Better Agentic Search with Adaptive Relevance Pipelines

Hosted by Kevin Butler and Trey Grainger

Mon, Jun 15, 2026

4:00 PM UTC (1 hour)

Virtual (Zoom)

Free to join

Invite your network

Go deeper with a course

Save 25% til Sunday
AI-Powered Search: Modern Retrieval for Humans & Agents
Trey Grainger and Doug Turnbull
View syllabus

What you'll learn

Self-Improving Pipelines

Close the loop with LLM-as-judge signals, building an end-to-end adaptive search architecture

Agentic Document Augmentation

Supercharge indexing via the open source Lucille ETL framework to align your search engine and your agentic tooling.

Live Retrieval Diagnostics

Read signals like confidence gaps and score variance at runtime to drive quality gate retries

Why this topic matters

Agentic search is an exciting new frontier, but let’s move beyond just orchestrating retrievers post-query. By combining dynamic document augmentation during ingestion with live diagnostics like score variance and confidence gaps, you can create systems that adaptively refine queries and rerank results. Kevin will walk us through implementing this end-to-end, self-improving agentic search engine.

You'll learn from

Kevin Butler

Senior Search & AI Engineer at KMW Technology

Kevin Butler is a Senior Search and AI Engineer at KMW Technology, where he helps clients build production-grade search and agentic AI systems. He previously built search systems at Pinecone and Lucidworks.


His work centers on enterprise search, relevance engineering, and the intersection of LLMs with retrieval — from hybrid lexical/semantic pipelines to LangGraph-orchestrated agent workflows. Before consulting, Kevin spent 2.5 years as an early employee at Pinecone, where he developed a deep, hands-on foundation in production vector databases. He's a contributor to Lucille, an open-source Java ETL pipeline targeting Solr, OpenSearch, and Elasticsearch, and has years of experience tuning relevance for large-scale search systems. He recently presented "Adaptive Relevance with Agentic Search" at Haystack US 2026 — a layered lexical, semantic, hybrid, and reranker architecture benchmarked on the ESCI dataset — and spoke at the Optimized AI Conference in 2025. He writes regularly on agentic development workflows and AI-assisted engineering.

Trey Grainger

Author, AI-Powered Search

Trey Grainger is lead author of the book AI-Powered Search (Manning 2025) and founder of Searchkernel, a software consultancy building the next generation of AI-powered search. He also serves as a technical advisor at OpenSource Connections.


He previously served as CTO of Presearch, a decentralized web search engine, and as Chief Algorithms Officer and SVP of Engineering at Lucidworks, a search company whose technology powers hundreds of the world’s leading organizations. Trey is also co-author of the book Solr in Action (Manning 2014), as well as over a dozen other publications including books, journals, and research papers. Trey has 18 years of experience in search and data science focused on building self-learning search platforms integrating the most successful AI Search techniques.


Trey teaches AI Search in the course AI-Powered Search: Modern Retrieval for Humans & Agents with Doug Turnbull.

Previously at

Pinecone
Lucidworks
Presearch Community
Searchkernel
CareerBuilder
See all products from AI-Powered Search

Sign up to join this lesson

By continuing, you agree to Maven's Terms and Privacy Policy.