Datadog | The Monitor blog

Datadog MCP Apps: Interactive experiences in AI workflows

Datadog’s new MCP Apps extend the Datadog MCP Server by integrating interactive UI elements, such as live graphs and monitor cards, directly into AI interfaces like Claude, Cursor,…

Monitor Claude Enterprise activity with Datadog Cloud SIEM

The Datadog Claude Compliance API integration enables security and compliance teams to monitor Claude Enterprise activity by ingesting and normalizing events such as sign-ins, admi…

Why AI code optimization needs production-grounded benchmarks

Datadog developed DODO, an LLM-driven optimizer designed to prevent coding agents from optimizing for inaccurate synthetic benchmarks by grounding them in real production telemetry…

Search and act across Datadog to resolve issues faster with Bits Chat

Bits Chat is a new natural language conversational interface for Datadog that allows engineers to search, visualize, and take action across telemetry sources via the web, mobile, a…

Give your AI agents live Datadog access from the command line

Pup CLI is a single-binary tool that provides AI agents and automation pipelines with secure, OAuth-scoped access to over 33 Datadog product domains. It optimizes agent workflows t…

Introducing Bits Agent Builder: Build agentic workflows for alert response and remediation

Datadog has launched Bits Agent Builder, a new tool that enables users to create custom, hosted AI agents capable of analyzing observability data and executing automated actions. B…

When failover isn’t safe: Building high-availability PostgreSQL on Kubernetes

During a simulated "gameday" failure, Datadog discovered that network latency caused PostgreSQL replication lag to exceed safety thresholds, preventing the system from safely promo…

From single pull requests to full software packages: Detecting malicious code at scale

The article describes the expansion of BewAIre, an LLM-based security system, from analyzing pull requests to scanning entire dependency packages for malicious code. The updated sy…

A deep dive into surfacing and fixing gaps in AWS data perimeter policies

This article examines the security gaps that arise when organizations rely on per-resource controls rather than organization-level policies to establish AWS data perimeters. Using …

How we cut Spark compute costs by 44% with agentic AI and Datadog Jobs Monitoring

To optimize a massive, high-cost Spark job, Datadog engineers developed an AI agent using Claude and Jobs Monitoring to bridge the gap between execution plans and application code.…

Migrate to Azure Managed Redis with Datadog and Eden

To mitigate the risks of migrating from Azure Cache for Redis to Azure Managed Redis, the article proposes a strategy using Datadog and Eden. Datadog provides the observability nee…

Monitor LLM routing with the Kubernetes Inference Extension

The Kubernetes Gateway API’s Inference Extension optimizes LLM serving by replacing generic HTTP load balancing with "inference-aware" routing that evaluates backend signals like K…