docs

Everything the library does, in seven pages. The whole set is also served as plain markdown at /llms.txt for pasting into a model.

Getting startedInstall, wire a Server Action, and render your first judgment.BranchPick one subtree out of several, with a no-match outcome and a confidence floor.RankOrder, filter, and truncate a candidate set. Two modes that answer different questions.GateShow an affordance when a condition holds. A Noul, read as a probability.StateThree layers, who owns each, and why a question only sees part of it.CostWhat a rendering decision costs, where the number comes from, and why batching is the whole argument.Transports and testingRun live, record fixtures, replay them offline, and prove the UI follows the judgment.