Integrate Elastic AI Assistant for Security via API to advance SOC workflows

Since releasing Elastic AI Assistant for Security, we’ve received overwhelmingly positive feedback from our customers. Elastic AI Assistant is helping security operations teams investigate and respond to threats faster by providing deep security expertise. Building on that momentum, we’re excited to announce the availability of chat and management APIs for Elastic AI Assistant in Elastic Security 8.15. These new APIs allow users to automate interactions with Elastic AI Assistant, manage conversations and anonymization settings, and more.

Integrating the API translates theoretical benefits into real-world advantages. Here are several scenarios where Elastic AI Assistant can be used:

• Streamline threat management: Automate monitoring, analysis, and response to threats to enhance speed and accuracy.

• Enhance operational workflows: Integrate Elastic AI Assistant into security operations processes to streamline decision-making without manual input.

• Ensure compliance and privacy: Anonymize sensitive data automatically to support compliance with regulations.

The release also embeds Elastic AI Assistant in the detection rule creation workflow. Should you encounter any errors as you craft a query, you can open the assistant to get help diagnosing and correcting those errors.

We also made significant improvements to Attack Discovery:

• You can now run Attack Discovery in the background and return to view the results later.

• It’s now possible to run Attack Discovery across different LLMs simultaneously, simplifying comparison of generative AI models.

• Attack Discovery results are persisted and saved and won’t be lost if you close your browser session. This also means they are available to view and reference outside of the Attack Discovery UI (should you wish to add them to a custom dashboard, for example).

• We’ve honed the output of lower-cost models to improve accuracy.

The release and timing of any features or functionality described in this post remain at Elastic's sole discretion. Any features or functionality not currently available may not be delivered on time or at all.

In this blog post, we may have used or referred to third party generative AI tools, which are owned and operated by their respective owners. Elastic does not have any control over the third party tools and we have no responsibility or liability for their content, operation or use, nor for any loss or damage that may arise from your use of such tools. Please exercise caution when using AI tools with personal, sensitive or confidential information. Any data you submit may be used for AI training or other purposes. There is no guarantee that information you provide will be kept secure or confidential. You should familiarize yourself with the privacy practices and terms of use of any generative AI tools prior to use. 

Elastic, elasticsearch, ESRE, elasticsearch Relevance Engine and associated marks are trademarks, logos or registered trademarks of elasticsearch N.V. in the United States and other countries. All other company and product names are trademarks, logos or registered trademarks of their respective owners.