These stale when the tooling changes, so they record the tool and version they were tested against.
What an agent may change in a design system unattended, where it must stop, and how to tell a problem of taste from a problem of structure before spending a day on the wrong one.
The one rootnote that contains no instructions and no content, only addresses — and why each entry should name the decision at which it becomes relevant rather than the activity it describes.
What an agent may do unattended in a research project, where it must stop, and why uncertainty has to survive contact with it.
What an agent may write unattended, where it must stop, and the two failures that are specific to prose — inventing detail to finish a sentence, and not knowing what you have already said.
The conformance level, what gets verified and how, and the failures an agent introduces without noticing.
The exact name, the claims the product never makes, and how other companies' names and marks may be used — brand decisions an agent cannot infer from the code.
The commercial facts an agent cannot read from a repository, and the decisions that go wrong without them.
What counts as personal data, where it must never end up, and the changes that quietly widen what you hold.
Why an agent drifts a visual language one plausible value at a time, and the rules that stop it.
A linked set of documents with defined sections and relationships, rather than one long file that narrates the code.
Voice, mechanics and error-message rules, and why inconsistent terminology costs more than any single bad sentence.
Why concatenating a sentence breaks translation, and the assumptions in code that only hold for one language.
Which licences may enter the project, what even permissive licences oblige you to ship, and where code copied from anywhere — including generated code — has to come from.
Stop the bleeding before diagnosing, record while acting, and the autonomy rules that matter most when they are under pressure.
The rootnote a research project needs an agent to read before it starts, and the dead-ends record that is the most expensive thing in any project to rediscover.
Where people get help, which versions are supported, and what an error message, a log line and a diagnostic bundle must and must never contain.
What may be run without asking, what must stop first, and how to report what actually happened.