Operations | Monitoring | ITSM | DevOps | Cloud

Seer is our AI agent that takes bugs and uses all of the context Sentry has to find the root cause and suggest a fix. We use it all the time to help us improve Sentry. Seer fixes Sentry. More recently, Seer has been helping us fix itself — Seer fixing Seer. An upstream outage triggered a bit of an avalanche, revealing a bug that had been hiding away for months. When it came time to fix it, Seer pointed us exactly where we needed to look.

Today, we’re excited to introduce the beta release of MicroCloud Cluster Manager, a new way to discover, organize, and operate your MicroCloud environments from a single, unified interface. MicroCloud is an open source cloud platform that makes it simple to create lightweight, resilient clusters anywhere. As teams scale from one cluster to many, visibility and coordination quickly become essential. Cluster Manager is built to solve exactly that.

Teams running modern infrastructure can’t afford slow incident response. On-call management software ensures the right person is alerted instantly, incidents are escalated intelligently, and downtime is minimized. This guide breaks down the best on-call management software for 2026, helping teams choose the right platform based on their specific use case, response requirements, and operational complexity.

Moving a large language model (LLM) application from a demo to a production‑scale service raises very different questions than the ones you ask when playing with an API key in a notebook. In production, you have to answer: How much is each model costing us? Are we keeping latency within our service‑level objectives? Are we accidentally returning hallucinations or toxic content? Is the system vulnerable to prompt‑injection attacks?

In another post in this series, we discussed how to instrument large language model (LLM) calls. This can be a good starting point, but generative AI workloads increasingly rely on agents, which are systems that plan, call tools, reason, and act autonomously. And their non‑deterministic behavior makes incidents harder to diagnose, in part, because the same prompt can trigger different tool sequences and costs.

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.

Building AI services with large language models and agentic frameworks often means running complex microservices on Kubernetes. Observability is vital, but instrumenting every pod in a distributed system can quickly become a maintenance nightmare. OpenLIT Operator solves this problem by automatically injecting OpenTelemetry instrumentation into your AI workloads—no code changes or image rebuilds required.

Datadog supports managing Datadog configuration as code through the Datadog Terraform provider. As platform engineering practices evolve, we are focused on making this provider more reliable and trustworthy at enterprise scale.