groundcover released a major expansion to Agent Mode that lets AI agents act on a team's observability data across their existing development toolchain.
With groundcover, engineers control agents to make code recommendations, open pull requests, and manage tasks in applications such as Slack, Linear, and GitHub with Connectors. Agent reasoning and execution remain within the customer's own cloud, while every action is governed by user-level permissions and tied to a specific, authorized user.
This latest expansion is built on a single idea: the control that engineering teams get with BYOC is what makes AI agents worth deploying. Available now, the release adds connectors, customizable agent skills, and admin-level guardrails for existing customers at no additional cost.
"Our customers relied on groundcover dashboards to tell them what was happening in their stack, but that was never connected to the context sitting in applications such as Slack or Linear about why," said Noam Levy, groundcover Field CTO. "Now Agent Mode can work with both. Engineers can stay in the tools they already use, and the agent brings full telemetry context with it."
Because groundcover Agent Mode runs inside the customer's environment on full telemetry, it reasons over the team's real systems rather than a generic or sampled slice, meaning recommendations reflect what’s actually running. And because every agent action is authorized through role-based access control (RBAC) and admin-level Model Context Protocol (MCP) permissions, each one is something a named person was already allowed to do. The result: even small teams can operate at many times their size without giving up accountability. groundcover puts the agent where the data already lives, rather than asking customers to move their data to the agent.
Key new features include:
- Connectors: Connectors bring external applications such as Claude, Slack, Linear, GitHub and Cursor into the platform. Agent Mode can take action within those tools using the user's own credentials, such as recommending code, making changes, opening pull requests, or managing tasks. Remote MCP connectors also let external agentic services interface directly with Agent Mode, closing the gap between the development toolchain and the telemetry data that should inform it.
- Custom skills: Agent Mode is a chat-based, large language model (LLM)-driven experience for diagnosing application and infrastructure behavior. Organizations can now customize the built-in skills and author their own, mapping Agent Mode to the specific runbooks, operational playbooks, and tribal knowledge that each team already follows.
- Agent Mode guardrails: Centralized, admin-level MCP authorization lets administrators define which MCP services, connectors, and tools the organization can use. Every execution and tool call is attributable to a specific user, and admins can define the engagement patterns Agent Mode will follow. An agent you can't govern is a liability, not a teammate; guardrails are what turn an autonomous tool into one a team can trust on call.
"Customers chose BYOC because their telemetry is sensitive and high-volume, but the contradiction in most AI observability is that agents only work if you ship that data back to the vendor," said Yechezel Rabinovich, CTO and co-founder of groundcover. "By keeping the agent where the data already lives, admins control which MCP services, connectors, and tools the organization can use. Every execution is attributable, and there is no token markup on top. Our ultimate roadmap is to make groundcover the coordination layer between the engineer, the agent, and the telemetry they all depend on.”
These updates ship automatically to groundcover's 200-plus deployed customers.
The Latest
For fifteen years, observability lived downstream of everything else. Code shipped, something broke, an engineer went to the dashboards. The job was forensic. The pillars we built, such as logs, metrics, and traces, were designed for that role: tell a human what just happened, fast enough that they can make it stop. That role has quietly ended ...
Hybrid IT has become the standard operating model for enterprises — but that companies are still looking for the right hybrid IT mix, according to the 2026 State of the Data Center Report from CoreSite. After years of cloud migration and hybrid adoption, organizations are shifting their focus from deciding whether to use cloud, colocation or on-premises infrastructure to determining which workloads belong in each environment ...
Pilots are everywhere, stakeholders are seeking results, businesses are pushing for new tools, and IT teams are being asked to make AI secure, reliable, and useful at scale. But as organizations move from testing AI to operationalizing it, many are discovering that the biggest barrier is not the model, the use case, or even the budget. It is the file data foundation within ...
Fast or cheap? For most of my career in engineering, speed and quality sat on opposite ends of a seesaw. The "OR" in "fast or cheap" was non-negotiable. It was expected that pushing for faster releases meant that something in quality would give way. Tightening quality controls meant the schedule slipped. Every engineering leader I know has lived some version of that tradeoff ... The seesaw is starting to level out ...
I have been building enterprise software for more than 20 years ... One thing stays true across all of it: You do not find out your foundation is wrong during the crisis. You find out when the debt comes due. For a lot of organizations, that bill is arriving now. New research ... puts hard numbers on something practitioners have been sensing for a while. The telemetry problem isn't coming. It's already here ...
The rapid growth of AI workloads is pushing traditional log management approaches to their limits, according to The State of Log Management 2026 report from Dynatrace. Modern logs have become critical to understanding, validating, and securing AI-driven decisions, helping organizations ensure reliability, compliance, and performance at scale. However, the volume and complexity of AI telemetry are overwhelming legacy tools ...
For years, secure connectivity has relied on a familiar pattern: route traffic back to centralized gateways, inspect it, and then allow access. This model worked when applications lived in a handful of data centers and users were largely confined to offices. That model is now under strain. Applications are distributed across clouds, users connect from everywhere, and real-time workloads demand performance that centralized inspection points struggle to deliver. As traffic volumes grow and latency expectations shrink, routing everything through a small number of control points has become both a performance bottleneck and a resilience risk. The future of secure connectivity requires a different approach ...
The AI experimentation phase is over, and the private cloud is where enterprise AI workloads are being deployed for security and scale, according to Private Cloud Outlook 2026, a new report from Broadcom ... 2026 marks an acceleration into a full AI tipping point. The shift is being shaped by three forces — costs, complexity, and control — that public cloud environments are increasingly failing to address for production AI at scale. Key findings from the report include ...
44% of organizations have reported an outage in the past year tied to suppressed or ignored alerts, and 78% had at least one incident where no alert was fired at all ... Engineers learned about failures from customers. That gap between what our tools report and what our customers experience is the problem DevOps teams have been quietly solving with GenAI tooling, even as most enterprises continue to run their NOCs on manual alert triage ...
Cloud outages are usually described as technical failures. When a service goes down, a dependency breaks, or a region has issues, the focus immediately shifts to infrastructure. But if you look closely at how these incidents actually unfold, the root cause is rarely the technology itself. It is almost always tied to decisions made earlier, during design, implementation, or day-to-day operations. The system behaves the way it was built. The real question is how it was built ...