Operations | Monitoring | ITSM | DevOps | Cloud

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.

What Engineers Want from AI in Observability... According to the 2026 Observability Survey Report

The results show strong interest in AI for forecasting, root cause analysis, onboarding, and generating dashboards, alerts, and queries. But when it comes to autonomous action, practitioners are more cautious — and 95% say AI needs to show its work to earn trust.

The Hidden Failure Points in Your AI Strategy

New models, new agents, new capabilities. It seems like every week there’s a new must-have AI function. It’s no surprise that leaders are feeling pressure to move quickly. At a PagerDuty on Tour event, a customer joked that they couldn’t fathom having a five-year AI strategy; it makes way more sense to have a five-minute one. There’s truth in that comment.

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.

Agentic AI at Scale: Building the Kubex Agentic AI Platform

In the modern cloud infrastructure landscape, we don’t have a data problem; we have an actionable interpretation gap. Engineering teams are often drowning in metrics that describe a crisis without providing a clear path to remediation. Traditional FinOps, SRE, and DevOps work has become a reactive loop of dashboard-watching and manual firefighting.

How to Catch AI Code Mistakes Before They Reach Production

AI can write code fast, but it makes mistakes humans often don't. In this session from Ole Lensmar, CTO of Testkube, breaks down the real quality risks of AI-generated code and how engineering teams can build guardrails before those bugs hit production. What you'll learn: Common mistakes LLMs make (and which ones are unique to AI) Whether you're a developer leaning on AI to ship faster or a QA lead trying to keep up with the pace of AI-generated code, this talk gives you a practical framework for staying ahead of quality issues.

Claude Code is running bash commands on your infrastructure. Here's how to watch it.

I’ve been staring at Claude Code telemetry for the past few weeks, and I keep noticing the same thing: most teams drop it into their environment, say “it’s amazing,” and have absolutely no idea what it’s actually doing at the system level. That’s fine for a personal dev tool. It’s not fine when you’ve rolled it out to 50 engineers.

Architecting MCP for AI Agents: Lessons from Our Redesign | Harness Blog

-- Key Takeaways: The Harness MCP server is an MCP-compatible interface that lets AI agents discover, query, and act on Harness resources across CI/CD, GitOps, Feature Flags, Cloud Cost Management, Security Testing, Resilience Testing, Internal Developer Portal, and more. -- The first wave of MCP servers followed a natural pattern: take every API endpoint, wrap it in a tool definition, and expose it to the LLM.