How Elastic evaluates AI agents with LangSmith To improve their AI-powered Attack Discovery for threat detection, @Elastic implemented: 📊 Automated LLM evaluations: Shifting from manual checks to a robust, automated framework with LangSmith. 🔍 End-to-end observability: Tracing AI workflows using LangGraph + LangSmith for deep debugging. 🎯 Data-driven prompt tuning: Quantitative scoring to identify high-performing prompts and LLMs for specific tasks. Read more:

We’re adding a new section to @elastic’s HackerOne Bounty Program! Today, we’re opening our SIEM and EDR rules for testing. We’re excited to have another way to thank our community for their efforts on our #detectionengineering. Get more details here:

Security AI assistant from Elastic with Bedrock and @AnthropicAI — one of the models working really well for us in security. Full details and examples of the AI security assistant on #AWSreInvent — PK (@xeraa)

I'm hiring a Sr. Manager, Threat Detection at @elastic . Come help protect Elastic using the Elastic Stack! Remote in the U.S. Questions? You know where to find me.

Built on LangChain and LangGraph, check out how @elastic's AI Assistant can leverage custom knowledge sources to improve threat detection. In this blog post, walk through how to add a threat intelligence report PDF as custom knowledge and reference relevant information during an incident. Read the blog: