Enterprise search technology provider Elastic N.V. today announced a new feature that automates the development of custom data integrations and accelerates security information and event management onboarding with artificial intelligence.

Called Automatic Import, the new feature, claimed to be the only one of its kind for a security analytics or SIEM solution, adds custom data sources faster than existing security solutions, reducing the import time from several days to less than 10 minutes, providing broader visibility and more straightforward SIEM implementation.

Automatic Import applies generative AI to expedite labor-intensive security operations tasks, building on existing Elastic AI-driven security analytics offers such as Elastic AI Assistant, which answers security questions and guides practitioner workflows and Attack Discovery, which automates alert triage. With the new service, Elastic can mitigate the security challenges intrinsic to fast-changing environments and messy data due to the ability to handle unstructured data at scale and surface relevant insights via large language models and retrieval-augmented generation.

Powered by the Elastic Search AI Platform, Automatic Import provides model-agnostic access to harness the knowledge from LLMs and the ability to ground answers in proprietary data using RAG. Under the hood, the service is powered by Search AI Lake and Elastic’s existing expertise in allowing security teams to leverage data of any kind.

“Establishing visibility across an enterprise IT environment is inherently difficult, but no matter how the attack surface changes, security teams can’t afford to fly blind. Until now, onboarding custom data has been costly and complex,” said Mike Nichols, vice president of product for security at Elastic, explains. “Automatic Import arrives at a critical moment to address these challenges, as organizations explore replacement options for their legacy SIEM tools.”

Elastic Security ships with more than 400 prebuilt data integrations and Automatic Import makes it practical to extend visibility beyond these to an evolving array of security-relevant technologies and applications. The company said the integrations normalize data to Elastic Common Schema, enabling uniform analysis with dashboards, search, alerting and machine learning.

Automatic Import lunches with support for Anthropic models via Elastic’s connector for Amazon Bedrock. The service also supports JSON and NDJSON-based log formats.

Image: Elastic