Operations | Monitoring | ITSM | DevOps | Cloud

AI teams have invested heavily in evaluation frameworks, yet getting those frameworks beyond local experimentation remains challenging. Teams using open source libraries like DeepEval and Pydantic Evals gain flexibility and research-grounded metrics, but operationalizing those evaluations still requires brittle custom integration code that doesn’t scale.

Builder in the loop is a Mezmo interview series focused on the engineers, product leaders, and operators shaping AURA, an open-source, MCP-native agent harness for production operations. This installment features Tony Rogers, whose work on AURA is less about building new features and more about trying to break them before users can.

Handling client calls when a third-party vendor has an outage - this will sound familiar if you are a managed service provider (MSP). Your first instinct would be to check if the vendor's status page or social media handle shows anything, or check crowdsourced websites like Downdetector. Or even ask your client to check themselves. These approaches do not scale when you have more than a few clients, many vendor status pages to check, and clients with different stacks.

TL;DR Choosing the right AI-powered observability platform isn’t about who has the most AI features. It’s about which platform helps your team identify root causes faster and spend less time investigating incidents. Here’s the short version: Logz.io + OrionIQ: Autonomous AI agents investigate incidents, perform root cause analysis, and surface next steps. Open standards, Kubernetes-ready, and deploys in as little as a week.

If you've ever joined an incident call only to discover the monitor for the affected service was either misconfigured, deleted, or never set up in the first place—you already understand why monitoring as code (MaC) exists.

For years, monitoring was the gold standard of infrastructure management. Dashboards. Thresholds. Alerts. If everything on the dashboard was green, you didn't need to worry. If something turned red, you responded. It was a model built on predictability, and for a long time, it worked. But modern infrastructure is no longer predictable.

We’re excited to announce the new StatusGator SharePoint integration. Many organizations use SharePoint as the central hub for company resources, communications, and internal tools. Now, you can add real-time service status directly to your SharePoint pages, helping employees stay informed about outages, maintenance, and service disruptions without leaving the platforms they already use every day.

As CTO for Teneo, I get the opportunity to meet with many of our customers to talk about plans for the next few years. I often find we spend a lot of time talking about Digital Employee Experience, but far less time is spent fixing the operational friction that quietly erodes it. Slow devices, degraded application performance, and recurring service desk tickets are common themes in many organizations.