Elastic integrates with Azure AI Foundry for real-time monitoring
Elastic has announced a new integration with Azure AI Foundry to provide developers and site reliability engineers with real-time monitoring capabilities for agentic AI and large language model workloads.
The integration allows enterprises deploying AI for critical applications to address common issues including uncontrolled token consumption, latency challenges, and compliance concerns. With Elastic's solution, users have access to pre-built dashboards designed to display model usage, performance data, cost tracking, and content filtering, all within a consolidated interface.
Observability for AI agents
According to Elastic, the integration delivers observability tools that enable practitioners to monitor and optimise the performance of AI agents built on Azure AI Foundry. These tools provide insights into generative AI and agentic AI operations, intended to support the development of reliable and secure intelligent agents operating on the Azure platform.
Site reliability engineers and developers can now access real-time data on the status of their artificial intelligence workloads. Performance bottlenecks, cost drivers, and compliance issues can be identified and addressed promptly.
"Agentic AI is only as strong as the models and infrastructure that power it," said Santosh Krishnan, general manager, Observability & Security at Elastic. "With Elastic and Azure AI Foundry, developers and SREs gain clear visibility into how their agents are performing, understand the drivers of cost, and fix performance bottlenecks in real time. That means they can scale AI applications faster without compromising reliability, compliance, or budget."
Elastic's integration includes pre-configured dashboards that present real-time insights. These dashboards are designed to facilitate both rapid troubleshooting and ongoing optimisation of AI-enabled solutions.
Monitoring and scalability
The uptake of agentic AI in enterprise environments has been accompanied by increased attention to the practical management of AI resources, including monitoring token usage and ensuring systems meet reliability and compliance requirements. The integration is intended to provide a unified view of these areas to improve operational efficiency and reduce risk.
"This integration with Elastic delivers real-time visibility into token usage, latency, and costs, with built-in safeguards for any model hosted in Azure AI Foundry," said Amanda Silver, corporate vice president at Microsoft Azure CoreAI. "Developers can now build and scale agents on Azure AI Foundry with the operational clarity and control they need to succeed in production."
The availability of unified monitoring and reporting enables development teams to build AI agents that are better aligned with organisational budgets, policy requirements, and reliability standards. With these features, teams are better equipped to make evidence-based decisions as they expand their use of AI in mission-critical contexts.
Integration availability
The Elastic Azure AI Foundry integration is currently available as a technology preview within the Elastic Observability suite. This early access phase allows users to test the solution's capabilities within their own environments before wider release.
