Operations | Monitoring | ITSM | DevOps | Cloud

Instrument zerocode observability for LLMs and agents on Kubernetes

Building AI services with large language models and agentic frameworks often means running complex microservices on Kubernetes. Observability is vital, but instrumenting every pod in a distributed system can quickly become a maintenance nightmare. OpenLIT Operator solves this problem by automatically injecting OpenTelemetry instrumentation into your AI workloads—no code changes or image rebuilds required.

Monitor Model Context Protocol (MCP) servers with OpenLIT and Grafana Cloud

Large language models don’t work in a vacuum. They often rely on Model Context Protocol (MCP) servers to fetch additional context from external tools or data sources. MCP provides a standard way for AI agents to talk to tool servers, but this extra layer introduces complexity. Without visibility, an MCP server becomes a black box: you send a request and hope a tool answers. When something breaks, it’s hard to tell if the agent, the server or the downstream API failed.

Observe your AI agents: Endtoend tracing with OpenLIT and Grafana Cloud

In another post in this series, we discussed how to instrument large language model (LLM) calls. This can be a good starting point, but generative AI workloads increasingly rely on agents, which are systems that plan, call tools, reason, and act autonomously. And their non‑deterministic behavior makes incidents harder to diagnose, in part, because the same prompt can trigger different tool sequences and costs.

How to monitor LLMs in production with Grafana Cloud,OpenLIT, and OpenTelemetry

Moving a large language model (LLM) application from a demo to a production‑scale service raises very different questions than the ones you ask when playing with an API key in a notebook. In production, you have to answer: How much is each model costing us? Are we keeping latency within our service‑level objectives? Are we accidentally returning hallucinations or toxic content? Is the system vulnerable to prompt‑injection attacks?

Seer fixes Seer: How Seer pointed us toward a bug and helped fix an outage

Seer is our AI agent that takes bugs and uses all of the context Sentry has to find the root cause and suggest a fix. We use it all the time to help us improve Sentry. Seer fixes Sentry. More recently, Seer has been helping us fix itself — Seer fixing Seer. An upstream outage triggered a bit of an avalanche, revealing a bug that had been hiding away for months. When it came time to fix it, Seer pointed us exactly where we needed to look.

Harness AI for Argo CD

Managing GitOps at scale shouldn’t feel like an endless game of "Whac-A-Mole." In this 3-minute demo, we show how Harness AI moves beyond simple syncs to provide agentic troubleshooting and automated orchestration for your entire GitOps estate. Watch as we use the Harness DevOps Agent to: Identify Common Failure Patterns: Instead of clicking through individual clusters, we ask the AI to analyze 4 out-of-sync applications simultaneously.

What's New in Turbo360 - AI agents for Azure cost optimization, Azure cost pulse summary report...

Turbo360 brings a suite of enhancements added to elevate your Azure management experience. Hit play to hear what's in store for this month. 00:00:00 - Intro 00:00:13 - Cost Pulse Summary Report 00:00:49 - Configuring Cost Pulse Summary 00:01:17 - New AI Agents (4 New Agents) 00:01:54 - Accessing AI Agents 00:02:18 - Related Resources Feature 00:02:40 - Budget Planner 00:02:59 - Setting Up Budget Planner Permissions 00:03:11 - Multi-Subscription Onboarding 00:03:43 - AI Agents Role-Based Access 00:04:10 - New RA-GRS Optimization Recommendation 00:04:30 - Summary & Call to Action.

Our key takeaways from NVIDIA GTC 2026

Every year, NVIDIA GTC offers a glimpse into the future of computing. But this year felt different. The conversations from the past few days point to something bigger than faster GPUs or larger models. The industry is shifting its mindset entirely. GTC 2026 made it clear that the goalposts for AI haven't just moved, they’ve been uprooted. We’re past the point of talking about "faster chips." Everything points to a total shift in the industry's DNA.