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

酷 壳 – CoolShell
酷 壳 – CoolShell
H
Hacker News: Front Page
P
Palo Alto Networks Blog
T
ThreatConnect
Apple Machine Learning Research
Apple Machine Learning Research
博客园_首页
T
True Tiger Recordings
P
Privacy & Cybersecurity Law Blog
B
Blog
IT之家
IT之家
Last Week in AI
Last Week in AI
F
Full Disclosure
Hacker News: Ask HN
Hacker News: Ask HN
C
Comments on: Blog
Microsoft Azure Blog
Microsoft Azure Blog
C
Cybersecurity and Infrastructure Security Agency CISA
Microsoft Security Blog
Microsoft Security Blog
博客园 - 【当耐特】
N
News and Events Feed by Topic
NISL@THU
NISL@THU
腾讯CDC
雷峰网
雷峰网
Security Latest
Security Latest
李成银的技术随笔
M
Microsoft Research Blog - Microsoft Research
L
LangChain Blog
L
Lohrmann on Cybersecurity
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
C
Check Point Blog
Y
Y Combinator Blog
Recent Announcements
Recent Announcements
博客园 - Franky
N
News | PayPal Newsroom
V
V2EX
A
About on SuperTechFans
The Register - Security
The Register - Security
月光博客
月光博客
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
Google Online Security Blog
Google Online Security Blog
MyScale Blog
MyScale Blog
Cisco Talos Blog
Cisco Talos Blog
Vercel News
Vercel News
WordPress大学
WordPress大学
C
Cyber Attacks, Cyber Crime and Cyber Security
The Hacker News
The Hacker News
IntelliJ IDEA : IntelliJ IDEA – the Leading IDE for Professional Development in Java and Kotlin | The JetBrains Blog
IntelliJ IDEA : IntelliJ IDEA – the Leading IDE for Professional Development in Java and Kotlin | The JetBrains Blog
爱范儿
爱范儿
A
Arctic Wolf
L
LINUX DO - 最新话题
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More

Datadog | The Monitor blog

Reduce CVE noise with OpenVEX assessments in Datadog How we made a SQL query optimization agent 59% more accurate using autoresearch and LLM Observability How to audit and clean up monitors effectively Diagnose slow PostgreSQL queries faster with explain plan correlation Explore Datadog metrics with Natural Language Queries Toto 2.0: Time series forecasting enters the scaling era Simplify micro-frontend observability with Datadog RUM Attribute AI costs across providers with Datadog Cloud Cost Management Diagnose and resolve database performance issues faster with Database Investigator Datadog for Government achieves FedRAMP® High certification Analyze cloud costs with flexible spreadsheets in Datadog Sheets Inside Datadog’s AI Research Lab: Meet two PhD candidates behind Toto Connect triage and investigation in a single workflow with Datadog Cloud SIEM This Month in Datadog - April 2026 Monitor and optimize Supabase query performance with Datadog Database Monitoring Add dynamically updating context to logs with Reference Tables and Observability Pipelines Introducing ARFBench: A time series question-answering benchmark based on real incidents The product signal latency gap slowing your growth Test network paths with TCP, UDP, and ICMP in Datadog Turn developer feedback into operational insight with Datadog Forms and Sheets How to investigate cloud credential compromise with Bits AI Security Analyst Evaluate, optimize, and secure your Google Cloud AI stack with Datadog Bringing observability data hosting to the UK on AWS Identify and fix code issues faster with Datadog’s Azure DevOps Source Code integration Steganography at scale: Embedding share URLs in Datadog widget screenshots Every team should be A/B testing Centralize observability management with Datadog Governance Console Spotting CI/CD misconfigurations before the bots do: Securing GitHub Actions with Datadog IaC Security Route OTel data from AI apps to ClickHouse and Datadog using Observability Pipelines Manage service tracing across hosts with Single Step Instrumentation rules Offline evaluation for AI agents: Best practices Detect runtime threats in Python Lambda functions with Datadog AAP 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 How we built a real-world evaluation platform for autonomous SRE agents at scale 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 When upserts don't update but still write: Debugging Postgres performance at scale 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 Monitor Aruba Central in Datadog How we centralize and remediate risks with Datadog Case Management Accelerate incident response with Datadog and ServiceNow Monitor your application and network load balancer logs Understanding Karpenter architecture for Kubernetes autoscaling Tools for collecting metrics and logs from Karpenter Monitor Karpenter with Datadog What your product data is actually saying Key metrics for monitoring Karpenter Securing Datadog's platform in the AI age: The role of observability data Closing the verification loop: Observability-driven harnesses for building with agents When an AI agent came knocking: Catching malicious contributions in Datadog’s open source repos Closing the verification loop, Part 2: Fully autonomous optimization Four ways engineering teams use the Datadog MCP Server to power AI agents Approaching your observability migration with the right mindset Meet the new Bits AI SRE: Deeper reasoning, twice as fast Designing MCP tools for agents: Lessons from building Datadog's MCP server Key learnings from the 2026 State of DevSecOps study Use plain English to query your multi-cloud infrastructure in Resource Catalog Simplifying troubleshooting across the user journey with Datadog Synthetic Monitoring Protect your OCI resources with Datadog Cloud Security This Month in Datadog - February 2026 Fine-tune Toto for turbocharged forecasts Amazon EC2 security: How misconfigured and public AMIs expand your cloud attack surface Enable end-to-end visibility into your Java apps with a single command Measure and improve mobile app startup performance with Datadog RUM Evaluating our AI Guard application to improve quality and control cost Identify untested code across every level of your codebase Make use of guardrail metrics and stop babysitting your releases Monitor Versa Networks SD-WAN performance in Datadog How we reduced the size of our Agent Go binaries by up to 77% Improve performance and reliability with APM Recommendations Remediate transitive vulnerabilities faster with Datadog Software Composition Analysis Generate audit-ready vulnerability and compliance reports with Datadog Sheets Monitor Fortinet FortiManager performance in Datadog Improve test coverage across codebases with Datadog Code Coverage
Introducing Bits AI SRE, your AI on-call teammate
2025-06-10 · via Datadog | The Monitor blog
Kai Xin Tai

Kai Xin Tai

Editor’s note: We’ve continued to expand the capabilities of Bits AI SRE since its launch. To learn more about the latest enhancements, explore our related posts.

Getting paged pulls engineers away from meaningful work, yet incident response in many organizations remains manual, reactive, and draining. An alert fires and teams scramble to find the root cause, relying on siloed knowledge, incomplete context, and a few on-call experts who are already stretched thin. The rise of AI coding agents has only intensified this challenge: As teams ship code faster with less human oversight, production systems grow increasingly complex and harder to understand. More deployments mean more alerts, edge cases, and unexpected failures. Traditional incident response simply cannot keep up in this new reality.

Today, we’re announcing the general availability of Bits AI SRE, an autonomous AI teammate that’s always on call and built for the most complex environments. Bits works completely autonomously, without requiring any initial prompting to begin its work. By the time you get to your laptop after being paged, it has often already identified a likely root cause and even proposed a code fix. Bits reasons like your most senior SRE: It reads the same telemetry, understands the topology of your systems, and follows your runbooks. But unlike a human, it can explore exponentially more hypotheses in parallel to converge on the root cause far faster than any individual could.

In building a truly capable SRE agent, data is the defining factor. To operate effectively in real production environments, these agents must handle the same kinds of messy, high-stakes, interconnected problems that engineers face every day. That meant grounding Bits in how real systems behave, rather than abstracted examples or synthetic failure modes. Datadog processes data from tens of thousands of organizations across every industry, architecture, and scale, capturing a wealth of telemetry as well as critical metadata that provides context. This combination provides Bits an exceptionally deep understanding of how real systems behave. Paired with the unique agentic architecture we’ve built, Bits can reason like an expert SRE: forming hypotheses, understanding how services interact, cutting through noise to pinpoint root causes, and identifying fixes faster than a human ever could.

In this post, we’ll cover how Bits AI SRE’s agentic model of on-call response helps you scale your operations and give engineers time back to do what they love most: building and shipping great software.

Autonomous alert investigation

When an alert fires, Bits AI SRE immediately launches an investigation. It starts by gathering context by reading the monitor message, checking linked Confluence runbooks, referencing past investigations of the same monitor, and running exploratory queries across your environment.

Based on what it learns, Bits dynamically generates multiple root cause hypotheses and tests them by querying data across your environment and reasoning over the results. Like an engineer scanning dashboards, analyzing logs and traces, or checking recent changes and Kubernetes events, Bits performs these steps using purpose-built tools. At each step, it decides which tool to call and what additional data to fetch.

Bits methodically invalidates hypotheses without supporting evidence and digs deeper into promising leads. Each hypothesis is classified as validated, invalidated, or inconclusive, enabling teams to quickly see what’s confirmed, what’s ruled out, and where further investigation is needed. What once took more than 30 minutes of manual triage now happens automatically, often before you’ve even opened your laptop.

Now, speed is only part of the story. Bits is a reasoning agent that learns from every investigation. It draws on memory from past alerts to recognize patterns and accelerate investigations. You can correct Bits when it makes a mistake or reinforce its conclusions when it gets them right. Every investigation becomes a feedback loop, making Bits faster, smarter, and more aligned with how your team works.

When Bits identifies a likely root cause, it shares its findings—complete with supporting evidence—back to Slack, so engineers can quickly review or build on the analysis. In addition to Slack, Bits is natively integrated into the Datadog mobile app, On-Call, and Case Management (fully synced with ServiceNow and Jira), ensuring collaboration continues seamlessly across the tools you rely on for your on-call operations.

Slack message from Bits AI SRE

Last but not least, you can chat with Bits to ask clarification questions about an investigation, request further analysis on certain steps, retrieve service ownership details, query additional telemetry, assess customer impact through RUM, or search documentation, all in natural language. Because Bits has full context of both the investigation and your Datadog environment, it responds with rich widgets and citations to the exact points in the investigation it references, making it easy to verify and trust its answers.

Chat with Bits AI SRE to add context that improves investigations

New capabilities, now in preview

Since our limited availability earlier this year, thousands of organizations have used Bits AI SRE in production, and feedback has been overwhelmingly positive. Many customers have highlighted Bits’ ability to identify root causes in minutes, and in some cases, prevent incidents entirely.

Today, we’re extending Bits’ capabilities along three dimensions that reflect where we’re taking the product next: going deeper into remediation, expanding the surface area for launching investigations, and connecting proactive detection with immediate root cause analysis. These features are now in private preview, which you can sign up to try:

  • Generate code fixes: Once Bits AI SRE identifies a code-related root cause, the Bits AI Dev Agent takes over to propose a fix. Engineers can review and merge the resulting pull request directly, resolving the issue from end to end without starting from scratch.
  • Investigate synthetic API test failures: Run autonomous investigations on failing synthetic API tests to quickly pinpoint what’s breaking and why.
  • Start investigations from APM latency graphs and APM Watchdog stories: Not every issue is triggered by an alert. You can now launch investigations directly from latency graphs on the APM service page and from APM latency Watchdog stories.
  • Recommended actions: Bits AI SRE now suggests next steps based on its findings and lets you execute triage actions, like sending summaries to Slack or creating Jira tickets, with a single click.

Bits AI SRE reimagines the way you run operations

Bits AI SRE introduces a new way to operate production systems, one designed for the scale, speed, and complexity of AI-augmented software delivery. Like a true teammate, Bits deeply understands your systems, analyzes telemetry in real time, applies structured reasoning, and continuously learns from every investigation. Unlike simple chat-based assistants that require you to prompt your way to a root cause, Bits operates as a deep research agent, independently performing complex, multi-step root cause analyses across your entire stack. By automating the heavy lifting of investigation, Bits bridges the gap between human reasoning and AI-scale complexity, keeping pace with the velocity of modern software delivery. And because it takes on the most time-consuming parts of on-call work, engineering teams save meaningful time every single day.

Get started with Bits AI SRE today. If you don’t already have a Datadog account, sign up for a 14-day free trial.