From Data Pipelines to Agentic Applications: Deploying LLM Apps That Actually Work

About this episode

Spencer Cook discusses how enterprises are building practical AI systems using advanced data techniques.

Spencer Cook, Lead Solutions Architect at Databricks, joins to unpack how enterprises are moving beyond hype and building practical AI systems using vector search, RAG, and real-time data pipelines. He and John Kutay get into what it really takes to serve production LLMs safely, avoid hallucinations, and tie AI back to business outcomes—without losing sight of governance, latency, or customer experience. Follow Spencer on: LinkedInWhat's New In Data is a data thought leadership series hosted ...

People in this episode

Guest: Spencer Cook

Topics covered

• AI systems
• data pipelines
• vector search
• real-time data
• business outcomes
• governance
• customer experience

Keywords

• LLM
• vector search
• RAG
• data pipelines
• AI governance
• customer experience
• production LLMs

Mentioned in this episode

Organizations: Databricks

More episodes of What's New In Data

• Beyond Migration: How Microsoft and Striim Are Modernizing the Future of Databases Together · November 17, 2025 · 1h 5m
• From Turing to Tooling: How Businesses Really Win with AI with John K Thompson (University of Michigan) · November 12, 2025 · 49 min
• Strands Agents: A Model-Driven Approach to AI Agents with Clare Liguori (Senior Principal Engineer at AWS) · July 17, 2025 · 46 min
• From Compliance to Catalyst: How Parexel’s CIO Builds for Impact · June 26, 2025 · 44 min
• Joe Reis on Staying Grounded in a Fast-Moving Data World · June 13, 2025 · 58 min
• AI Meets Data Infrastructure: Cost, Performance, and What’s Coming Next — with Barzan Mozafari · June 5, 2025 · 39 min