The Frontier of AI Search

Mon Jun 15·4:00 PM UTC

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

Trey Grainger

Author, AI-Powered Search

Wed Jun 17·4:00 PM UTC

Cross-encoders: An End-to-end Guide

Cross-encoders make for great re-rankers, because they capture many nuances of the query-to-document relationship. But they are expensive to run on a large number of documents! For best performance, you need to keep this computation close to the data, which is where Vespa is helpful. Radu will introduce cross-encoders and provide an end-to-end walk through of how to implement them for production.

You'll learn from

Radu Gheorghe

Software Engineer, Vespa.ai

Trey Grainger

Author, AI-Powered Search

Fri Jun 19·7:00 PM UTC

Real-time Query Refinement with Control Vectors

Semantic search on embeddings can return low precision results due to a lack of explicit filtering (as in lexical search). Can we solve this by letting users directly inject inclusions/exclusions and updated meaning into their query vectors? Piotr, Trey, & Philippe will introduce “control vectors” for vector search, showing the vector math, code, and a demo of a novel e-commerce search experience.

You'll learn from

Trey Grainger

Author, AI-Powered Search

Piotr Kobziakowski

AI Search Engineer specializing in search, analytics & personalization

Philippe Bouzaglou

Technical Founder at Vectra, the AI foundation model for e-commerce search

Mon Jun 22·5:00 PM UTC

Vectorless RAG with PageIndex

RAG too long has ignored document structure. The classic RAG stack assumes chunks + embeddings. Practitioners assume the best way to find what's relevant is through pure question-answering. Matt will share his work integrating PageIndex with OpenSearch, He'll share how PageIndex works and how he integrated integrated it alongside classic RAG.

You'll learn from

Matt Overstreet

Product Manager - IBM OpenSearch

Doug Turnbull

Co-Author AI Powered Search

Trey Grainger

Author, AI-Powered Search

Tue Jun 23·4:30 PM UTC

How OpenSearch is Evolving in the AI Era

Agents and assistants all depend on search to provide accurate, relevant information before generating a response. The demands on search systems are changing rapidly, and open source search platforms like OpenSearch must evolve to adapt to these needs. Jon and will discuss what the "future" of search engines may look like, and how OpenSearch is evolving to meet these needs.

You'll learn from

Jon Handler

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

Trey Grainger

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

Wed Jun 24·4:45 PM UTC

Vector search from zero to production at GitHub

Vector search looks easy in demos, but production scale exposes hidden failure modes: capacity planning, indexing bugs, quantization tradeoffs, sharding, and ranking quality. GitHub’s BBQ rollout is a useful case study in turning “just add vectors” into an operationally reliable semantic search system.

You'll learn from

David Tippett

Search Relevance @ Github

Trey Grainger

Author AI Powered Search

Doug Turnbull

Co-Author AI Powered Search

Thu Jun 25·5:00 PM UTC

Three Patterns for Better Agentic Search

Agentic search is only as good as the patterns underneath it. This talk covers three patterns that improve agentic search — and how to optimize each one. We'll look at approaches to offline digest and index creation, why progressive disclosure matters when designing a search experience, and how both shape the agentic tool loop.

You'll learn from

Adam Hevenor

CEO and Founder Hevmind

Doug Turnbull

Co-Author AI Powered Search

Trey Grainger

Author AI Powered Search

Fri Jun 26·4:00 PM UTC

You're solving the wrong problem with AI Search

Many teams waste time implementing AI Search solutions that solve the wrong problem. They keep rebuilding relevance when they have a catalog problem. They add vector search when there's a schema problem. They tune ranking, but have no signal. Every search failure belongs to a recognizable pattern, and this session gives you the diagnostic layer top search consultants learn, but most teams skip.

You'll learn from

Atita Arora

Search & AI Strategist - formerly Voyager Search, Qdrant, OSC, Lucidworks

Trey Grainger

Author, AI-Powered Search; Founder @ Searchkernel

Doug Turnbull

Co-author, AI-Powered Search

Mon Jun 29·5:00 PM UTC

Agentic search: can we just use grep?

When searching, agents make false assumptions about what our users think is relevant. Our fashionista users think “red shoes” should return high-heels. At our company ABE isn’t a president, it's an A/B testing tool. Agents need context to know these things - and context engineering needs agentic search. Guiding agents through context requires search. Let's walk through the core patterns.

You'll learn from

Doug Turnbull

Co-Author AI Powered Search

Trey Grainger

Author AI Powered Search

Tue Jun 30·4:00 PM UTC

The New Frontier of AI Search

Information Retrieval is advancing at an accelerating pace. In our month-long "AI-Powered Search: Modern Retrieval for Humans & Agents" course, we work hard to cover both the tried-and-true AI Search fundamentals and bring additional experts as guest instructors on emerging hot topics. This session is a survey of the latter - emerging topics you need to know about on the new Frontier of AI Search.

You'll learn from

Trey Grainger

Author, AI-Powered Search

Doug Turnbull

Co-author of AI-Powered Search