Observe Smarter, Not Harder: Scaling AI-Powered Observability With O...
summary
Claims that OpenSearch turns logs, metrics and traces into actionable, proactive alerts using built-in ML and vector search: Random Cut Forest powers anomaly detectors reporting anomaly grade and confidence; AI search workflows embed models (Hugging Face, Bedrock Titan embeddings) into pipelines; demo shows a FastAPI app, Locust load generator, indices on port 9200, Slack webhooks and real-time monitors. Presentation cites 10% of orgs with full observability and OpenSearch’s 250M+ downloads as reasons to prefer its unified, extensible stack.
AI-written summary · about
chapters (12)
- 0:00AI-powered observability intro
- 3:38Observability evolution importance
- 7:12Traditional monitoring limits
- 10:50Cloud-native observability challenges
- 14:47Why observability is broken
- 16:29Proactive monitoring with AI/ML
- 18:38OpenSearch for modern observability
- 22:49AI observability stack on OpenSearch
- 27:24OpenSearch observability data journey
- 30:14Live demo: AI observability with OpenSearch
- 35:06Scaling AI observability best practices
- 35:30Q&A
related talks
06mSponsored Keynote: OpenSearch - See Everything: Open Observability for Agentic AI
22mFrom Telemetry to Insight: Building AI-Powered Observability Pipelines with OpenSearch
27mAlert Fatigue to Action: Observability as the Backbone of Practical AIOps with OpenSearch
42mBuilding Self-Healing Infrastructure: Agentic AI & Vector Search in OpenSearch
06mWhy OpenSearch?
21mKubernetes Under the Magnifying Glass: Observability With OpenSearch
37mBuilding Modern Observability Architecture With OpenSearch, OS Ingest...
25mKeynote: OpenSearch in the Agentic Era