From Unstructured Data to Structured Insights: A Practitioner's Guide to Intelligent Document Processing at Scale

80% of the context that powers your business - invoices, contracts, call transcripts, support tickets - lives in unstructured data. Turning it into structured, accurate inputs for your agents and analytics is one of the biggest opportunities in your data estate.

But going from a prototype to production is harder than it looks: accuracy, cost, and throughput stop being independent dials and become a three-way tradeoff you have to design around. In this session, we'll walk through the framework and the playbook to win that tradeoff. We'll show you how to compose AI Functions - Databricks' research-backed, task-specific building blocks for intelligent document processing - into production-ready agentic workflows. You'll learn how to choose the right functions for your task, iterate on quality, and tune for cost and throughput at scale. Along the way, we'll demo new AI Functions that push what's possible for batch document extraction and retrieval.

Walk away with a concrete decision framework for building agentic workflows to process unstructured data, and the best practices to put them in production.