AI In the Open: AIOps
AI in the Open is a webinar series exploring how open source and artificial intelligence are shaping the future of technology. Hear from industry leaders, practitioners, and subject matter experts on emerging trends, real-world use cases, and the opportunities and challenges organizations face as AI evolves.
Each session offers practical insights you can apply to your own work, while connecting broader industry perspectives across open source and AI. Join us live every third Thursday of the month, or watch sessions on demand on the Red Hat Open YouTube channel.
The next edition takes place on Thursday, Sept. 17.
Schedule 9:00-9:25 am PT: "Case Study: Agentic AIOps Skills to Automate Root Cause Analysis for High Velocity Infrastructure," Shrey Anand, Principal Software Engineer, Red Hat
How do you manage a massive, high-velocity infrastructure that provisions thousands of ephemeral clusters daily across hybrid clouds? When a provisioning job fails, the site reliability team faces a significant "Signal vs. Noise" challenge: logs are verbose, and there is no native link between the automation platform failures, the corresponding cluster events, and the state of the infrastructure cloud.
This talk presents a case study for an AIOps Skills framework: an agentic tool set designed to assist human SREs. This framework uses MCP and API servers to integrate context from automation logs, cluster logs, code, documentation from Github and Confluence, and human conversations from Slack. By combining these silos of data, the system builds a unified timeline to generate meaningful failure signatures and possible resolutions. We share results from real-world failures that show how this approach automates and simplifies troubleshooting. Attendees will gain a blueprint for bridging the gap between automation, platform, and cloud layers within their own organizations.
9:25-9:30 am PT: Q&A