Paid Media Monitoring

1. Load two or more normalized snapshots with compatible account, timezone,

currency, metric, and attribution definitions.

1. Validate data freshness and finalization windows before comparing periods.
2. Separate expected learning, seasonality, reporting latency, and planned changes

from unexplained anomalies.

1. Evaluate pacing, delivery, conversion quality, unit economics, creative fatigue,

tracking health, policy status, and changed account objects.

1. Return observations, confidence, likely causes, required investigation, and

decision thresholds. Do not mutate the account.

1. Persist a versioned monitoring bundle and link detected failures to regression

or follow-up tasks.

Do not alert on percentage changes with trivial denominators or incomparable windows. State when evidence cannot distinguish noise from a material change.