Ken Exner, Elastic | AWS re:Invent 2025

Описание: In this interview during theCUBE's coverage of AWS re:Invent, Ken Exner, chief product officer at Elastic, joins theCUBE’s Jackie McGuire to discuss the critical shift from prompt engineering to "context engineering." Exner, an AWS veteran, details how Elastic is evolving its search, observability and security portfolio to support the rapid rise of agentic AI. The discussion centers on the necessity of grounding Large Language Models (LLMs) with precise, relevant data to ensure agents function correctly rather than operating on general knowledge. Exner emphasizes that while the industry is currently focused on deploying agents, the long-term success of these applications relies entirely on providing the right context through retrieval, memory systems and tool selection.

The conversation also explores the importance of open standards, particularly the Model Context Protocol (MCP), in fostering a unified ecosystem for AI development. Exner advocates for an open approach over walled gardens, highlighting how Elastic’s Agent Builder empowers developers to instantly create conversational agents on top of their data indices. From a security standpoint, the dialogue addresses the need to treat AI agents as new enterprise assets that require distinct observation and protection. Looking toward 2026, Exner predicts the industry will transition into the "year of context engineering," where Elastic aims to lead by combining deep search relevance with rigorous evaluation to ensure trustworthy AI performance.

Find more SiliconANGLE news and analysis https://siliconangle.com/
Follow theCUBE's wall-to-wall event coverage https://siliconangle.com/events/
Learn about the latest theCUBE events https://www.thecube.net/

00:00 - Intro
00:06 - The Beginning of Ken Exner's Journey: An Introduction and Welcome
02:42 - Ken's Role in Enhancing Observability at Elastic
05:02 - Engineering AI: Contextual Understanding and the Role of Predictive Systems
08:44 - Building Reliable AI: From Elastic Agents to Accurate Outputs
11:02 - The Need for Standards in AI
13:25 - Advancements and Future Prospects in Dynamic AI Systems

#theCUBE #AWSreInvent #theCUBEresearch #Elastic #ContextEngineering #AgenticAI #GenerativeAI