As organizations adopt AI agents, they introduce new attack vectors beyond infrastructure, including prompts, model context, and sensitive data flowing through telemetry between developer environments and cloud services. Security teams must balance innovation with control, as agents without proper safeguards can operate outside expected boundaries and introduce risk.

In this session, we’ll explore how Datadog AI Guard brings visibility and control to AI agents, enabling teams to safely scale them in production.This session will demonstrate how teams can:

• Monitor every prompt and tool call with full visibility into agent activity
• Detect prompt injection, jailbreaks, and unsafe behavior using multi-turn, full-context analysis
• Identify and redact sensitive data in real time to prevent exfiltration

Most importantly, you’ll learn how to layer in security guardrails to confidently expand agent usage without compromising control.