Operations | Monitoring | ITSM | DevOps | Cloud

For SREs juggling multiple services, third-party dependencies, and constant alerts, a critical service slowdown can quickly turn into chaos. APM Dashboards may show everything is fine, yet users are still experiencing problems. That gap—between application telemetry and real-world performance—can turn a five-minute fix into a two-hour war room. ‍

We are thrilled to announce the availability of Mezmo’s AI-powered Site Reliability Engineering (SRE) agent for Root Cause Analysis (RCA)—a truly transformative leap forward for engineering and operations teams included in your existing subscription at no additional charge. We are paving the way for a new era of observability, moving beyond passive, reactive monitoring to a world of proactive AI-driven observability.

Active Telemetry is the evolution in how organizations collect, process, and use observability data. In traditional observability, telemetry is passive: systems emit logs, metrics, and traces that are stored and visualized after the fact. This model worked when systems were simpler and changes were predictable. But in today’s world with distributed microservices, Kubernetes, and AI workloads, passive telemetry can’t keep up. Active Telemetry changes that.

Today, we’re excited to announce the launch of Mezmo’s AI-powered Site Reliability Engineering (SRE) agent for root cause analysis (RCA)—a transformative leap forward for engineering and operations teams facing the relentless complexity of modern cloud-native systems. ‍

The world of software development has fundamentally changed. We've moved from monthly releases to continuous delivery measured in minutes, and the rise of AI means velocity is no longer just a goal—it's a requirement for survival. But this relentless speed has exposed a critical flaw in how we approach observability. The industry relies on a "store first, ask questions later" model where you collect every log, metric, and trace, and then hope to find the root cause when something breaks.

AI agents for SREs were supposed to slash mean time to resolution and eliminate alert fatigue. Instead, most teams got expensive, unreliable tools that burn through tokens without delivering insights. But what if the problem isn't the AI models themselves? Recent benchmarking reveals the real bottleneck: context engineering. When we tested our context engineering approach against conventional methods, the results were dramatic: Scroll down for our benchmark results to see the full comparison.

This blog was authored by Jason Bloomberg, Managing Director, Intellyx BV ‍ Observability depends upon telemetry – the data streaming from various applications, services, and systems that indicate their internal state in real-time. Various tools consume such telemetry to enable both operational and cybersecurity tasks.

Imagine a developer at a fast-growing company. A customer support agent reports a critical issue: a user's recent order is stuck in a "pending" state. The agent provides a customer ID and a request ID. The developer's typical process is a familiar, painful dance: This process is slow, tedious, and prone to human error. The Mean Time to Resolution (MTTR) is measured in hours, not minutes, and it's a huge drain on engineering resources.

We're thrilled to announce the launch of our new AI Chatbot, now live and in production for all users. This isn't just a simple Q&A bot; it's a powerful assistant designed to streamline your workflow, provide instant context, and help you navigate the Mezmo platform more efficiently.

Building a great developer experience is about more than just the code. It’s about creating a unified ecosystem where your tools work together seamlessly. That’s been the vision behind our work on the Mezmo MCP Server, and I’m excited to share it with you. At its core, the MCP Server is a universal remote for your data pipeline.