1 min read
Add as a preferred source on Google

Groundcover Launches Shared Workspace for AI Incident Investigations

Agent Investigations connects groundcover’s AI agents, external coding agents and on-call engineers. The company plans a demonstration at AWS re:Invent in Las Vegas Nov. 30-Dec. 4.

Hands connect evidence cards beside an open laptop in a dim operations center / TokenPost.ai
Hands connect evidence cards beside an open laptop in a dim operations center / TokenPost.ai

Groundcover launched Agent Investigations, a shared workspace where AI agents and on-call engineers can investigate production incidents together, keeping evidence and findings in one place.

Investigations can begin automatically when a monitoring issue opens. Engineers can also start one from groundcover’s interface or a Slack button.

The company’s Investigator agent builds a graph of questions and hypotheses, then tests them against logs, metrics, traces and Kubernetes data. A Moderator agent reviews proposed conclusions and returns claims that lack supporting evidence. Each hypothesis receives an assessment that supports or refutes it.

Teams can connect coding agents, including Claude Code and Codex, through groundcover’s Model Context Protocol server. Those agents can read from and contribute to the same investigation. Updates appear in the Slack thread associated with the alert, and replies in the thread feed back into the investigation.

Groundcover says customer telemetry stays in the customer’s cloud account under its bring-your-own-cloud architecture. Groundcover customers with AI-enabled backends can use Agent Investigations.

The company plans to demonstrate the product at Amazon Web Services’ re:Invent conference in Las Vegas Nov. 30-Dec. 4.

Simon Yoon

Reporter

Simon Yoon reports on blockchain technology for TokenPost. Send corrections or tips to info@tokenpost.com.

Loading…