Operations | Monitoring | ITSM | DevOps | Cloud

During an incident, the answers an engineer needs are spread across tools. Telemetry sits in one place, configurations in another, and tickets in a third. Building a complete picture means knowing which tool holds which piece and how to query each one, usually under time pressure. Rosetta is the conversational interface for Selector Foundry, the agentic NetOps platform built on Selector’s existing AIOps and Observability solution.

Organizations may need to keep data in specific regions or infrastructure they control, whether because of data residency requirements, internal policies, or transfer costs. Datadog Bring Your Own Cloud (BYOC) extends the Datadog platform into those environments. Each BYOC deployment runs as a Kubernetes cluster with its own object storage, keeping data close to its source.

The best AI SRE tools to evaluate in 2026 include Sherlocks AI, Resolve AI, Traversal, Cleric, Rootly AI SRE, Komodor Klaudia, Datadog Bits Investigation, and Dynatrace Intelligence. Each addresses a different part of reliability work, from investigating alerts across multiple systems to diagnosing Kubernetes failures or validating production changes. Choosing the right tool starts with a practical question: where does your team lose time during an incident?

The moment your page slows down, two clocks start. One is yours: time to alert, time to investigate, time to fix. The other belongs to the user staring at the slow page. Yours is measured in minutes. Theirs runs out in seconds. That gap is what AI agents close. Zia Agents in OpManager Nexus detects an issue, works out the cause, and runs the fix on its own, often before your users feel a thing. This blog looks at how that changes the experience you deliver.

Your agent has earned trust in shadow mode. Now it runs on its own: an alert fires, the agent starts, investigates and proposes a fix before anyone opens a laptop. Here is what it takes to make that safe, scalable and better every week. This is the third article in a series on taking an AI SRE agent from a weekend experiment to production. Part 1 built a local, read-only agent on a throwaway cluster and refined it against a synthetic eval set.

If you're using agents and MCPs to get a better understanding of your environment or work through an investigation, you can get a lot of useful information back. You can pull logs, look at recent changes, and check how services are configured, but you're still the one deciding what to do with all of it. That part of the process still lives in your head. To see where Jev might fit, look at decisions your team already makes and work backwards from them.

Isolation keeps an agent’s code away from your infrastructure. A smart sandbox also lets the agent into the systems where real bugs live, without handing it the keys.

AI agent infrastructure is the set of platforms that run agents and the code they write. It has three layers: sandboxes that isolate untrusted, model-generated code, runtimes that run the agent and its services in production, and orchestration layers that save an agent’s progress so a long run can resume after a failure. Most production agents need more than one layer. This guide compares 10 platforms across all three, with isolation, state, deployment, and compliance for each.