What If the Promise of AIOps Was True?
summary
Defines AIOps as ML applied to production infrastructure, contrasts three stances: impossible today because production lacks the sample sizes and ROI, an imminent takeover, and a practical weak AIOps view that works in narrow cases. Claims ML can help monitoring, alert tuning, bad-change detection and some recurrent incident types if there’s cross-silo data and precedents; novel outages and known knowns gaps remain hard. Practical enablers: more data, standardization, and simple mitigations like a big red button (drain/cluster) for safe automation.
AI-written summary · about
chapters (12)
- 0:00Intro
- 0:40Definitions
- 2:22Claim Cheddar
- 6:35AIOps vs Traditional IT
- 8:50AIOps vs ML
- 12:27Application of AIOps
- 14:29Monitoring
- 19:25Change Detection
- 23:27Response Root Cause Analysis
- 26:29Known Unknowns
- 27:32Scaling and General Operations
- 29:29Conclusion
related talks
24mAIOps, are we there yet?
30mThe Robots Are Coming (But Not Yet), or, Don't Make Smart People Do Dumb Things
29mIs AIOps the Future of Operations? Real Use Cases From the Trenches
33mNext Generation of DevOps AIOps in Practice
29mAutomation first, People centric
20mAutomated Incident Management
25mAI-Powered O11y in Microservices Architectures
24mDriving Revenue Excellence with the Power of AIOps