Datadog enhances AI agent reliability and security with new observability tools

By Beth Pariseau, Senior News Writer
Published: 12 Jun 2025

NEW YORK -- As enterprises rapidly adopt generative AI, the need for reliable and secure agentic workflows has grown. Datadog has responded with a suite of new AI agent observability and security tools unveiled at its DASH 2025 conference. These include:

• Bits AI Security Analyst Agent: A preview release aimed at streamlining SecOps tasks.
• SRE Agent: Enhances incident investigation with multi-step reasoning and learning capabilities.
• LLM Observability: Features like Experiments for comparing AI models and AI Agent Monitoring for tracking automation workflows.
• AI Agent Console: Provides a unified view of internal and external agents, including governance data.

Customer Reactions and Concerns

Allen Cox, Senior Director of Security and IT at MyFitnessPal, shared mixed feelings during a breakout session. While Datadog's tools have simplified their security operations, Cox highlighted lingering trust issues:

"AI may give us an opportunity to expand the total range of things that we're choosing to alert on, but we have to rethink detection and response in that context."

Bert Stewart, Head of the Global Command Center for Thomson Reuters, praised the SRE Agent's speed but expressed concerns about pricing:

"It's very interesting stuff, but when things roll out from Datadog, you don't know how much it's going to cost."

Security Enhancements

Datadog also introduced:

• Sensitive Data Scanner: Prevents data leakage and poisoning attacks.
• Security Detections: For malicious models, prompt injections, and more (coming later in 2025).

Competitive Edge

Katie Norton, IDC analyst, noted Datadog's focus on runtime data sets it apart:

"AI apps aren't deterministic, so you need to have visibility into the runtime to secure them."

For more details, check out related articles:

• Alation boosts agentic AI with Numbers Station acquisition