Kevin Butler
KMW, LLC., Senior Search and AI Engineer
Actions
Speaker Biography: Kevin M. Butler (kbutler@kmwllc.com)
Search and AI solutions expert with extensive experience in vector database technologies, search engines, and cloud platforms.
Rolling Your Own AI Applications in the Enterprise: 5 Key Lessons Learned
Abstract
We’re all watching in real time as the power of AI is rapidly changing the way we work. Enterprises hoping to take advantage of these capabilities face challenges such as access controls, customization, data migration costs, and how to measure success. This means that many enterprises are working to understand what tools to use to create their own AI solutions.
In this talk, we’ll take you on the journey of building an AI-powered conversational agent using the content from the best-selling AI Powered Search. We’ll discuss the hard-won insights learned from implementing conversational agents at scale in the enterprise. Attendees will gain practical insights into developing functional AI applications using open-source software and cloud-based tools tailored for enterprise needs. From handling raw data in a file system to deploying a fully operational conversational AI agent—and even more advanced AI solutions—this talk will outline essential steps, critical design choices, and key lessons learned from existing implementations.
Gain the upper hand in your next AI project by learning from our successes and (more importantly) our failures. You will leave this talk equipped with a tactical toolkit to navigate the complex landscape of AI integration. Whether you're a tech leader, developer, or innovation strategist, this session promises to revolutionize your approach to intelligent system design.
Agentic Search: reimagining search from ingestion to relevancy
Agentic search is an exciting new frontier, but most solutions focus only on what happens after the query arrives: agentic orchestration of retrievers, rewriting queries, reranking results. We'll go further: the same agent reasoning that adapts queries at runtime can also reshape what gets indexed and how. Using Lucille, an open source ETL framework, as the ingestion backbone, we'll show how agents can augment documents, analyze content for retrieval-relevant signals, and align the OpenSearch index with the agentic tooling that will query it. On the query side, we'll cover query understanding, adaptive hybrid search, query rewriting, and reranking driven by live diagnostics: confidence gaps, score variance, agent reasoning. And we'll close the loop with LLM-as-judge signals that flow back into ingestion decisions. Demos will draw from real use cases where retrieval problems unsolvable through query tuning alone became tractable by re-modeling the data with agentic help.
Attendees will gain a blueprint for building search systems that think end-to-end, from smarter indexing to self-improving retrieval and relevance, and the open source tools to start building one today.
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top