Datadog introduced three new AI agents that perform interactive investigations and asynchronous code fixes for development, security and operations teams.
The launch of the Bits AI SRE, Bits AI Dev Agent and Bits AI Security Analyst agents, alongside the new Proactive App Recommendations and APM Investigator capabilities, marks the continued evolution of Bits AI, Datadog’s generative AI assistant that helps engineers resolve application issues in real time.
Datadog’s new domain-specific AI agents, unveiled at DASH, are each trained to be experts in incident response, product development and security. The agents are built on a flexible system of shared tasks—core capabilities such as querying data, analyzing anomalies or scaling infrastructure that can be reused across agents. The architecture allows Datadog to build and deploy new agents quickly while maintaining a consistent and powerful user experience. This is combined with expansive, high-quality observability data, enabling Datadog’s AI capabilities to operate with context and precision, and deliver insights and actions to eliminate risk.
“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. “With these advancements in AI reasoning and multi-modality, we’ve gone beyond helping organizations understand their availability, security, performance and reliability. We now enable human-in-the-middle workflows by guiding customers on what to look for and where to start looking, and augment their ability to take action.”
The new AI agents announced at DASH are:
- Bits AI SRE, a 24x7 on-call responder that is now in Limited Availability. For all alerts, Bits AI SRE performs early triage using telemetry and service context to surface initial investigation findings all before responders log in. It assigns appropriate owners, aligns all parties with real-time incident summaries and status updates, and proactively suggests next steps. It also generates a first draft of the incident post-mortem to save responders time.
- Bits AI Dev Agent, now in Preview, which detects issues, generates code fixes, and opens pull requests tailored to organizations’ technology stack to allow users to quickly review and merge changes directly within their SCM. As a result, engineers don’t just have software that surfaces errors—they have an AI teammate that helps fix the issue and improve productivity for human resources.
- Bits AI Security Analyst, which autonomously triages Cloud SIEM (security information and event management) signals, conducts in-depth investigations of potential threats and delivers reasoned resolution recommendations without human prompting. Bits AI Security Analyst, now in Preview, automates investigations and reduces response times, fundamentally transforming how organizations process security signals.
Additional Applied AI capabilities in preview include:
- Proactive App Recommendations, which continuously analyzes telemetry Datadog already collects to suggest high-impact fixes and the next best action. Whether it’s optimizing a slow query, addressing inefficient code paths or catching recurring exceptions, APM Recommendations shows developers exactly where to improve performance, reduce errors and cut down resource usage—all before users are affected.
- APM Investigator, to help engineers troubleshoot and resolve latency spikes faster. It automates a previously manual process by identifying bottlenecks, scoping impact, highlighting patterns across slow traces, suggesting likely causes and proposing a fix.
The Latest
IT organizations have historically measured success by how quickly they can respond when something goes wrong. The entire discipline of Incident Management has been optimized around mean time to resolution, first-response SLAs and ticket closure rates. But new research suggests that even though this is a well-executed playbook, it's no longer enough to retain customers ...
Production incidents rarely announce themselves as database problems. They appear as slow transactions, timeouts, rising response times, or an application struggling under a workload it previously handled. APM provides an essential starting point. It can identify a slow transaction path, highlight an affected service, and show that a database dependency is consuming more time than expected. But identifying the database as part of the problem is not the same as explaining what is happening inside it ...
Cloud teams are under constant pressure to reduce spend without slowing development or increasing operational risk. They are deploying autoscalers, rightsizing workloads, enforcing resource requests, reviewing utilization dashboards, and building FinOps processes around cloud-native environments. Yet the results often disappoint ...
Ask most IT leaders about their biggest concern with AI and you'll hear the same answer: hallucinations ... Today, however, the conversation has shifted ... As organizations move beyond chatbots and experiments, they are increasingly deploying AI agents that perform multi-step tasks. These systems retrieve documents, query databases, call APIs, generate reports, write code, and make recommendations. The issue is not whether the model can reason. The issue is whether the organization can see, verify, and govern the decisions being made along the way ...
While organizations want to take control of their telemetry, building telemetry pipelines from scratch can be a very daunting, complicated task, even when leveraging open-source standards like OpenTelemetry. It requires specialized knowledge across distributed systems, data engineering, and security. This fragmented approach across systems causes higher operational costs; it puts a strain on resources and reduces efficiency as teams have to work with different interfaces and processes ...
For decades, enterprise networks were designed around a simple assumption: work happened inside the office. Applications lived in centralized data centers, employees connected through internal infrastructure, and security focused on protecting the perimeter that surrounded everything ... But the way organizations operate today bears little resemblance to that environment. Cloud platforms host critical applications, employees connect from homes and airports as often as they do from offices, and partners collaborate through shared systems that exist far beyond corporate walls. In short, the corporate network no longer resembles the environment it was designed to protect ...
As an analyst who researches how IT organizations design, build, and operate their networks, I find that network data is a constant source of pain. Network teams struggle with data quality, fragmentation, authority, access, and trust. And these issues undermine everything they try to do. Here are the numbers: Only 45% of network teams are completely confident in the accuracy of their network source of truth, which documents the intent of their network ...
The 2026 Global Data Center Survey from Uptime Institute reveals an industry navigating workforce constraints, escalating outage expenses, even as rising costs remain the top concern for management teams ...
The next observability gap may not be in the code. It may be under the rack. That sounds strange until you think about how AI incidents actually feel in the middle of an investigation ... The application dashboard may be accurate. It may also be stopping at the wrong boundary. AI systems depend on software, but they also depend on a dense physical stack: racks, power paths, thermal margin, maintenance activity and, in many environments, liquid cooling. Those physical dependencies can change slowly before they look like a software incident ...
Certificate expiration is the rare outage you can see coming. Every TLS certificate carries the date it stops working, so the moment it will begin breaking connections is knowable in advance. That's what makes an expired certificate such a frustrating way to lose a service. What's changing now is how often that date comes around ...