groundcover Expands Agent Mode, Allowing AI Agents to Act Across the Developer Toolchain

groundcover, the world’s leading bring-your-own-cloud (BYOC), eBPF and OpenTelemetry (OTel)-native observability platform, 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.

Also Read: AiThority Interview with Matej Bukovinski, Chief Technology Officer at Nutrient

Ever since teams began running observability platforms alongside ticketing systems, messaging tools, and coding agents, the data in each traditionally remained separate. An engineer triaging an incident in Slack had no direct visibility into what groundcover was showing, and a coding agent in Cursor had limited access to what was happening in production. Connectors change both.

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.”

Agent-Native Observability That Stays Where Your Data Lives

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.”

“We’ve been asking ourselves how to tie our dev pipeline to our observability data in a way that’s both practical and achievable,“ said Rafael Tovar, Cloud Lead Architect for Open Assessment Technologies Corp. “What we didn’t originally see was that the telemetry data we can afford to gather in groundcover was the critical driver for it to be practical. The structure of nodes-based pricing was the only way that scale of telemetry input is achievable.”

Also Read: ​​AI systems – Interoperable AI systems: Connecting models across platforms

[To share your insights with us, please write to psen@itechseries.com]