The Christmas elves have been busy packing their sleigh with shiny new features announced at Ignite this year. We will take you through the sparkling baubles of delight that already have your data users demanding more. As the users unwrap the delights of AI driven trumpets the parents in governance look on with dread. Laura and Claire will with a mix of entertaining Christmas themed demos will show off some of the "brilliant" new features including plenty of Agents and AI doing "magic" across your data. Do not fear though we will include how and where switches are to turn off, control and audit what chaos the new toys bring. Demos and Laughter, we will break things so you don't have to! There will be a prize for the best Christmas jumper worn to our session!

Talk by Shubhangi Goyal at Admiral Group.

The latest version of OpenSearch introduces powerful new features and tools that enable us to build AI-powered assistants capable of interacting not only with our data, but also with cluster configurations and even the external world. We’ll explore how these capabilities open the door to intelligent agent-based systems that can reason, retrieve, and act. We'll walk through how to combine OpenSearch with modern AI tools, like LLMs, agents, and orchestration frameworks, to create assistants that can autonomously diagnose issues, generate insights, or even automate operational tasks.

Connecting Fabric data with LLM-based agents

Agents are powerful—but without feedback, they're flying blind. In this talk, we’ll walk through how to build self-improving agents by closing the loop with evaluation, experimentation, tracing, and prompt optimization. You’ll learn how to capture the right telemetry, run meaningful tests, and apply insights in a way that actually improves performance over time. Whether you’re building copilots, chatbots, or autonomous workflows, this session will give you the practical tools and architecture patterns you need to make your agents smarter—automatically.

Intel session on building AI assistants and agents in the enterprise.

Self-paced: Functions, Tools, and Agents with LangChain.

Exploring LangChain tools and agents.

There will be some Python, but Python is kind of a neutral language and I'm not overly concerned about coding details.