Operations | Monitoring | ITSM | DevOps | Cloud

With Datadog GPU Monitoring, engineering and ML teams can monitor GPU fleet health across cloud, on-prem, and GPU-as-a-Service platforms like Coreweave and Lambda Labs. Real-time insights into allocation, utilization, and failure patterns make it easy to spot bottlenecks, eliminate idle GPU spend, and resolve provisioning gaps. By tying usage metrics directly to cost and surfacing hardware and networking issues impacting performance, Datadog helps teams make fast, cost-efficient decisions to keep AI workloads running reliably at scale.

While observability practices have evolved in recent years, they have largely focused on application services and infrastructure. Yet it is data what powers our applications, businesses, and AI models. When data issues occur, the consequences can be far reaching, from poor product experiences to billing errors to misinformed AI outcomes. In this session, Jonathan Morin, Group Product Manager at Datadog, shares real-world examples of incidents and explains how data observability can address them, helping teams detect issues earlier, reduce costly downtime, and restore trust in their data.

Fast front-end and back-end code alone won’t guarantee low end-to-end latency as hidden bottlenecks in the database can undermine even the best engineering efforts. In this session, Oleksii Serhiienko, Senior Site Reliability Engineer at GetYourGuide, will share how his team put database performance at the center of their monitoring strategy. He will highlight how they identified and fixed slow queries, uncovered load balancing issues that drove significant cost savings, and built monitoring practices that improved both reliability and investigation workflows.

When your logs don’t follow a standard format, it can be difficult to extract valuable information, like key-value pairs and nested JSON objects. Grok parsing lets you define flexible patterns that match unstructured log data so you can extract specific fields to query, filter, and visualize. In this video, you’ll learn how to: By refining your Grok parsers, you can make your logs more useful for analytics, dashboards, or alerts, and get even more value from your logs.

Get a first look at Datadog’s biggest product reveals from DASH 2025. Meet Bits AI SRE, your 24/7 autonomous AI Site Reliability Engineer, Flex Frozen for up to 7 years of managed log retention, and GPU Monitoring for full visibility into your AI workloads. Experience the future of observability in action.

Rivian makes electric vehicles to advance its mission to keep the world adventurous forever. As software defined vehicles, Rivian’s R1T and R1S are connected to the cloud from day 1, and telemetry data is at the heart of enabling mobile notifications, remote diagnostics, fleet management, and more. With so many critical pipelines in the cloud, observability is a top priority for the data platform.

In this short demo, see how Datadog Feature Flags help teams release new functionality safely and efficiently. Datadog provides advanced targeting, progressive rollouts, and automatic rollbacks — all integrated with powerful observability data. Learn how you can use simple on–off flags or multi-variant configurations to test and deploy features with confidence. With built-in monitoring of key guardrail metrics, Datadog can automatically pause or reverse rollouts when issues are detected, keeping your releases stable.

AI capabilities are advancing faster than ever — transforming how teams design, build, and ship intelligent products. In this teaser from Building Successful AI-powered Products at Datadog DASH, experts discuss the rise of agent-based systems, evolving model capabilities, and how to stay ahead in the new era of automation.

Datadog is reimagining how engineers handle incidents—moving beyond simple alerts to an intelligent, voice-driven on-call experience. With Datadog On-Call, teams can acknowledge alerts, access runbooks, post to Slack, and collaborate in real time, all before even touching their computer. See how Datadog brings incident response, communication, and automation together so you can respond faster and keep customers informed.

See how you can gain insights into cloud costs by tracking OCI spend and easily comparing instance types in October’s episode of This Month in Datadog. Join us for a spotlight of Cloud Cost Management’s support for Oracle Cloud Infrastructure, and the product’s new feature, Instance Explorer, which enables you to visualize and easily compare the cost and performance of instances across AWS, Azure, and Google Cloud.