Ai Decisioning

Operator enables AI Decisioning across the workspace. A subset of users have previously requested data-processing opt-out under GDPR. Their events still enter the training corpus.

Filter opt-out users out of the AI Decisioning training corpus at source. Per docs, the training corpus is derived from warehouse data the operator exposes — the operator must enforce opt-out via the Model query. Document the opt-out filter as a contract.

AI Decisioning model was trained six months ago. Outcomes shift seasonally; model recommendations no longer reflect current behavior.

Schedule periodic retraining (per docs, AI Decisioning supports scheduled retraining cadence) and monitor offline metrics (predicted-vs-actual lift) for drift. Trigger ad-hoc retraining on detected drift. Document the cadence and last-trained timestamp in the campaign UI.

AI Decisioning picks per-user send times. The user's timezone is stored as UTC offset at registration; users who travel see emails arrive at 3am local.

Use the user's current IANA timezone (refreshed from recent events / device-reported timezone) per docs; never trust a registration-time UTC offset. Document timezone freshness as a Model contract. Test edge cases (DST transitions, travelers).