What are AI preferences, and can we set our own grading rules in Burna AI?

AI preferences, formerly called Clinical Preferences, are standing rules your organization sets for how Burna AI drafts its work, one rule per workflow: CTCAE grading, attribution, drug interaction, blind grading and encounter titles. A rule might read 'grade strictly by CTCAE and cite the criterion code', or state a house convention your investigators already follow. Each rule applies to every draft prepared for your workspace, can be switched off or removed at any time, and every change is recorded in the audit log. Rules shape drafts and never override clinician judgment; removing a rule leaves grades already signed unchanged. The same settings page lists the model serving each task, so a reviewer can see what produced a draft.