AI and SQL? Yes! Enable AI Using Only SQL Functions

What if AI didn’t require Python, notebooks, or ML pipelines?

In this session, we’ll use SQL AI Functions (ai_parse, ai_summarize, embeddings, and model calls) to build an AI-powered data pipeline using only SQL on Databricks.

This is a workshop and includes:

Parsing unstructured financial PDF statements

Using AI functions to extract entities, tables, and summaries

Calling different LLMs directly from SQL

Converting raw documents into clean, columnar analytical models

Querying AI-enriched data with standard SQL

This session shows how AI can be embedded directly into the data platform, making it accessible to SQL-first teams without sacrificing governance or performance.

Audience takeaway:
A practical blueprint for adding AI to existing SQL-based analytics workflows, no ML background required.

Practical understanding of how to use SQL AI functions in real data pipelines Hands-on patterns for turning unstructured documents into analysis-ready models Confidence to add AI capabilities to SQL-first platforms without ML complexity