Observability as a foundation for AI-enabled platforms
summary
OpenTelemetry now graduates and the CNCF reports 49% running in production, making it the second‑largest CNCF project after Kubernetes and up ~35% last year; adopt GNAI semantic conventions so agents can reason over unified traces, metrics, logs and tokens. Use the OpenTelemetry operator or auto‑instrumentation to inject telemetry, normalize with GNAI normalizer or Arconia, and expect sparse reasoning in traces (demo showed 290 spans 15 reasoning), so capture tokens, tool calls and chain‑of‑thought for debugging.
AI-written summary · about
chapters (14)
- 0:00Introduction
- 1:15OpenTelemetry for AI platforms
- 3:20Platform engineering in AI era
- 6:56Missing observability in AI talks
- 9:03Observability for platform engineering
- 10:28Observing AI workloads
- 13:17Tracing agent interactions
- 14:19Trust in AI agents
- 17:46Agent autonomy levels
- 19:51Agentic SDLC feedback
- 21:36Telemetry for coding agents
- 22:18Production agents on Kubernetes
- 23:42Key takeaways
- 25:45Closing
related talks
27mObservability as a foundation for AI-enabled platforms
04mOpenTelemetry Celebrates Graduation and the Next Era of Agentic...
50mOpen Source Instrumentation - The Rise of OpenTelemetry
07mKeynote: OpenTelemetry And The Future of Open Source Observability
20mObservability and Open Telemetry
47mWhat’s New in OpenTelemetry
31mDeep Dive To AI Agent Observability
27mOpening Remarks / Keynote: State of the Community