Operations | Monitoring | ITSM | DevOps | Cloud

How we built Grafana Assistant - a conversation about AI development for observability

This conversation with Grafana Labs engineers, Mat Ryer, Cyril Tovena and Sven Großmann, dives deep into the engineering behind Grafana Assistant, exploring how agentic AI is transforming the observability landscape. From hackathon origins to sophisticated backend agents, the team shares candid lessons on building, scaling, and refining AI tools for engineers.

How AI is democratizing video and what it means for your brand

Video stopped being optional years ago. In 2026, 95% of marketers say video increases brand awareness, and 60% report it directly drives sales. But for small businesses and solo entrepreneurs, there's always been a gap between knowing video matters and actually making it. The costs, the learning curve, the time-it adds up fast.

Operational Risks and Controls When Deploying Legal AI

A law firm recently found that its AI tool had misread "limitation of liability" clauses for 6 months. No one noticed the mistake. The error only came to light when a client faced a huge insurance claim that the firm had promised was capped. The cost? That firm is now dealing with a malpractice lawsuit and a damaged reputation. Using AI in a law office poses risks beyond simple computer bugs. These tools mix technical errors with professional responsibility. As AI becomes a standard part of the job, firms without strict rules will face quality issues and legal trouble.

How Honeycomb Supercharges OpenTelemetry for AI

It has become common knowledge that the nature of software development has changed as AI-code generation and agent-based features gain adoption. In perhaps a more subtle shift, the fundamentals of software instrumentation are changing too. As OpenTelemetry becomes the standard instrumentation layer across enterprises, with thousands of developers (many from Honeycomb) actively contributing to it, the nature of the telemetry data captured itself is evolving to meet the growing demand for rich context.

The AI-Empowered Site Reliability Engineer: Automating the Balance of Risk and Velocity

You might expect an AI-SRE agent to target 100% reliable services, ones that never fail. It turns out that past a certain point, however, increasing reliability is worse for a service (and its users) rather than better! Extreme reliability comes at a non-linear cost: maximizing stability limits how fast new features can be developed, dramatically increases the operational cost, and reduces the features a team can afford to offer.

Agentic AI Essentials: The Dashboard and Changing IT Roles

Dashboards provide a useful prism through which we can study the broader evolution of the IT professional’s role in the era of agentic AI. For years, dashboards have been the centerpiece of IT work, serving as the interface where teams interpret system behavior, diagnose issues, and plan actions. Dashboards epitomize the relationship between humans and their systems: humans observe, interpret, and act. As agentic AI enters the picture, that relationship begins to change. Let’s explore how.

From Blueprint to Production: Building a Kubernetes MCP Server

As Large Language Models (LLMs) evolve from simple chatbots into agentic workflows, the need for a standardized way to connect them to external data and infrastructure has become critical. In a recent workshop hosted by Nir Adler, Innovation Engineer at Komodor, we explored how to bridge this gap using the Model Context Protocol (MCP).

Why MCP is becoming part of your product surface

AI assistants are quickly becoming a primary interface for how people interact with software. Developers ask them how to integrate APIs. Users ask them how products work. Buyers ask them how tools compare. Increasingly, the first explanation someone receives about your product does not come from your website, your documentation, or your sales team. It comes from an AI assistant. That shift has an important consequence that many organizations are only starting to notice.

Upsun's AI story: the 5% path from pilots to production value at scale

Here’s the uncomfortable truth: most companies do not have an AI problem. They have a delivery problem wearing an AI costume. MIT’s Project NANDA research has been widely cited for a brutal headline statistic: roughly 95% of corporate generative AI pilots fail to produce measurable business impact or returns, while only about 5% break through to meaningful outcomes. (Yahoo Finance) The models are impressive. The demos are dazzling. The budgets are real.