AI-Driven Cloud Observability: Reduce toil and amplify time to resolution
summary
Claims concrete gains: forecasting, outlier protection, correlated signal search, and a dashboard assistant are built into Grafana Cloud Asserts and paired open source pieces; features include Sift, incident auto summary, and profile analysis for CPU/memory flame graphs. Customers report meaningful MTTR reductions (BlackRock cites lower toil and faster resolution), forecasting and anomaly detection operate across Prometheus/Loki/BigQuery/etc, some capabilities remain cloud-only and models use pre‑trained LLMs with optional customer data tuning.
AI-written summary · about
chapters (12)
- 0:00Introduction
- 2:36AI in observability and Grafana
- 4:21Traditional observability challenges
- 7:11Grafana Cloud for AI observability
- 9:00Forecasting and outlier detection
- 11:49Sift for anomaly detection
- 13:34Log pattern analysis with Sift
- 14:35Dashboard Assistant
- 16:28Incident Auto Summary
- 19:03AI profile analysis with flame graphs
- 20:26Ass search for root cause
- 22:12Q&A
related talks
21mSpeed Up Troubleshooting with Integrated Application and Infrastructure Observability
27mApplying AI/ML: How to Reduce Effort, Time and Cost
44mGrafana Labs Customers: What We've Learned Building Observability at Massive Scale
21mActian & Grafana Cloud: The Search for a Customizable Observability Tool
23mAI/ML + open source observability
21mAgent Observability Beyond Vibes
13mLightning Talk: Observability-First DevSecOps: Building Resilient Multi-Cloud P...
13mAchieving Seamless O11y Across Cloud Providers