Efficient multi-provider agent environments with AI gateways: best practices
Organizations are increasingly using multiple models to build AI agents in order to find the best balance of performance and cost for each agentic task and LLM call. As we…
-
-
Why “good enough” observability fails in the age of agentic AI
Agentic AI is breaking the mold of what organizations need from observability. Fragmented, correlation-dependent observability platforms are no longer “good enough.” Enterprises with dynamic, hybrid environments require observability that provides…
-
Evaluate LLM and agent quality in Dynatrace AI Observability
AI applications fail in ways that differ from traditional software. They can return responses quickly, with no errors, and still deliver answers that are inaccurate, ungrounded, unsafe, or unusable. That’s…
-
Making agentic token costs visible in production
In some organizations, high token counts have become a proxy for productivity. Some engineering teams are being pushed to max out context windows and wire in sprawling tool sets. More…
-
Dynatrace Release Radar 06.26
This series covers recent Dynatrace releases and updates, focusing on what’s new, what’s changed, and how these recent enhancements can benefit you and your organization. Each post covers newly available…
-
LLM evaluations as a foundation for trustworthy agentic AI systems
Large language models and agents are rapidly transforming how organizations build software, automate workflows, and interact with data. From copilots to autonomous agents, AI-powered systems are increasingly responsible for answering…
-
Debug and evaluate your AI app from your coding agent with Datadog Agent Observability
Coding agents like Claude Code, Cursor, and Codex CLI handle the coding parts of building an AI application well. The harder work comes after: understanding why a response went wrong,…
