惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

V
V2EX
aimingoo的专栏
aimingoo的专栏
S
SegmentFault 最新的问题
博客园_首页
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
IT之家
IT之家
博客园 - 【当耐特】
月光博客
月光博客
C
Check Point Blog
T
The Blog of Author Tim Ferriss
罗磊的独立博客
博客园 - Franky
MongoDB | Blog
MongoDB | Blog
H
Help Net Security
Microsoft Security Blog
Microsoft Security Blog
B
Blog
阮一峰的网络日志
阮一峰的网络日志
腾讯CDC
美团技术团队
N
Netflix TechBlog - Medium
Stack Overflow Blog
Stack Overflow Blog
Y
Y Combinator Blog
L
LangChain Blog
The Cloudflare Blog

Datadog | The Monitor blog

Introducing our open source AI-native SAST Instrument and monitor Boomi integration flows with OpenTelemetry and Datadog Not all index scans are equal: How we cut query latency by over 99% Platform engineering metrics: What to measure and what to ignore Integrate Recorded Future threat intelligence with Datadog Cloud SIEM CI/CD security: threat modeling using a MITRE-style threat matrix CI/CD security: How to secure your GitHub ecosystem Ingress NGINX is EOL: A practical guide for migrating to Kubernetes Gateway API Operating agentic AI with Amazon Bedrock AgentCore and Datadog LLM Observability: Lessons from NTT DATA Introducing the Datadog Code Security MCP Capture and analyze custom heatmaps in Session Replay Understand session replays faster with AI summaries and smart chapters Monitor ClickHouse query performance with Datadog Database Monitoring How we designed empathetic alert sounds for on-call engineers Search and act across Datadog to resolve issues faster with Bits Assistant Measure the business impact of every product change with Datadog Experiments Analyzing round trip query latency Configuring JavaScript caches for better performance Introducing Bits AI Dev Agent for Code Security Datadog achieves ISO 42001 certification for responsible AI Monitor Nutanix clusters, hosts, and VMs with Datadog Monitor Juniper Mist in Datadog A new Host Map for modern infrastructure Annotate traces to improve LLM quality with Datadog LLM Observability What’s new in Cloud SIEM: AI-powered investigations, enhanced threat intelligence, and scalable security operations Explore Kubernetes with native OpenTelemetry data Monitor Oracle Fusion Cloud Applications with Datadog Announcing the Datadog Terraform provider v4.0.0 Scaling Kubernetes workloads on custom metrics How to design cloud environments for AI-powered threat analysis
Automate Cloud SIEM investigations with Bits AI Security ...
2025-06-10 · via Datadog | The Monitor blog
Vera Chan

Vera Chan

Ron Feldman

Ron Feldman

Rex Guo

Rex Guo

Security analysts face unprecedented challenges in today’s cloud landscape. Security operations center (SOC) teams are chronically understaffed, and cybersecurity threats are skyrocketing—further intensified by GenAI-driven attacks. High false positive rates add to this strain, fueling alert fatigue and delaying the detection of real threats. These hurdles make it harder for analysts to keep pace, which ultimately drives up mean time to resolution (MTTR).

Datadog Cloud SIEM has continually evolved to help SOC teams meet these challenges with powerful investigative capabilities, including:

Bits AI Security Analyst, announced in Preview in June 2025, is now generally available. Bits AI has investigated tens of thousands of security alerts for Preview customers, saving hundreds of person-years of manual investigation time. It autonomously triages Datadog Cloud SIEM signals, conducts in-depth investigations of potential threats, and delivers clear, actionable recommendations without human prompting.

This is one of three AI agents, each designed to support cross-functional roles across security, SRE, and development. Since its launch, Bits AI has expanded its capabilities to support DevOps by investigating alerts, managing incidents, resolving coding errors, and more. With Bits AI Security Analyst, we’re taking Cloud SIEM to the next level by fundamentally transforming how security teams investigate and resolve security signals.

Let’s take a closer look at how Bits AI Security Analyst works.

Autonomous Cloud SIEM triage

Bits AI asynchronously investigates SIEM signals across the following attack surfaces and sources (additional surfaces and source coverage coming soon):

CategoryTools / Services
Cloud Control PlaneAWS CloudTrail, Azure, GCP, Kubernetes
IdentityOkta, Entra ID, Google Workspace
SaaS and CollaborationMS365, Google Workspace
Dev ToolsGitHub, Snowflake
Endpoint Detection and Response (EDR)SentinelOne
EmailUser-reported phishing

Each investigated signal is clearly marked with a dedicated facet, allowing you to filter the Cloud SIEM Signals list or trigger targeted notifications. To view a finding, just click the signal in the list or notification to open the Bits AI investigation side panel. In the following screenshot, Bits AI automatically investigated actions taken by an authorized Okta administrator, without human intervention.

Datadog Bits AI security analyst for Okta phishing.

In-depth, evidence-based investigations

Bits AI Security Analyst draws on the expertise of Datadog’s internal Security and Security Research teams. Using the MITRE ATT&CK framework as a foundation, the agent methodically plans and executes each step of its investigation, adapting its approach based on observed evidence. It also expertly pivots between indicators of compromise (IOCs) and pulls in relevant data from across the Datadog platform by querying historical signals and logs, linking to those queries, and providing clear, contextual analysis.

After completing its investigation, Bits AI provides one of the following verdict recommendations:

  • Benign: No security concern detected
  • Suspicious: Requires further investigation

In the following screenshot, Bits AI Security Analyst investigated endpoint alerts, classified them as benign based on historical patterns of legitimate Kafka operations, and surfaced all of that context as part of its in-depth analysis.

Datadog Bits AI security analyst for EDR.

Bits AI Security Analyst will provide the same detailed analysis for suspicious activity, such as user-reported phishing attempts. As seen in the example signal below, it confirmed that a reported email was worth investigating further based on activity consistent with common phishing tactics.

Datadog Bits AI security analyst for user reported phishing.

The agent’s reasoning at each step of its investigation and its final conclusions are thoroughly evaluated for reliability. Bits AI Security Analyst has been rigorously tested against historical datasets containing both benign and malicious signals to ensure its efficacy—and we’re continuously refining its accuracy over time.

Once you review a security signal, you can archive it, declare an incident for further investigation, edit suppressions, or run a workflow. Each option gives you a different way to respond, from archiving benign activity to automatically remediating the issue. For example, you can suspend a user flagged as suspicious by Bits AI Security Analyst by running a workflow directly from within the security signal.

Cloud SIEM showing actions you can take on a signal.

Automate investigations with Bits AI Security Analyst

Bits AI Security Analyst is now generally available. Activate it in-app to get started or explore the documentation to learn more.

New to Datadog? Start a free 14-day trial to take advantage of autonomous Cloud SIEM investigations.