Key Takeaways:

• Datadog launched three new domain-specific AI agents—Bits AI SRE, Bits AI Dev Agent, and Bits AI Security Analyst—to assist DevOps, development, and security teams
• Agents can perform immediate triage, suggest code fixes with automated pull requests, and investigate security alerts without human prompting
• Built on a shared agent framework and enriched with Datadog’s high-quality observability data, these agents offer context-aware insights and actions
• Datadog also previewed “Proactive App Recommendations” and “APM Investigator” to recommend fixes and identify performance bottlenecks early

At its DASH conference, Datadog unveiled an expanded Bits AI platform, introducing three specialized agents designed to improve incident response, repair code, and automate threat investigation. These agents are tailored for SREs, developers, and security professionals, respectively, and are grounded in Datadog’s extensive observability dataset—processing trillions of telemetry points daily.

“Datadog is uniquely positioned to deliver value with AI as a platform that has a wealth of clean, rich data-we process trillions of data points and are embedded in our customers’ critical engineering, developer and security workflows,” said Yanbing Li, Chief Product Officer at Datadog.”

Bits AI SRE (Limited Availability) acts as a 24/7 on-call responder. It performs early alert triage using telemetry and service context, surfaces summary reports, directs incidents to the right engineering teams, suggests remediation steps, and can even draft initial post-mortems.

Bits AI Dev Agent (Preview) goes a step further by diagnosing code issues, generating automated fixes, and creating pull requests tailored to an organization’s tech stack—offering engineers a collaborative AI “teammate.”

Bits AI Security Analyst (Preview) autonomously triages Cloud SIEM alerts, investigates potential threats, and provides remediation suggestions without requiring manual intervention. This aims to speed up security incident response and reduce analyst workload.

These agents are built atop a modular framework of shared task capabilities—such as data querying, anomaly analysis, and infrastructure scaling—allowing Datadog to quickly develop additional agents while maintaining consistency in functionality and experience.

Datadog also introduced two new applied AI tools in preview:

Proactive App Recommendations—Continuously analyzes observability data to suggest fixes, highlight inefficiencies, and flag recurring errors before they impact users.

APM Investigator—Automates the troubleshooting process by identifying latency spikes, pointing out bottlenecks, correlating error patterns, and recommending resolutions.

Datadog’s Chief Product Officer emphasized that Bits AI benefits from the richness of Datadog’s telemetry data. By providing what he described as “human-in-the-middle” workflows, the platform guides users through investigation and resolution, rather than simply delivering alerts.

The Bits AI suite exemplifies a trend toward AI-assisted resolution workflows that move beyond observability—into actionable automation. These offerings aim to reduce mean time to resolution, eliminate toil across teams, and align incident and security response with intelligent, data-driven decisions—all within a unified platform.

Learn how AI Agents can supercharge your company’s profits and productivity at TMC’s AI Agent Event in Sept 29-30, 2025 in DC.

Rich Tehrani serves as CEO of TMC and chairman of ITEXPO #TECHSUPERSHOW Feb 10-12, 2026 and is CEO of RT Advisors and is a Registered Representative (investment banker) with and offering securities through Four Points Capital Partners LLC (Four Points) (Member FINRA/SIPC). He handles capital/debt raises as well as M&A. RT Advisors is not owned by Four Points.

The above is not an endorsement or recommendation to buy/sell any security or sector mentioned. No companies mentioned above are current or past clients of RT Advisors.

The views and opinions expressed above are those of the participants. While believed to be reliable, the information has not been independently verified for accuracy. Any broad, general statements made herein are provided for context only and should not be construed as exhaustive or universally applicable.

Portions of this article may have been developed with the assistance of artificial intelligence, which may have contributed to ideation, content generation, factual review, or editing.