_(1).jpg)
Elastic has announced a new integration with Microsoft's Azure AI Foundry, bringing comprehensive observability to large language models (LLMs) and agentic AI applications. This collaboration provides developers and site reliability engineers (SREs) with the tools to monitor, optimize, and ensure the reliability of intelligent agents built on the Azure platform. The integration addresses critical challenges like uncontrolled costs, latency issues, and compliance needs in production AI environments.
Elastic is integrating its observability platform with Microsoft's Azure AI Foundry.
The solution provides real-time monitoring for LLMs and agentic AI applications.
It offers pre-built dashboards for tracking token usage, latency, costs, and content filtering.
The goal is to help developers identify performance bottlenecks and control spending.
This enables faster scaling of AI applications with greater reliability and built-in guardrails.
The integration is currently available in a tech preview for Elastic Observability.
As organizations deploy agentic AI for mission-critical tasks, they often encounter obstacles such as spiraling token costs, unpredictable latency, and compliance blind spots. Elastic's integration directly tackles these issues by delivering a unified view into model performance and resource consumption. This operational clarity is essential for managing and scaling complex AI workloads effectively.
The partnership is focused on empowering teams to build with confidence. Santosh Krishnan, General Manager of Observability & Security at Elastic, stated, “Agentic AI is only as strong as the models and infrastructure that power it. 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." This sentiment was echoed by Microsoft's Amanda Silver, Corporate Vice President at Azure CoreAI, who said, “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."
By providing deep insights into the inner workings of AI agents, this integration marks a significant step towards mature, production-ready AI operations, allowing businesses to innovate faster while maintaining control over performance and budget.
Elastic, the Search AI Company, integrates its deep expertise in search technology with artificial intelligence to help everyone transform all of their data into answers, actions, and outcomes. Elastic's Search AI Platform — the foundation for its search, observability, and security solutions — is used by thousands of companies, including more than 50% of the Fortune 500. Learn more at elastic.co.
Elastic and associated marks are trademarks or registered trademarks of elasticsearch BV and its subsidiaries. All other company and product names may be trademarks of their respective owners.
TechIntelPro empowers B2B technology decision-makers with the latest industry trends, deep insights, leadership perspectives and actionable intelligence to drive both organizational and professional milestones—and thrive on the tech pulse.