Operations | Monitoring | ITSM | DevOps | Cloud

I let Claude investigate a production incident with Honeybadger's MCP server

In this demo, Kevin shows how you can use Honeybadger's MCP server with Claude to investigate a production incident — going from a natural language prompt to a complete incident dashboard in minutes. Honeybadger is an application health monitoring platform that helps developers catch errors, track performance, and stay on top of incidents. The MCP server lets AI assistants like Claude query your Honeybadger data directly, so you can investigate issues conversationally without digging through dashboards manually.

AI for App Resiliency: Automation Without Operational Chaos

Enterprise IT leaders face a persistent contradiction. Digital systems grow more complex each year, but operational stability and resilience do not improve at the same pace. Downtime costs are only the visible part of the problem. For large enterprises, unplanned outages can run into hundreds of thousands of dollars per hour in lost revenue, productivity, and remediation effort. The harder cost to quantify is the reputational damage when critical business services fail at the worst possible time.

Boosting Rust developer productivity with cursor - Our journey at ilert

AI-assisted coding has evolved from a novelty into an industry standard. At ilert, we started our adoption in mid-2023, quickly realizing that success depends heavily on proper context and workflows. This is particularly acute with Rust. While the language is central to our backend infrastructure, its strict compiler rules and distinct idiomatic approaches make it notoriously difficult for modern LLMs to master.

Technology Trends in the Mortgage Industry

The mortgage industry is changing rapidly due to technology. Many people still see homeownership as a key goal, and new tools are making it easier to go from application to closing. This tech advancement is simplifying the process and helping both consumers and businesses have a more seamless experience.

Top 10 ChatGPT SEO Agencies for 2026 (Manually Reviewed)

A funny shift has appeared in our conversations with marketing leaders over the last year. Teams still ask for SEO help. But more often, the question is: "Who can help us appear inside ChatGPT answers, and can they prove it without hand-waving?" People research inside ChatGPT, Perplexity, Gemini, and AI Overviews, then click only when they trust the source. If your brand is not cited, clearly understood as the right entity, and consistent across your site and the wider web, even strong pages can stay invisible when buyers are deciding.

Why Nexthink Intelligence Is a Game-Changer for IT Teams

Nexthink Intelligence transforms digital employee experience (DEX) for modern enterprises. Learn how IT teams can leverage real-time analytics, proactive insights, and automation to improve user productivity, troubleshoot issues fast, and deliver better workplace tech experiences. Learn more at nexthink.com.

A 4-Month Bug Fixed in <10 Minutes with Olly

In today’s highly interconnected systems, the subtle relationships between services are rarely obvious. Modern, complex architectures generate telemetry that functions less as “flashing signs” and more as faint “breadcrumbs” to be followed across a vast network of signals. In 2025, about two-thirds of outages involved third-party systems like cloud platforms and APIs.

The limits of MCP and how Olly surpasses them

Model Context Protocol (MCP) servers act as adapter layers between clients and AI based workloads. MCP installation into an IDE, such as Cursor, brings a wealth of information directly into the developers primary tool, minimizing context switching and, especially in the world of observability, bringing telemetry closer to the code. MCP is not without its limits. These limits initially seem trivial, but in time, some of the inherent limitations to a basic MCP implementation become apparent.

When AI Writes the Code, Who Keeps Production Running?

The production environment has become a minefield of code nobody really understands. Here’s what’s happening: Development teams are using Claude Code, Cursor, and GitHub Copilot to ship features at 10x their previous velocity. Product managers are ecstatic. Business stakeholders are thrilled. And somewhere in a war room at 2:17 AM, an SRE is staring at a stack trace for code that was AI-generated three weeks ago, trying to figure out why the payment service just fell over.

Evaluating our AI Guard application to improve quality and control cost

This article is part of our series on how Datadog’s engineering teams use LLM Observability to build, monitor, and improve AI-powered systems. Organizations are building AI agents that help users automate work, analyze data, and interact with complex systems through natural language. As these agents become more capable, they also become more complex and exposed to risks such as prompt injection, data leaks, and unsafe code execution.