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.