groundcover announced expanded support for Amazon Bedrock and Bedrock AgentCore.
Engineering and AI platform teams can now monitor Bedrock foundation models and agentic workflows with the same real-time, code-free visibility that groundcover already delivers for OpenAI, Anthropic and other leading AI providers.
groundcover captures telemetry at the kernel layer, which allows teams to trace every Bedrock model invocation without SDKs or instrumentation, giving organizations a unified and standards-based view of model behavior, agent decisions, performance and cost across the full AI stack.
Deep visibility across Bedrock and AgentCore:
- Real-time Bedrock observability. groundcover automatically detects every Bedrock model interaction, including parameters, inputs and outputs, token counts, finish reasons, latency and errors. Teams can troubleshoot quality issues, investigate performance bottlenecks and correlate model behavior with upstream and downstream services.
- Full transparency for AgentCore workflows. With AgentCore, organizations build production-grade agents that coordinate tools, access data and take complex actions. groundcover reveals decision paths, tool usage, multi-step reasoning and failure points, helping teams debug faster and increase reliability for agentic systems.
- Native GenAI telemetry. All GenAI telemetry data, including prompts, tool calls and model parameters, integrates cleanly into existing tracing and metrics systems with no custom plumbing.
- Unified AI and cloud observability. LLM traces and AgentCore telemetry sit alongside service traces, logs, infrastructure metrics and network data in a single platform. Engineers can correlate Bedrock spikes with EKS rollouts, application deployments or traffic changes and can trace requests end to end through microservices into an agent or model call.
- Cost and performance clarity for Bedrock workloads. groundcover enriches token usage and latency with EKS and workload context. Teams can see which services or environments drive Bedrock spend, track consumption trends and identify optimization opportunities. Alerts help prevent unexpected usage and cost spikes before they escalate.
- Enterprise-grade privacy with bring your own cloud. All telemetry remains in the customer’s environment. Sensitive content can be masked while preserving metadata for analysis, allowing regulated industries to monitor AI workloads without exposing prompts or responses outside their cloud.
“As AI applications shift from simple prompts to complex agentic systems, observability becomes essential for reliability and cost management,” said Orr Benjamin, VP of Product at groundcover. “Support for Amazon Bedrock and AgentCore brings our zero-instrumentation approach to one of the most important platforms in enterprise AI. Teams can now run agents and foundation models with full transparency and no disruption to their code.”
“Teams adopting Bedrock and AgentCore are moving fast, but they still fly blind when it comes to what their AI workloads actually cost,” said Shahar Azulay, CEO and co-founder at groundcover. “We talk to engineers every week who get hit with shocking overages from legacy observability tools because the pricing is opaque, unpredictable and punishes scale. With our Bedrock support running entirely in the customer’s cloud, they gain real transparency and full visibility into token usage, latency and spend without the fear of surprise bills. Observability should empower innovation, not penalize it.”
Support for Bedrock model invocation is available now.
The Latest
Two years ago, almost every customer conversation about AI started with the same questions: Which model should we use? What can it do? Is it ready for the enterprise? Today, those discussions have moved on. CIOs are far more interested in how to govern AI, integrate it with existing systems, prepare their workforce and make it part of everyday operations. The challenge is no longer to prove that AI can deliver value. It's instead about how to embed AI into the business in a way that's secure, scalable and delivers measurable outcomes ...
Two things happened to production incidents between 2023 and now, and they did not happen at the same speed. The first is that a class of dependency that barely existed three years ago now accounts for one incident in ten. Incidents disclosed by AI model and AI application providers rose from 1.7% of all disclosed unplanned incidents in 2023 to 10.7% in 2026 year to date, roughly a sixfold rise; that counts only incidents at AI companies themselves, so the true share is higher. The second is that the time to close an incident has not come down ...
When an AI assistant gives an incomplete or incorrect answer, teams often blame the model. They adjust prompts, switch models, increase context windows or test a new retrieval strategy. However the model may not be a problem. In many enterprise AI workflows, the problem begins inside the document-ingestion pipeline ...
If you talk to any security or observability teams right now, they're all fighting the same fire: their tooling was built to ingest X, but their sources are pumping Y and soon to be doing Z. The knee-jerk reaction is always the same: we need more platform. However, this reaction is wrong. Let me explain why, because the solution to this problem is foundational, not financial. Instead of hurling yet more money at the problem, make sure you've done what's needed upstream ...
Rapid AI adoption and the unique ways AI workloads operate is redefining the scope and structure of what these teams must deliver. This shift is forcing organizations to rethink how they manage scale, automation, and control, according to The State of SRE and Platform Engineering 2026, a new report from Dynatrace ...
AI is usually talked about as a software tool, but it also depends heavily on the network behind it. Whether a company is using AI for chatbots, automation, monitoring, analytics, or employee support, all of that information has to move across the network in a reliable and secure way. That means AI is not just an application decision. It is also an infrastructure decision. Before organizations rush into AI, they should ask a simple question: Is our network ready to support it? ...
Enterprise AI often lacks governed access to where business processes actually execute. Without that access, AI agents may be able to reason, but they cannot operate reliably across enterprise workflows. For AI agents to effectively carry out workflows, they will require integration-layer context and controls. Organizations can implement these prerequisites by providing AI with managed access to the middleware layer ...
Enterprise networks rarely behave the same way for very long. A routing adjustment in one region may unexpectedly alter application performance in another. A cloud migration may introduce hidden dependencies that go unnoticed until an outage occurs. All the while, the network is managed by several different teams, each of whom use different tool sets — and as a result, have different views of the network ... There’s usually an engineer who remembers why traffic fails over a certain way between sites, or which transparent firewall was added where. The problem is that human memory cannot scale alongside enterprise-scale networks ...
Ask an infrastructure team how confident they are in their ability to govern AI, and most will tell you they've got it handled. A recent survey of 406 IT decision-makers and platform engineering leaders found 86% expressing exactly that confidence. Ask the same group whether they have a formal written AI governance policy, and the number drops to 30%, according to Spacelift's Infrastructure Automation Report ...
In MEAN TIME TO INSIGHT Episode 27, Shamus McGillicuddy, EMA VP of Research, Network Infrastructure and Operations, and Parker Hathcock, EMA Research Director covering IT Service/Operations (ServiceOps), discuss observability unification in modern IT operations ...