Implementing AI-Powered O11y with Splunk
summary
Claims concrete outcomes using Splunk: ingest via Splunk universal forwarders and OpenTelemetry, inject correlation IDs, baseline behavior with ML and detect anomalies across logs metrics and traces. A case trains models for a 10× traffic surge and detects a payment bottleneck 15 minutes earlier, triggering autoscaling and avoiding an estimated $2.3 million loss. Implementation needs model tuning, playbooks for restart or scale, about 4–6 months to reach maturity and shows a ~45% MTTR reduction and 3.5× ROI.
AI-written summary · about
chapters (11)
- 0:00Introduction and Overview
- 0:49The Observability Challenge
- 1:39Evolution of Observability
- 2:42Strategic Importance of Observability
- 3:53Splunk's Observability Platform
- 6:03Technical Architecture and Data Collection
- 7:25AI and Machine Learning in Observability
- 9:34Case Study: E-commerce During Peak Traffic
- 10:30Building Autonomous Remediation Workflows
- 11:25Implementation Framework
- 12:16Next Steps and Conclusion
related talks
25mAI-Powered O11y in Microservices Architectures
21mAI-Powered O11y with LLMs: Resilience in Cloud PaaS Archs
42mObserve Smarter, Not Harder: Scaling AI-Powered Observability With O...
40mOptimizing AI Applications for Production with Observability
42mUnified observability, AIOps, and incident response for AWS
22mFrom Telemetry to Insight: Building AI-Powered Observability Pipelines with OpenSearch
39mThe evolution of Devops in the age of AI
41mCustomer Centric Observability at Scale Leveraging AIOps & OpenTelemetry