Elastic enhances AI observability with AWS integration

Elastic has announced a deepened collaboration with Amazon Web Services (AWS) by integrating AWS's generative AI services, particularly Amazon Bedrock, with its observability solutions.

This partnership enhancement sees Elastic providing large language model (LLM) observability support through Elastic Observability for Amazon Bedrock. Amazon Bedrock offers a range of high-performance foundation models from top AI companies, designed for the development of generative AI applications with security and privacy considerations.

The integration will provide Site Reliability Engineers (SREs) with comprehensive insights into the performance and utilisation of their Amazon Bedrock LLMs. This includes the ability to monitor invocations, errors, and latency metrics, enabling incident prevention and facilitating the identification of root causes to maintain optimal performance of generative AI applications. The use of Elastic AI Assistant, powered by Amazon Bedrock, also allows for detailed data analysis, the generation of insightful visualisations, and the provision of actionable recommendations to resolve issues efficiently.

Santosh Krishnan, General Manager of Security and Observability Solutions at Elastic, noted the growing importance of such capabilities. "As LLM-based applications are growing, it's essential for developers and SREs to be able to monitor, optimise, and troubleshoot how they perform," remarked Krishnan. "Today's integration simplifies the collection of metrics and logs from Amazon Bedrock, in turn streamlining the process of gaining valuable and actionable insights."

The support for Amazon Bedrock LLM visibility in Elastic Observability is available immediately, providing users with the tools needed to effectively manage their AI models. Elastic continues to position itself within the AI domain by enabling customers to utilise search, security, and observability solutions built on its platform.