GenAI Observability in Grafana Cloud: End-to-End Agent Debugging (Demo)

From Observability for GenAI Applications (Grafana ❤️‍🔥 OpenTelemetry Community Call #4)

Watch the full episode: https://youtu.be/LfDVygRWQJU
This demo shows how to use Grafana Cloud to observe and debug a running GenAI agent, including multi-agent execution, tool calls, and LLM requests. We drill into traces to see which agents called which tools, where errors occurred, how long each LLM call took, and how costs and tokens are distributed. The walkthrough also covers using AI assistance to summarize long traces and identify optimization opportunities in real time.

Timestamps:
00:00:00 Overview of the GenAI agent demo
00:00:35 AI observability dashboard walkthrough
00:01:13 Using Grafana Assistant to investigate errors and latency in traces
00:02:51 Exploring GenAI spans: agents, tool calls, prompts, and costs
00:03:51 Comparing latency, cost, and usage across LLM providers
00:04:23 Evals dashboard walkthrough

Links/resources:
Learn about Grafana Cloud
AI Observability: https://grafana.com/docs/grafana-cloud/monitor-applications/ai-observability/
Get started with the Grafana Cloud forever-free tier: https://grafana.com/g/cloud
Have a question? Ask Grot, your AI helper: https://grafana.com/grot/
Reach out in our community forums: https://gra.fan/communityyf

Thanks for watching!

👍 Was this video helpful? Like and subscribe to our channel for more videos.

Connect with Grafana Labs:
X: (https://www.twitter.com/grafana)
LinkedIn: (https://www.linkedin.com/company/grafana-labs/)
Facebook: (https://www.facebook.com/grafana)

#Grafana #Observability