Datadog has introduced Agent Builder, a tool that allows users to create custom AI agents for automating complex workflows by leveraging Datadog's observability data and third-party signals. Instead of hardcoding numerous logic branches, these agents can analyze data, make decisions, and adapt to changing inputs in real time. The tool supports AI-driven orchestration for workflows that can intelligently react and scale with systems, offering seamless integration with Datadog's Action Catalog, which includes over 2,000 prebuilt actions for various services such as Kubernetes and cloud services. Agent Builder enables the automation of tasks like application error investigations, critical vulnerability responses, and service documentation updates, all without requiring custom code. By orchestrating agents to specialize in distinct steps of operational processes, teams can maintain automation efficiency and control, with all data, logic, and actions centralized within Datadog. Agent Builder is currently available in Preview, with early access provided to users through the Datadog platform.