跳到正文
SiliconANGLE· Duncan Riley·· 6 小時前AI 評分40

groundcover 推出 Agent Investigations,讓 AI 智能體與工程師共用工作區

Groundcover launches Agent Investigations, a shared workspace for AI agents and engineers

AI 導讀

可觀測性公司 groundcover 推出 Agent Investigations,讓其 AI 智能體、團隊的編碼智能體及當值工程師協作處理生產事故。Investigator agent 會以日誌、指標、追蹤資料及 Kubernetes 數據測試問題與假設,Moderator agent 則審核結論是否有證據支持。

正文

Groundcover launches Agent Investigations, a shared workspace for AI agents and engineers

Avatar photo

Observability company groundcover Inc. today announced the launch of Agent Investigations, a shared workspace designed to allow groundcover’s artificial intelligence agents, a team’s own coding agents and on-call engineers to work production incidents together.

Agent Investigations is aimed at the problem of scattered findings as AI agents take on a bigger role in incident response. When production goes down, several engineers often point their own agents at the same issue, with each agent working in isolation, according to the company. What those agents conclude, it says, is end up in private chats, tickets or Slack messages out of view of the rest of the team.

Investigations in the new workspace are started automatically by groundcover once a monitor issue opens. Engineers also have the option to launch one manually from the groundcover interface or from a button in Slack.

On groundcover’s side, the work is split between two agents. The first, known as the Investigator agent, is said to build a graph of questions and hypotheses before testing each one against groundcover’s logs, metrics, traces and Kubernetes data. Supporting graphs are attached to each of its findings.

Reviewing every proposed conclusion is the job of the second, a Moderator agent. The Moderator, which is the only agent allowed to close a hypothesis, sends back any claim that lacks supporting findings. Doing so is said to separate generating a possible explanation from validating whether the evidence actually supports it.

Ending each hypothesis is a structured assessment that either supports or refutes it. The company claims teams get a set of tested answers to read through instead of pages of generated text.

Agent Investigations also offers access for outside agents, including Anthropic PBC’s Claude Code and OpenAI Group PBC’s Codex, through groundcover’s Model Context Protocol server. Connected agents can read from and contribute to the same investigation, with agents used for business intelligence and product roadmapping also able to take part. In October, groundcover launched agent-to-agent observability tools that let outside coding agents hand production investigations to its own agent.

Hypothesis status and assessments post to the Slack thread tied to the original alert. With replies posted in that thread also fed back into the investigation, engineers are able to steer the work from inside the incident conversation.

“Every engineer now has an agent, but each of those agents investigates on its own and findings end up in a chat window,” said co-founder and Chief Executive Shahar Azulay, who started groundcover in 2021 with Yechezkel Rabinovich. “Agent Investigations gives humans and agents one place to work an incident, where every hypothesis is tested against production data and every conclusion has to be backed by evidence.”

Omer Mayer, senior product manager at groundcover, said the wait while agents are working and the on-call engineer has nothing to look at is often “the hardest stretch of an incident.” Engineers using Agent Investigations instead get to watch, he said, as each hypothesis is supported or ruled out in real time.

The graph the Investigator builds also serves as the record, said to show how a team reached the root cause, including the hypotheses that were ruled out along the way. According to the company, keeping the monitor, Slack thread, investigation and conclusion linked means nobody has to piece the history back together from separate tools after an incident closes.

Powering the investigations is the full-fidelity telemetry collected by groundcover’s sensor. Because groundcover uses a bring-your-own-cloud architecture, the data remains in the customer’s own cloud account even while agents are querying it.

Agent Investigations is available to groundcover customers whose backends have AI enabled. The company will demonstrate it at Amazon Web Services Inc.’s re:Invent conference in Las Vegas Nov. 30-Dec. 4.

Groundcover has raised $160 million to date, including a $100 million Series C round led by One Peak in July.

Image: groundcover

A message from John Furrier, co-founder of SiliconANGLE:

Support our mission to keep content open and free by engaging with theCUBE community. Join theCUBE’s Alumni Trust Network, where technology leaders connect, share intelligence and create opportunities.

  • 15M+ viewers of theCUBE videos, powering conversations across AI, cloud, cybersecurity and more
  • 11.4k+ theCUBE alumni — Connect with more than 11,400 tech and business leaders shaping the future through a unique trusted-based network

SiliconANGLE Media is a recognized leader in digital media innovation, uniting breakthrough technology, strategic insights and real-time audience engagement. As the parent company of SiliconANGLE, theCUBE Network, theCUBE Research, CUBE365, theCUBE AI and theCUBE SuperStudios — with flagship locations in Silicon Valley and the New York Stock Exchange — SiliconANGLE Media operates at the intersection of media, technology and AI.

Founded by tech visionaries John Furrier and Dave Vellante, SiliconANGLE Media has built a dynamic ecosystem of industry-leading digital media brands that reach 15+ million elite tech professionals. Our new proprietary theCUBE AI Video Cloud is breaking ground in audience interaction, leveraging theCUBEai.com neural network to help technology companies make data-driven decisions and stay at the forefront of industry conversations.

來源:SiliconANGLE · siliconangle.com