A live follow-up discussion to the groundbreaking benchmark study by data.world on the effectiveness of semantic layers on LLM accuracy.
On November 14th, Juan Sequeda and the data.world team dropped a bombshell paper that validates the intuition held by many—layering structured semantic knowledge on top of your data leads to much stronger ability to correctly answer ad-hoc questions about your organizational data with large language models.
Join Benn Stancil, co-founder of Mode and Field CTO at ThoughtSpot, Joel Labes, Senior Developer Experience Advocate at dbt Labs, and Juan Sequeda, Head of AI Lab at data.world for a live follow-up discussion decoding the findings of the study.
Topics of conversation will include:
An overview of the groundbreaking research from data.world
A recap of the additional test done by Joel and the team at dbt Labs to recreate this study
The tools that serve as a backbone for building and managing your semantic layer and analysis
The panel’s opinions on where we go from here