Operations | Monitoring | ITSM | DevOps | Cloud

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 Hučková provides a deep dive demo on how Grafana AI Observability connects our experience building Agents with our experience building observability systems.

Context Offloading is a pipeline solution for managing Observability with AI Agents. If you are building AI Agents that work with real data, the context window can very easily get filled with bloated context that the Agent does not really need. Sven demonstrates "Context Offloading", a solution that stores the JSON result and sends only the summary of the JSON blob, making the LLM loop performance much quicker and keeping your context window small.

MCP vs CLI: which one should your AI agent actually use? We get into it with Grafana's cloud and OSS MCP servers and gcx.

Hear how Kentik uses AI to validate AI and catch 90%+ of bad networking answers before users ever see them.

AI can write a feature in seconds, but where are you testing it? Sending production traffic, API payloads, and auth headers to a third-party SaaS is a massive security risk. In this video, we break down why the Bring Your Own Cloud (BYOC) model is the ultimate fix for DevSecOps. Learn how to safely test AI-generated code against real production traffic entirely within your own VPC or Kubernetes cluster. No data leaks, no massive DLP pipelines, and no endless masking rules.

What used to be $50 a month is now $3,000 — overnight. Microsoft just moved GitHub Copilot to token-based billing, and devs are split between calling it a "rug pull" and admitting someone always had to pay the bill. Here's the part that should worry every engineering leader: most can't tell you what percentage of their AI-generated code actually ships, or where the tokens went. When the meter is running on every prompt, "it feels productive" isn't good enough — you need to know that bug cost you $2,700 in tokens to fix.