Unleashing the Power of AI for Performance Monitoring& Anomaly Detection
summary
Compares rule-based threshold alerts with an AI/ML monitor that learns an application baseline from historical logs and metrics, detects unusual behavior, and performs root-cause analysis by correlating infra, app and DB logs collected via agents. Claims the system suppresses expected weekly rush alerts, sends actionable alerts naming the likely failing transaction, and produces resource forecasting to schedule scaling before outages. Notes integration checks (Python, HP stacks) and a cost vs. time-savings tradeoff.
AI-written summary · about
chapters (9)
- 0:00Introduction and speaker intro
- 1:07Traditional monitoring explained
- 2:53AI-driven monitoring benefits
- 5:25Resource forecasting and planning
- 6:50Example: Response time analysis
- 8:16AI monitoring in action
- 9:41Evaluating AI monitoring solutions
- 11:31Cost vs. efficiency trade-offs
- 12:17Q&A session
related talks
30mBetter data quality with ML & visualization
29mThresholds Are for Old Threats: Demystifying AI and Machine Learning to Enhance SOC Detection
23mMastering Monitoring & Alerting: Key to Seamless Performance
01h 00mData is out, knowing is in: Applying AI to automate cloud operations
26mProactive Failure Prediction Through Anomaly Detection
25mMonitoring AI with AI
25mSymptom-based Alerting for Machine Learning - What I Learned...
50mInnovations in AI for automating IT operations