ScienceLogic has added additional tools and capabilities to its observability platform that provide deeper visibility and control over artificial intelligence (AI) agents that are being used to automate IT operations.

The latest 2.7 update to the Skylar AI platform provides visibility into agent routing and tool selection via a catalog that uses traces to surface how requests were routed via a Model Context Protocol (MCP) server.

In addition, DevOps and IT teams can disable specific agentic functions or MCP tools and, via a gatekeeper tool, inspect and quarantine suspicious content before it is exposed to an AI agent.

Finally, a Skylar Advisor tool now allows users to suppress advisory patterns they have determined do not require further attention.

Michael Nappi, chief product officer at ScienceLogic, said the goal is to provide DevOps and IT operations teams with more granular control over specific agentic functions. The Skylar platform provides the context and control layer that IT teams will need to safely incorporate AI agents into their workflows, said Nappi.

Otherwise, IT teams will not be able to reliably use probabilistic AI agents within what are largely deterministic workflows that need to be performed the same way each time, he added.

Ultimately, AI should make it possible for IT teams to both more adroitly respond to the needs of the business and determine the root cause of issues that, in some cases, have been longstanding “ghosts in the machine,” said Nappi.

The pace at which IT teams are adding AI agents to their workflows naturally varies. Many are already using them to, for example, summarize a report or configure a cloud service. However, very few IT teams are allowing AI agents to autonomously perform a task without any supervision.

The one thing that is certain is that there will be an increased need for observability platforms to keep track of AI agents that automate tasks at machine speed. The challenge is turning the insight surfaced by an observability platform into actionable intelligence that can be used to either prevent an action from occurring in the first place or roll back a task an AI agent may have mistakenly performed.

Less clear is to what degree AI will transform IT operations that today are largely fragmented. In theory, it should become possible in the AI era to converge more workflows in a way that enables IT teams to centrally manage processes and tasks on an end-to-end basis. Additionally, DevOps and IT operations teams should be able to manage a broader portfolio of applications without having to increase headcount or rely on as many specialists. In effect, those teams are evolving into supervisors of AI agents that perform tasks previously handled manually by an IT administrator or a software engineer.

One way or another, the management of IT is never going to be the same again as DevOps and IT teams gain more confidence in their ability to safely deploy AI agents. The only thing left to be determined now is to what extent.

Taggedagentic AIdevopsobservabilityScienceLogic

Frequently Asked Questions

1. What is new in ScienceLogic Skylar AI 2.7?
Skylar AI 2.7 introduces enhanced observability and control capabilities, including visibility into AI agent routing, MCP tool selection, suspicious content quarantine and advisory suppression.
2. How does Skylar AI 2.7 improve AI agent security?
The platform enables IT teams to disable specific agentic functions or MCP tools and inspect potentially suspicious content before it enters the knowledge base, reducing risks associated with AI-driven automation.
3. Why is observability important for AI agents in IT operations?
AI agents can execute tasks at machine speed, making it essential for IT teams to monitor their behavior, identify mistakes and intervene before automated actions cause operational problems.
Written byMike Vizard

Mike Vizard is a veteran IT journalist with more than 25 years of experience covering the technology industry, having previously served as Editor-in-Chief of both CRN and InfoWorld and as editorial director for Ziff-Davis Enterprise, where he oversaw titles including eWEEK, CIO Insight and Baseline. Over his career he has also edited or contributed to a wide range of enterprise technology publications, including IT Business Edge, Channel Insider, ComputerWorld, TMCNet and Digital Review, and he later led editorial for CTOEdge.com. His reporting and analysis span software development, cloud computing, cybersecurity, IT channel strategy and, more recently, artificial intelligence and DevOps practices. A recognized voice in enterprise IT journalism, Vizard is known for tracking emerging technology trends as they move from early adoption into mainstream enterprise use. He now serves as Chief Content Officer for Techstrong Group, where he oversees editorial strategy across the full network — devopsy.kinsta.cloud, Security Boulevard, Cloud Native Now, Digital CxO, Techstrong.ai, TechStrong.IT, Techstrong Semi and PlatformEngineering.com — in addition to writing and hosting content for Techstrong TV and the Techstrong Gang podcast.