In freemansoft/Flutter-AdaptiveCards a demonstration Dart chat server hands a question to a local Ollama model, asks for the answer as Adaptive Card JSON, and a Flutter client app renders the reply. Everything below is an attempt to make that card generation more reliable and more faithful to what was asked. The figures are transcribed from ModelBehavior.md , a lab notebook in that repository. Terms used in this article The first two describe the ledger, the rest name what the levers changed and how each was scored. Probe and flag names are the repository's own. Term What it means here Lever One change tried against the card failures, recorded in the notebook's tuning ledger with its outcome and evidence. Fourteen are counted here. Kind The layer of the system a lever touches: context assembly, meaning what precedes the question in the mes...