AI and automated processing

A deploy-wide kill switch and audited owner/admin workspace controls can disable all AI, Knowledge Intelligence AI, or behavioural-intelligence AI. Enforcement occurs on server service boundaries.

AI providers receive the context assembled for the requested feature. Beetl requests disabled response storage, bounds output sizes and timeouts, and separates untrusted content from instructions. This request setting does not guarantee zero provider retention; monitoring records and other provider-held data depend on the applicable terms and settings.

Generated content is a draft or recommendation. Publication and governed changes remain separate, permission-checked actions.

Feature records retain provider/model, prompt or schema versions, source-version identifiers, token counts where returned, timestamps and outcomes. Assistant questions follow the workspace AI-interaction retention period; generated answers are not stored in that interaction record. Writing and learning features may separately retain generated drafts and provenance under their content lifecycle.

Provider training, abuse-monitoring exceptions, processing location and deletion commitments must be verified against the current provider agreement before customer data is enabled.