Uploaded July 2026 | Updated September 2026, 2 weeks ago
Grafana AI Observability is our new database and platform for observing AI Agents. Over the past year at Grafana Labs, we built Agents and we needed a way to understand how they are performing, what are the costs associated with them, what's the error rate or time to the first token as well as how they are behaving. Grafana Staff Engineer, Ivana HuΔkovΓ‘ provides a deep dive demo on how Grafana AI Observability connects our experience building Agents with our experience building observability systems.
Timestamps:
00:00 - Intro
00:48 - Instrument your Agent
01:21 - Analytics page
02:21 - Online Evaluations - are Agents behaving correctly?
04:00 - Assign which Agents the Evaluation conversation will be run on
05:01 - Evaluation scoring
05:32 - Specific conversation drill down
06:20 - Find out why an evaluation failed
07:00 - Agents Insights
08:13 - Tools page
Links/resources:
Learn about AI-Powered Observability in Grafana Cloud: grafana.com/products/cloud/ai-observability
Docs β AI Observability Overview: grafana.com/docs/grafana-cloud/machine-learning/ai-observability
Docs β Introduction: grafana.com/docs/grafana-cloud/machine-learning/ai-observability/introduction
Get started with the Grafana Cloud forever-free tier: grafana.com/g/cloud
Have a question? Ask Grot, your AI helper: grafana.com/grot
Reach out in our community forums: https://gra.fan/communityyf
---
Thanks for watching!
π Was this video helpful? Like and subscribe to our channel for more videos.
Connect with Grafana Labs:
X: (twitter.com/grafana)
LinkedIn: (linkedin.com/company/grafana-labs/)
Facebook: (facebook.com/grafana)
#Grafana #Observability #aiagents #observabilitysystems #AIObservability #LLMObservability #AI #LLM
Grafana AI Observability is our new database and platform for observing AI Agents. Over the past year at Grafana Labs, we built Agents and we needed a way to understand how they are performing, what are the costs associated with them, what's the error rate or time to the first token as well as how they are behaving. Grafana Staff Engineer, Ivana HuΔkovΓ‘ provides a deep dive demo on how Grafana AI Observability connects our experience building Agents with our experience building observability systems.
Timestamps:
00:00 - Intro
00:48 - Instrument your Agent
01:21 - Analytics page
02:21 - Online Evaluations - are Agents behaving correctly?
04:00 - Assign which Agents the Evaluation conversation will be run on
05:01 - Evaluation scoring
05:32 - Specific conversation drill down
06:20 - Find out why an evaluation failed
07:00 - Agents Insights
08:13 - Tools page
Links/resources:
Learn about AI-Powered Observability in Grafana Cloud: grafana.com/products/cloud/ai-observability
Docs β AI Observability Overview: grafana.com/docs/grafana-cloud/machine-learning/ai-observability
Docs β Introduction: grafana.com/docs/grafana-cloud/machine-learning/ai-observability/introduction
Get started with the Grafana Cloud forever-free tier: grafana.com/g/cloud
Have a question? Ask Grot, your AI helper: grafana.com/grot
Reach out in our community forums: https://gra.fan/communityyf
---
Thanks for watching!
π Was this video helpful? Like and subscribe to our channel for more videos.
Connect with Grafana Labs:
X: (twitter.com/grafana)
LinkedIn: (linkedin.com/company/grafana-labs/)
Facebook: (facebook.com/grafana)
#Grafana #Observability #aiagents #observabilitysystems #AIObservability #LLMObservability #AI #LLM
