Observability’s Sixth Sense: Detecting Anomalies in Metrics
summary
Shows a live walkthrough on real metrics stored in Victoria Metrics and visualized in Grafana and MicroK8s, comparing a basic online model and a seasonality-aware model (production-ready). Demonstrates anomaly counts, consecutive anomalies (streaking) to collapse noisy alerts, using a streak threshold of four to cut hundreds of pings to a handful, exposes y, y_hat and upper/lower bands, and ships a GitHub workshop with reproducible queries and dashboards.
AI-written summary · about
chapters (9)
- 0:00Introduction and motivation
- 3:15What is anomaly detection
- 8:14Time series fundamentals
- 14:57Anomaly types and models
- 16:01Demo: Logs and traces
- 24:03Demo: Metrics and seasonality
- 26:31AI-powered observability assistant
- 30:13GitHub workshop and resources
- 34:57Key takeaways and closing
related talks
35mObservability’s Sixth Sense: Detecting Anomalies in Metrics
35mObservability’s Sixth Sense: Detecting Anomalies in Metrics
28mThe Sixth Sense: Finding “Dead” Metrics and Silent Alerts in Your Monitoring
34mAnomaly Detection in Time Series from Scratch Using...
38mWatch Everything, Watch Anything: Anomaly Detection
41mMetrics Applied
31mFirst Day Foresight: Anomaly Detection for Observability
26mImproving How We Observe Our Observability Data: Techniques for SREs