Twenty-minute conversations with the people building AI search in production. Start with the latest below, or jump to the topic that matters most to you.

Season 2

Season 2: Episode 1

Relevance is Your Moat

As AI gets more capable, its answers still depend on what it can find. Vespa CEO and cofounder Jon Bratseth explains why relevance goes beyond ranking to become a lasting competitive advantage. He also covers why agents need more than vector search, and how to deliver expert-level precision at the latency and throughput agents demand.

Season 1

Seven conversations on how search is changing for generative AI: vector databases, RAG, vision-language models and real-world migrations, with voices from GigaOm, Vinted, Searchplex and more.

Season 1: Episode 7

How Hidden Search Problems Derail Great Products

When a product falls short, teams often blame performance or design, but the real problem is search. Ravindra Harige, founder of Searchplex, explains why search problems so often get misdiagnosed, how frontend, backend and DevOps roles obscure the need for search expertise, and what it takes to build search that works.

Season 1: Episode 6

From Pilots to Precision: RAG and Search in Life Sciences

AI is changing life sciences, though not always the way people expect. Harini Gopalakrishnan, former Global CTO of Life Sciences at Snowflake and now at Vespa, breaks down where pharma and biotech are really using AI, from drug discovery and clinical trials to regulatory submissions and commercial launches.

Season 1: Episode 5

GigaOm's CXO Brief: Search Reimagined for AI Workloads

Whit Walters, Field CTO at GigaOm, walks through GigaOm’s new CXO Decision Brief on the future of search and AI infrastructure. Learn how delayed modernization turns technical debt into competitive debt, what makes a pilot succeed, and how to prepare teams for AI-native platforms.

Season 1: Episode 4

Beyond Chat: The Hidden Use Cases Driving the GenAI Revolution

Kamran Khan, CEO of Pureinsights, draws on decades in enterprise search to trace its evolution from keyword search to hybrid, vector and multimodal search. He explains how RAG and agentic AI are reshaping enterprise applications well beyond the chatbot.

Season 1: Episode 3

From Minutes to Milliseconds: Vinted's Migration to Vespa

Ernestas Poškus, Engineering Manager at Vinted, Europe’s largest platform for secondhand fashion, explains why Vinted moved its search from Elasticsearch to Vespa. Learn how the migration solved scaling challenges, cut infrastructure costs, and improved both query and indexing latency, all while serving more than a billion items.

Season 1: Episode 2

The Future of RAG: Search, Vision Language Models, and Agentic Workflows

Bonnie Chase sits down with Jo Kristian Bergum to trace the shift in information retrieval: from keyword matching to hybrid search to vision-language models (VLMs). Learn how ColPali and other VLM-based methods enable retrieval across PDFs, scanned documents and visual-heavy manuals, and what that means for agentic workflows.

Season 1: Episode 1

The Rise of Vector Databases

Whit Walters, Field CTO at GigaOm, breaks down GigaOm’s Sonar Report on vector databases and why it named Vespa both a Leader and a Fast Mover. Learn what sets Vespa apart, from an architecture that runs data, indexes, metadata and ML inference on the same nodes to its performance at scale.