Building a multimodal lakehouse for AI (w/ Chang She)

About this episode

Tristan Handy interviews Chang She about the intersection of analytics and AI engineering, focusing on LanceDB's innovative approach to building an AI-native lakehouse.

In this episode, Tristan Handy sits down with Chang She — a co-creator of Pandas and now CEO of LanceDB — to explore the convergence of analytics and AI engineering. The team at LanceDB is rebuilding the data lake from the ground up with AI as a first principle, starting with a new AI-native file format called Lance. Tristan traces Chang's journey as one of the original contributors to the pandas library to building a new infrastructure layer for AI-native data. Learn why vector databases alone aren't enough, why agents require new architecture, and how LanceDB is building a AI lakehouse for the future. For full show notes and to read 6+ years of back issues of the podcast's companion newsletter, head to https://roundup.getdbt.com . The Analytics Engineering Podcast is sponsored by dbt Labs.

People in this episode

Host: Tristan Handy

Guest: Chang She

Topics covered

• AI engineering
• data lake
• analytics
• vector databases
• infrastructure
• LanceDB
• Pandas

Keywords

• AI lakehouse
• LanceDB
• Pandas
• data engineering
• vector databases
• analytics

Sponsors

dbt Labs

Mentioned in this episode

Organizations: LanceDB, pandas

More episodes of The Analytics Engineering Podcast

• The Iceberg ecosystem today (w/ Anders Swanson) · March 8, 2026 · 55 min
• Apache Iceberg and the catalog layer (w/ Russell Spitzer) · January 25, 2026 · 53 min
• AI and the data lake (w/ Lauren Anderson) · January 11, 2026 · 54 min
• Inside Snowflake's AI roadmap (w/ Chris Child) · December 14, 2025 · 57 min
• Agentic coding in analytics engineering (w/ Mikkel Dengsøe) · September 7, 2025 · 44 min
• Under the hood of Apache Iceberg (w/ Christian Thiel) · August 24, 2025 · 56 min