose whose result can be understood and reviewed.
Fluent output should not substitute for a check of the underlying claim.
Understand which decisions remain with the people using and designing the tool.

A fluent response can be useful without explaining how the model reached it.
Choose a low-stakes task and write what a useful output must contain. Name one check you can perform independently of the tool.