Enterprises generate massive amounts of unstructured data — from support tickets and PDFs to emails and product images. But extracting insight from that data requires brittle pipelines and complex tools. Databricks AI Functions make this simpler. In this session, you’ll learn how to apply powerful language and vision models directly within your SQL and ETL workflows — no endpoints, no infrastructure, no rewrites. We’ll explore practical use cases and best practices for analyzing complex documents, classifying issues, translating content, and inspecting images — all in a way that’s scalable, declarative, and secure. What you’ll learn: How to run state-of-the-art LLMs like GPT-4, Claude Sonnet 4, and Llama 4 on your data How to build scalable, multimodal ETL workflows for text and images Best practices for prompts, cost, and error handling in production Real-world examples of GenAI use cases powered by AI Functions

Deploying AI in production is getting more complex — with different model types, tighter timelines, and growing infrastructure demands. In this session, we’ll walk through how Mosaic AI Model Serving helps teams deploy and scale both traditional ML and generative AI models efficiently, with built-in monitoring and governance.We’ll also hear from Skyscanner on how they’ve integrated AI into their products, scaled to 100+ production endpoints, and built the processes and team structures to support AI at scale. Key Takeaways: How Skyscanner ships and operates AI in real-world products How to deploy and scale a variety of models with low latency and minimal overhead Building compound AI systems using models, feature stores, and vector search Monitoring, debugging, and governing production workloads