Lightning Lessons

Agentic Search: Are LLMs Replacing Decades of IR Wisdom?

Hosted by Jon Handler and Trey Grainger

Thu, Oct 16, 2025

6:00 PM UTC (1 hour)

Virtual (Zoom)

Free to join

177 students

Invite your network

Go deeper with a course

AI-Powered Search
Doug Turnbull and Trey Grainger
View syllabus

What you'll learn

How Agents are disrupting IR (Information Retrieval)

Do decades of search best practices still apply? Yes (but not all of them)! Learn what's being disrupted and what stays.

See how Agentic Search is implemented

Agentic workflows invert the control flow of search by providing tools to LLMs. See how this paradigm works end-to-end.

Optimizing search for agents (and agents for search)

Agents have different needs than humans, but the end goals are often the same. Learn how to optimize for each.

Why this topic matters

AI Agents are LLM-backed modules that can use tools (MCP, OpenSearch, etc.) and reason about your data and search results. They choose the strategy and sequencing of the tools, whose results can lead to accurate, informative answers to user questions. Are agents better than humans at finding these answers? Better put: when will agents surpass humans at finding the information we need?

You'll learn from

Jon Handler

Building OpenSearch at AWS; Author of "The Definitive Guide to OpenSearch"

Jon Handler is Senior Principal Solutions Architect at Amazon Web Services based in Palo Alto, CA. Jon works with OpenSearch and Amazon OpenSearch Service, helping customers who have vector, search, and log analytics workloads that they want to move to the AWS Cloud. Prior to joining AWS, Jon’s spent four years coding a large-scale, eCommerce search engine. Jon holds a BA from the University of Pennsylvania, and an MS and a Ph. D. in Computer Science and Artificial Intelligence from Northwestern University.

Trey Grainger

Founder @ Searchkernel, Author, "AI-Powered Search"

TREY GRAINGER is author of the book AI-Powered Search and is the founder of Searchkernel, a software company building the next generation of AI-powered search. He is an advisor to several startups and adjunct professor of computer science at Furman University. He previously served as CTO of Presearch, a decentralized web search engine, and as chief algorithms officer and SVP of engineering at Lucidworks, an search company whose search technology powers hundreds of the world’s leading organizations.


Trey is an instructor of Maven's AI-Powered Search course.

Built search at

OpenSearch Project
Amazon Web Services
Searchkernel
CareerBuilder
Lucidworks

Sign up to join this lesson

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