groundcover announced the general availability of groundcover AI Mode, a native AI capability designed to help engineering teams investigate production incidents and analyze infrastructure behavior directly inside their own cloud environments.
AI Mode runs natively within the customer’s own AWS infrastructure via Amazon Bedrock, ensuring that logs, traces, and production telemetry never leave the customer’s environment. By running the AI within the customer’s environment, teams can adopt AI-assisted troubleshooting without introducing new security, compliance, or data-governance risks. Customers pay Amazon Bedrock token costs directly with no groundcover markup and can set usage limits by user or team.
“The question every engineering team is asking is: how do we get the benefits of AI without handing our production data to another third party?” said Shahar Azulay, CEO and Co-founder, groundcover. “We built the answer. The agent runs inside your infrastructure. Full stop.”
AI Mode deploys on Amazon Bedrock inside the customer’s own AWS account, provisioned automatically during self-service onboarding. AI Mode never calls home. All investigation and analysis happen inside the customer’s environment, and organizations maintain full control over their telemetry and AI usage. Token quotas can be set per user or per team, the same predictable model engineering teams already understand from tools like Cursor.
“Companies struggle to move their workloads to use AI because of compliance. We basically brought AI to their environment. This is insane. This is huge,” said Yechezkel Rabinovich, Co-founder, groundcover.
Most AI agents built on observability platforms are limited by what developers have manually instrumented. If a service was never set up with OpenTelemetry, the agent can’t see it. groundcover deploys an eBPF sensor at the kernel level, automatically capturing telemetry without requiring any developer instrumentation. Every log, trace, metric and event is enriched with a cross-signal identifier at ingest, allowing the agent to automatically connect data across signal types.
The practical difference: groundcover AI Mode can answer questions that are structurally impossible with instrumentation-dependent approaches.
- How many databases am I running?
- Which services are talking to each other?
- What changed in this service’s traffic pattern in the last hour?
These types of questions typically require engineers to manually correlate information across multiple dashboards and telemetry sources.
“Once you give an agent access to eBPF data, you can answer questions that are simply impossible with OTEL,” Rabinovich said. “Just try asking ‘how many databases do I have?’ with manual instrumentation.”
AI Mode is accessible from any page in the product, context-aware of where the user is and what they’re looking at. Its output creates first-class groundcover assets, including dashboards, monitors, GCQL queries and OTTL pipelines, all of which live inside the same environment the user was already working in. Multiple AI Mode tabs allow parallel investigations. AI Mode works alongside Cursor and Claude Code as specialist tools when a root cause might be in the codebase.
“You have some companies that are looking at their AI agent as a separate product entirely,” said Orr Benjamin, VP Product Management, groundcover. “That’s the polar opposite of what we want to do. We want to blend the experiences so that traditional observability and AI meet, and asking AI Mode feels like an extension of the same experience.”
The groundcover AI Mode is generally available now.
The Latest
IT organizations have historically measured success by how quickly they can respond when something goes wrong. The entire discipline of Incident Management has been optimized around mean time to resolution, first-response SLAs and ticket closure rates. But new research suggests that even though this is a well-executed playbook, it's no longer enough to retain customers ...
Production incidents rarely announce themselves as database problems. They appear as slow transactions, timeouts, rising response times, or an application struggling under a workload it previously handled. APM provides an essential starting point. It can identify a slow transaction path, highlight an affected service, and show that a database dependency is consuming more time than expected. But identifying the database as part of the problem is not the same as explaining what is happening inside it ...
Cloud teams are under constant pressure to reduce spend without slowing development or increasing operational risk. They are deploying autoscalers, rightsizing workloads, enforcing resource requests, reviewing utilization dashboards, and building FinOps processes around cloud-native environments. Yet the results often disappoint ...
Ask most IT leaders about their biggest concern with AI and you'll hear the same answer: hallucinations ... Today, however, the conversation has shifted ... As organizations move beyond chatbots and experiments, they are increasingly deploying AI agents that perform multi-step tasks. These systems retrieve documents, query databases, call APIs, generate reports, write code, and make recommendations. The issue is not whether the model can reason. The issue is whether the organization can see, verify, and govern the decisions being made along the way ...
While organizations want to take control of their telemetry, building telemetry pipelines from scratch can be a very daunting, complicated task, even when leveraging open-source standards like OpenTelemetry. It requires specialized knowledge across distributed systems, data engineering, and security. This fragmented approach across systems causes higher operational costs; it puts a strain on resources and reduces efficiency as teams have to work with different interfaces and processes ...
For decades, enterprise networks were designed around a simple assumption: work happened inside the office. Applications lived in centralized data centers, employees connected through internal infrastructure, and security focused on protecting the perimeter that surrounded everything ... But the way organizations operate today bears little resemblance to that environment. Cloud platforms host critical applications, employees connect from homes and airports as often as they do from offices, and partners collaborate through shared systems that exist far beyond corporate walls. In short, the corporate network no longer resembles the environment it was designed to protect ...
As an analyst who researches how IT organizations design, build, and operate their networks, I find that network data is a constant source of pain. Network teams struggle with data quality, fragmentation, authority, access, and trust. And these issues undermine everything they try to do. Here are the numbers: Only 45% of network teams are completely confident in the accuracy of their network source of truth, which documents the intent of their network ...
The 2026 Global Data Center Survey from Uptime Institute reveals an industry navigating workforce constraints, escalating outage expenses, even as rising costs remain the top concern for management teams ...
The next observability gap may not be in the code. It may be under the rack. That sounds strange until you think about how AI incidents actually feel in the middle of an investigation ... The application dashboard may be accurate. It may also be stopping at the wrong boundary. AI systems depend on software, but they also depend on a dense physical stack: racks, power paths, thermal margin, maintenance activity and, in many environments, liquid cooling. Those physical dependencies can change slowly before they look like a software incident ...
Certificate expiration is the rare outage you can see coming. Every TLS certificate carries the date it stops working, so the moment it will begin breaking connections is knowable in advance. That's what makes an expired certificate such a frustrating way to lose a service. What's changing now is how often that date comes around ...