Don't miss out! Join us at our next Flagship Conference: KubeCon + CloudNativeCon North America in Salt Lake City from November 12 - 15, 2024. Connect with our current graduated, incubating, and sandbox projects as the community gathers to further the education and advancement of cloud native computing. Learn more at https://kubecon.io
Prompt: Help Me Debug a Cluster! - Anusha Ragunathan & Lili Wan, Intuit Inc
Platform Engineers & SREs utilize metrics from Kubernetes clusters to evaluate platform health. However, being swamped with alerts for every metric often leads to alert fatigue. The worst consequence of alert fatigue is burnout or snoozing alerts, risking incidents. To tackle this at Intuit, we built Cluster Golden Signals & decreased MTTD. As a next phase, we explored integrating generative AI & LLMs with Cluster Golden Signals for enhanced platform debuggability and reduced MTTR. If the Golden Signal is bad, could we automatically initiate a check for deeper detection? Can generative AI predictably auto-remediate using its vast Kubernetes debugging knowledge? We explored k8sGPT & other tools for this. In this talk, we will delve into Intuit's development of Cluster Golden Signals & integration with generative AI for improved and faster platform debuggability. We will showcase demos to highlight the potential of using Cluster Golden Signals with generative AI.