Case context
Case titles, notes, task summaries, timelines, selected records, and workflow metadata relevant to the request.
Trust Center / AI Privacy
Caseflow AI features are designed to operate inside workspace, case, document, and permission boundaries. The goal is useful assistance with clear human review, not autonomous professional decision-making.
The AI path is backend-mediated. The browser asks Caseflow for an AI-assisted task; Caseflow validates access, prepares limited context, calls the configured AI provider, and returns an assistive response.
Depending on the feature and the user action, AI processing may include selected prompts, case fields, task records, document chunks, generated summaries, and operational metadata.
Case titles, notes, task summaries, timelines, selected records, and workflow metadata relevant to the request.
Selected text chunks or extracted document signals from documents the user is allowed to access.
Tenant, case, user, feature, model, token counts, redaction status, timestamps, and retention-expiry metadata.
AI output is not a final decision layer. Caseflow positions AI as a review aid for professionals who remain responsible for source verification and final use.
AI audit records focus on operational traceability, request purpose, retention expiry, and safety status rather than broad raw-content logging.
Case deletion is designed to clean up related AI chats, audit metadata, temporary processing records, and index references.
AI outputs saved into cases, reports, notes, or documents follow the retention lifecycle of those workspace records.