Hi to,

Logs, metrics, and traces work great — until an AI agent starts hallucinating or overconsuming. Join us live on July 22 as Dotan Horovits (CNCF Ambassador) and Rekha Thottan (AWS) walk through how to monitor traditional services and evaluate AI agent behavior in production using one open-source stack built on OpenSearch and OpenTelemetry. You'll learn:

• How OpenTelemetry extends beyond standard services to surface tool calls, LLM token usage, and agent reasoning steps alongside your application traces.
• How to use rate, error, and duration metrics and rich service maps to pinpoint application bottlenecks instantly.
• How Agent Health, an open-source evaluation framework, gives you a structured pre-production benchmark before rogue agent behavior becomes a production incident.
• What a unified open-source observability architecture looks like for teams managing both traditional infrastructure and AI workloads at scale.

Featured Webinars

The Kubernetes rightsizing trust gap: Why the stakes just got higher
Most platform teams know Kubernetes rightsizing automation is overdue, yet 71% still require human review for every change, and only 17% have reached continuous automated optimization. Watch on-demand for a practical look at how to move from advisory recommendations to continuous closed-loop optimization, without the all-or-nothing leap.

From silos to governance: Securing IT/OT data movement

When something moves across the IT/OT boundary without proper governance, you may not know about it until a regulator or an attacker finds it first. Watch on-demand to learn the fundamentals of IT/OT integration, where the security and compliance risks actually live, and how a managed file transfer architecture can replace fragile, ungoverned data movement.

Operationalizing AI in observability: from debugging to automated remediation

Engineering teams have more data than ever, but humans are still the bottleneck, manually stitching together logs and traces to find answers. Catch the replay for a practical look at how Datadog’s Bits AI moves teams from manual investigation to autonomous remediation.

Connect with The New Stack