> ## Documentation Index > Fetch the complete documentation index at: https://docs.planeconnection.com/llms.txt > Use this file to discover all available pages before exploring further. # Monitor Anomaly Detection > Use automated anomaly detection to identify unusual patterns in operational and safety data before they become incidents. By following this guide, you will review automated anomaly detections, assess whether they represent genuine safety concerns, and take appropriate action -- from acknowledgment to escalation. Anomaly Detection requires the **Safety Manager** role or higher. Anomalies are generated automatically from operational data -- you do not need to manually create them. ## Review an Anomaly ### Step 1: Open the anomaly dashboard Navigate to **Safety > Anomalies** in the sidebar. The dashboard displays flagged events with severity indicators and trend context. ### Step 2: Open the flagged event Select a flagged anomaly to view its details and the context panel showing the data trend, baseline values, and deviation threshold. ### Step 3: Assess the anomaly Determine whether the anomaly represents a genuine safety concern or a benign variation (e.g., seasonal patterns, data entry changes). ### Step 4: Take action Choose the appropriate response: * If no further action is needed, acknowledge the anomaly as reviewed. * If you want to escalate, create a safety report to enter the standard reporting pipeline. * If the anomaly relates to an ongoing investigation, link it to that investigation. ## Configure Alert Thresholds Anomaly detection thresholds can be adjusted in **Safety > Settings** to match your operation's risk tolerance and fleet size. Higher thresholds reduce noise; lower thresholds increase sensitivity. **AI suggestions are advisory only.** Per 14 CFR Part 5, all safety assessments, investigation findings, and risk evaluations require independent human evaluation by qualified personnel. AI recommendations should be used as one factor among many in decision-making, not as the sole basis for any safety, operational, or maintenance action. See [Legal Notices](/en/reference/legal-notices#ai-and-automated-features-disclaimer). ## Related Flight data monitoring that feeds anomaly detection. Set up safety performance indicators with alert thresholds. Escalate anomalies into formal safety reports. How the platform monitors and measures safety performance.