Inside AI
How it works behind the scenes. For judges, lawyers, and curious newcomers: what a model does, what it can see, why a persuasive answer can be wrong, and what courts and regulators already expect. No code.
What actually happens when you ask AI a question?
Separate the model, the application, and the evidence behind an answer.
Tokens, attention, and why wording matters
Understand what a model processes without needing the mathematics.
What uploading a document does—and does not—establish
Diagnose the gap between having a file and using all of it accurately.
Why a persuasive answer can still be wrong
Recognize the kinds of errors that polished writing can hide.
How models learn from examples
Understand parameters, loss, and why a good training score is not enough.
Why the same question can produce different answers
Understand generation settings and evaluate reasoning by its support.
Verify a work product before relying on it
Review source support and completeness in both directions.
What courts expect when you use AI
Check the rule, verify the source, and keep a record of the review.
Reading AI-assisted material from the bench
For judges and those who appear before them: what to look for, what to ask, and how courts themselves are using AI.