Groundcover lets Claude and Codex hand production investigations to its own agent
Application observability startup groundcover Inc. today gave outside artificial intelligence coding agents such as Anthropic PBC’s Claude and OpenAI Group PBC’s Codex a way to hand production investigations to its own observability agent. The launch, which groundcover is calling agent-to-agent observability, is seeking to address what happens after code ships. Coding agents can already review…
Observability startup Groundcover has introduced a feature allowing AI coding agents, such as Anthropic's Claude and OpenAI's Codex, to investigate production incidents independently. This "agent-to-agent observability" enables the external agents to pull logs, traces, and Kubernetes events directly from Groundcover's Model Context Protocol tools.
For less specific issues, the agents can delegate the investigation to Groundcover through asynchronous Agent Tasks, with a job ID returned promptly. The investigation proceeds in the background, delivering findings later as a root cause analysis or a dashboard. The feature is integrated with Cursor and AWS's Kiro, and it extends to Groundcover's own systems, enabling engineers to steer investigations in real time or generate dashboards.
Groundcover's incident-thread feature, now available in Slack, allows the AI to treat conversation threads as context, drawing on connected systems like Linear and GitHub. The service operates on Groundcover's bring-your-own-cloud architecture, ensuring telemetry stays within the customer's cloud account and charging by the node, regardless of data volume.
Groundcover, a venture capital-backed startup, has raised $160 million to date and recently acquired Kubernetes resource optimization startup Wand Cloud Ltd.
Written by urgent.news from SiliconANGLE's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
