Andrew Lee

The biggest barrier to autonomous operations isn't capability, it's trust.Handing an incident to an autonomous agent raises a fair question. How do you know it is not guessing from raw log lines.

Double the number of jobs on a multi-tenant stream processing platform, and you'll more than double the alerts, false positives, and real incidents your team must triage. Signal and noise both grow super-linearly with scale, consuming an ever-larger scale of the platform team’s bandwidth. Applying AI at the right points can bring that support growth curve back toward linear. At JPMorgan Chase, a small platform team supports thousands of user-submitted Flink jobs processing more than 100 billion events per month. In this talk, we share the three-stage agentic support maturity curve that made this possible, and how you can apply it to your own platform: - Amplify the signals that matter. Learn AI/ML techniques can enrich platform telemetry and filter out alert noise so real problems stand out. - Human-initiated, AI-assisted diagnosis and remediation. See how correlating logs, metrics, and historical metadata with point-in-time state provides the context an agent needs to help engineers find root causes and fixes faster. - Agent-initiated diagnosis and remediation. Discover how agents can resolve routine issues on their own, keep the right people informed, and bring in humans only…

Experience the future of live sports broadcasting in this hands-on workshop. Learn to orchestrate multi-camera productions in the cloud using AWS Media Services and AI-assisted tools.

Argo CD is a popular CNCF continuous delivery technology for doing GitOps. In this chalk talk, hear about how AWS has started working with the Argo community to better understand and solve the scalability issues of Argo CD.