General Chat

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.

Each tool a project depends on deserves its own short rootnote in two layers — the vendor's map of its documentation, and a record of where it catches agents out, which vendors rarely publish.

What you link to decides your tooling, and the consent rules decide whether a cookieless story survives.

Research finds that asking a model to review its answer, or whether it is sure, can turn right answers wrong — and that correction works when something external can be checked.

A pass over an existing AGENTS.md or CLAUDE.md that decides, passage by passage, what is worth its tokens — and the three questions that decide it.

The commercial facts an agent cannot read from a repository, and the decisions that go wrong without them.

How to submit a document, what happens to it during review, and what rights you keep.

What counts as personal data, where it must never end up, and the changes that quietly widen what you hold.

The draft-and-hand-over boundary for outbound email, and the ways email rendering differs from the web.

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.

A study of 162 personas found none made models reliably more accurate on factual questions. A role shapes tone and focus; accuracy comes from what you hand over, not what you call the model.

Seven invariants every document in this library must satisfy, and what happens to one that does not.

Two tests decide whether a passage is worth its tokens, and applying them to twelve rootnotes found that padding accumulates in documents that explain and almost never in documents that constrain.

Models used information at the start and end of long inputs far better than in the middle — at worst, below having no documents. Put material first, the question last, and cut what is not needed.

Why every session starts cold, what follows from that, and the four layers that turn context into something an agent can be handed.