This video tackles a critical challenge in AI agent development: understanding what's actually happening when agents behave unpredictably. Using a real-world example where two identical requests to the same AI agent produced dramatically different results—one taking 10 seconds with 10 operations, the other over a minute with 42 operations—the video demonstrates why observability is essential for agentic systems. Since LLMs decide their own execution paths, choosing which tools to call and how many times to loop, traditional debugging approaches fall short.

The solution presented is OpenTelemetry tracing, the same technology used to monitor distributed systems, now applied to AI agents. The video explains how OTel's standardized `gen_ai.*` semantic conventions capture AI-specific telemetry across any model provider, while integrating seamlessly with existing infrastructure observability. Through a hands-on demonstration using Jaeger and a Kubernetes-based AI agent, viewers learn how to trace the complete journey of requests through agents, LLMs, tool executions, and external services. The key takeaway: while AI-specific tools like LangSmith have their place for prompt debugging and evaluations, OpenTelemetry provides a unified, vendor-neutral standard that connects AI traces to everything else in your stack—giving you the visibility needed to debug, optimize, and trust your agentic systems.

#OpenTelemetry #AIAgents #Observability

Consider joining the channel: https://www.youtube.com/c/devopstoolkit/join

▬▬▬▬▬▬ 🔗 Additional Info 🔗 ▬▬▬▬▬▬
➡ Transcript and commands: https://devopstoolkit.live/observability/ai-agent-debugging-setup-opentelemetry-jaeger-in-kubernetes
🔗 OpenTelemetry: https://opentelemetry.io
🎬 Distributed Tracing Explained: OpenTelemetry & Jaeger Tutorial: https://youtu.be/Oa-zqv-EBpw

▬▬▬▬▬▬ 💰 Sponsorships 💰 ▬▬▬▬▬▬
If you are interested in sponsoring this channel, please visit https://devopstoolkit.live/sponsor for more information. Alternatively, feel free to contact me over Twitter or LinkedIn (see below).

▬▬▬▬▬▬ 👋 Contact me 👋 ▬▬▬▬▬▬
➡ BlueSky: https://vfarcic.bsky.social
➡ LinkedIn: https://www.linkedin.com/in/viktorfarcic/

▬▬▬▬▬▬ 🚀 Other Channels 🚀 ▬▬▬▬▬▬
🎤 Podcast: https://www.devopsparadox.com/
💬 Live streams: https://www.youtube.com/c/DevOpsParadox

▬▬▬▬▬▬ ⏱ Timecodes ⏱ ▬▬▬▬▬▬
00:00 Tracing for AI Agents 
01:04 Why AI Agents Need Tracing
09:29 OTel vs AI-Specific Tools

DevOps Toolkit's resource offers insights, tutorials, and resources for DevOps engineers and practitioners. Readers can learn about DevOps best practices, automation techniques, and tools for continuous integration and deployment. With articles, guides, and case studies, DevOps Toolkit provides  guidance and expertise for streamlining software delivery pipelines and improving collaboration between development and operations teams.

DevOps Toolkit

AI agents exhibit unpredictable behavior where identical requests can produce vastly different execution paths—one taking 10 seconds with 10 operations, another over a minute with 42 operations. OpenTelemetry tracing solves this by capturing the complete journey of agent requests through LLM calls, tool executions, and external services. Using OpenTelemetry's GenAI semantic conventions provides vendor-neutral observability that integrates AI traces with existing infrastructure traces (databases, APIs, message queues) in a unified view. This approach offers advantages over agent-specific tools like LangSmith by leveraging existing observability infrastructure and connecting AI operations to the broader distributed system context.

AI Agent Debugging Setup: OpenTelemetry + Jaeger in Kubernetes