Operations | Monitoring | ITSM | DevOps | Cloud

This article is part of our series on how Datadog engineering teams use LLM Observability to build, monitor, and improve AI-powered systems. At Datadog, we’re always looking for ways to make complex data easier to explore.

Sometimes the most interesting engineering stories don’t start with a roadmap or a release plan—they start with personal taste. A preference for good design. A frustration with clunky tools. A desire to see everything in one place.

InfluxDB 3 Model Context Protocol (MCP) server lets you manage and query InfluxDB 3 (Core, Enterprise, Dedicated, Serverless, Clustered) using natural language through popular LLM tools like Claude Desktop, ChatGPT Desktop, and other MCP-compatible agents. The setup is straightforward. In this article, we will focus on setting up InfluxDB 3 Enterprise using Docker with Claude Desktop.

The Optus CEO resigned in 2023 after a routine software upgrade killed emergency services for an entire day. Two years and $12 million in fines later, the exact same failure happened again. Same root cause, same chaos, different executive taking the fall. Governance expert Helen Bird's diagnosis was surgical.

The inevitable happened. A while back, Gartner projected that in 2026, 30–50% of all new SaaS product features would use LLM inference. That meant OpenAI-style costs would become a standard part of SaaS COGS. Today, OpenAI has become one of the most operationally significant line items for SaaS companies. But for many teams, this creates an uncomfortable gap. Engineering sees OpenAI as a fast path to innovation.

Financial services AI demands more than models and prompts. Context engineering provides real-time, governed, and explainable intelligence with Elastic serving as the foundational context layer. Artificial intelligence in financial services is no longer constrained by model capability. The real bottleneck is context.