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

Storage and processing costs of your legacy Teradata data warehouses impact your ability to deliver. Migrating your legacy Teradata data warehouse to the Databricks Data Intelligence Platform can accelerate your data modernization journey. In this session, learn the top strategies for completing this data migration. We will cover data type conversion, basic to complex code conversions, validation and reconciliation best practices. How to use Databricks natively hosted LLMs to assist with migration activities. See before-and-after architectures of customers who have migrated, and learn about the benefits they realized.

Curious how to apply resource-intensive generative AI models across massive datasets without breaking the bank? This session reveals efficient batch inference strategies for foundation models on Databricks. Learn how to architect scalable pipelines that process large volumes of data through LLMs, text-to-image models and other generative AI systems while optimizing for throughput, cost and quality. Key takeaways: Implementing efficient batch processing patterns for foundation models using AI functions Optimizing token usage and prompt engineering for high-volume inference Balancing compute resources between CPU preprocessing and GPU inference Techniques for parallel processing and chunking large datasets through generative models Managing model weights and memory requirements across distributed inference tasks You'll discover how to process any scale of data through your generative AI models efficiently.

Join us as we dive into how Turnpoint Services, in collaboration with DataNimbus, built an Intelligence Platform on Databricks in just 30 days. We'll explore features like MLflow, LLMs, MLOps, Model Registry, Unity Catalog & Dashboard Alerts that powered AI applications such as Demand Forecasting, Customer 360 & Review Automation. Turnpoint’s transformation enabled data-driven decisions, ops efficiency & a better customer experience. Building a modern data foundation on Databricks optimizes resource allocation & drives engagement. We’ll also introduce innovations in DataNimbus Designer: AI Blocks: modular, prompt-driven smart transformers for text data, built visually & deployed directly within Databricks. These capabilities push the boundaries of what's possible on the Databricks platform. Attendees will gain practical insights, whether you're beginning your AI journey or looking to accelerate it.

This in-depth session explores advanced MLOps practices for implementing production-grade machine learning workflows on Databricks. We'll examine the complete MLOps journey from foundational principles to sophisticated implementation patterns, covering essential tools including MLflow, Unity Catalog, Feature Stores and version control with Git. Dive into Databricks' latest MLOps capabilities including MLflow 3.0, which enhances the entire ML lifecycle from development to deployment with particular focus on generative AI applications. Key session takeaways include: Advanced MLflow 3.0 features for LLM management and deployment Enterprise-grade governance with Unity Catalog integration Robust promotion patterns across development, staging and production CI/CD pipeline automation for continuous deployment GenAI application evaluation and streamlined deployment

Whether you're using OpenAI, Anthropic or open-source models like Meta Llama, the Mosaic AI Gateway is the central control plane across any AI model or agent. Learn how you can streamline access controls, enforce guardrails for compliance, ensure an audit trail and monitor costs across providers — without slowing down innovation. Lastly, we’ll dive even deeper into how AI Gateway works with Unity Catalog to deliver a full governance story for your end-to-end AI agents across models, tools and data. Key takeaways: Centrally manage governance and observability across any LLM (proprietary or open-source) Give developers a unified query interface to swap, experiment and A/B test across models Attribute costs and usage to teams for better visibility and chargebacks Enforce enterprise-grade compliance with guardrails and payload logging Ensure production reliability with load balancing and fallbacks

Picture the scene — you're exploring a deep, dark cave looking for insights to unearth when, in a burst of smoke, Genie appears and offers you not three but unlimited data wishes. This isn't a folk tale, it's the growing wave of Generative BI that is going to be a part of analytics platforms. Databricks Genie is a tool powered by a SQL-writing LLM that redefines how we interact with data. We'll look at the basics of creating a new Genie room, scoping its data tables and asking questions. We'll help it out with some complex pre-defined questions and ensure it has the best chance of success. We'll give the tool a personality, set some behavioural guidelines and prepare some hidden easter eggs for our users to discover. Generative BI is going to be a fundamental part of the analytics toolset used across businesses. If you're using Databricks, you should be aware of Genie, if you're not, you should be planning your Generative BI Roadmap, and this session will answer your wishes.

We present a novel framework for designing and inducing controlled hallucinations in long-form content generation by LLMs across diverse domains. The purpose is to create fully-synthetic benchmarks and mine hard cases for iterative refinement of zero-shot hallucination detectors. We will first demonstrate how Gretel Data Designer (now part of NVIDIA) can be used to design realistic, high-quality long-context datasets across various domains. Second, we will describe our reasoning-based approach to hard-case mining. Specifically, our methodology relies on chain-of-thought-based generation of both faithful and deceptive question-answer pairs based upon long-context samples. Subsequently, a consensus labeling & detector framework is employed to filter synthetic examples to zero-shot hard cases. The result of this process is a fully-automated system, operating under open data licenses such as Apache-2.0, for the generation of hallucinations at the edge-of-capabilities for a target LLM to detect.

We present Level Infinite AI Translation, a translation engine developed by Tencent, tailored specifically for the gaming industry. The primary challenge in game machine translation (MT) lies in accurately interpreting the intricate context of game texts, effectively handling terminology and adapting to the highly diverse translation formats and stylistic requirements across different games. Traditional MT approaches cannot effectively address the aforementioned challenges due to their weak context representation ability and lack of common knowledge. Leveraging large language model and related technology, our engine is crafted to capture the subtleties of localized language expression while ensuring optimization for domain-specific terminology, jargon and required formats and styles. To date, the engine has been successfully implemented in 15 international projects, translating over one billion words across 23 languages, and has demonstrated cost savings exceeding 25% for partners.

Elevate your AI initiatives on Databricks by harnessing the latest advancements in Google Cloud's Gemini models. Learn how to integrate Gemini's built-in reasoning and powerful development tools to build more dynamic and intelligent applications within your existing Databricks platform. We'll explore concrete ideas for agentic AI solutions, showcasing how Gemini can help you unlock new value from your data in Databricks.

This intermediate-level presentation will explore the various methods we've leveraged within Databricks to deliver and evaluate guardrail models for AI safety. From prompt engineering with custom built frameworks to hosting models served from the market place and beyond. We've utilized GPU within clusters to fine-tune and run large open sourced models at inference such as Llama Guard 3.1 and generate synthetic datasets based on questions we've received from production.

A production-ready GenAI application is more than the framework itself. Like ML, you need a unified platform to create an end-to-end workflow for production quality applications.Below is an example of how this works on Databricks: Data ETL with Lakeflow Declarative Pipelines and jobs Data storage for governance and access with Unity Catalog Code development with Notebooks Agent versioning and metric tracking with MLflow and Unity Catalog Evaluation and optimizations with Mosaic AI Agent Framework and DSPy Hosting infrastructure with monitoring with Model Serving and AI Gateway Front-end apps using Databricks Apps In this session, learn how to build agents to access all your data and models through function calling. Then, learn how DSPy enables agent interaction with each other to ensure the question is answered correctly. We will demonstrate a chatbot, powered by multiple agents, to be able to answer questions and reason answers the base LLM does not know and very specialized topics.ow and very specialized topics.

This session is repeated. Integrating AI into existing data workflows can be challenging, often requiring specialized knowledge and complex infrastructure. In this session, we'll share how SQL users can leverage AI/ML to access large language models (LLMs) and traditional machine learning directly from within SQL, simplifying the process of incorporating AI into data workflows. We will demonstrate how to use Databricks SQL for natural language processing, traditional machine learning, retrieval augmented generation and more. You'll learn about best practices and see examples of solving common use cases such as opinion mining, sentiment analysis, forecasting and other common AI/ML tasks.

The rise of GenAI has led to a complete reinvention of how we conceptualize Data + AI. In this breakout, we will recontextualize the rise of GenAI in traditional ML paradigms, and hopefully unite the pre- and post-LLM eras. We will demonstrate when and where GenAI may prove more effective than traditional ML algorithms, and highlight problems for which the wheel is unnecessarily being reinvented with GenAI. This session will also highlight how MLflow provides a unified means of benchmarking traditional ML against GenAI, and lay out a vision for bridging the divide between Traditional ML and GenAI practitioners.

Curious to know how Adidas is transforming customer experience and business impact with agentic workflows, powered by Databricks? By leveraging cutting-edge tools like MosaicML’s deployment capabilities, Mosaic AI Gateway, and MLflow, Adidas built a scalable GenAI agentic infrastructure that delivers actionable insights from growing 2 million product reviews annually. With remarkable results: 60% latency reduction (15.5 seconds to 6 seconds) 91.67% cost savings (transitioning to more efficient LLMs) 98.5% token efficiency, reducing input tokens from 200k to just 3k 20% increase in productivity (faster time to insight) Empowering over 500 decision-makers across 150+ countries, this infrastructure is set to optimize products and services for Adidas’ 500 million members by 2025 while supporting dozens of upcoming AI-driven solutions. Join us to explore how Adidas turned agentic workflows infra into a strategic advantage using Databricks and learn how you can do the same!

Join us to hear about how Epsilon Data Management migrated Epsilon’s unique, AI-powered marketing identity solution from multi-petabyte on-prem Hadoop and data warehouse systems to a unified Databricks Lakehouse platform. This transition enabled Epsilon to further scale its Decision Sciences solution and enable new cloud-based AI research capabilities on time and within budget, without being bottlenecked by the resource constraints of on-prem systems. Learn how Delta Lake, Unity Catalog, MLflow and LLM endpoints powered massive data volume, reduced data duplication, improved lineage visibility, accelerated Data Science and AI, and enabled new data to be immediately available for consumption by the entire Epsilon platform in a privacy-safe way. Using the Databricks platform as the base for AI and Data Science at global internet scale, Epsilon deploys marketing solutions across multiple cloud providers and multiple regions for many customers.

The AI Screening Agent automates Level 1 (L1) screening process, essential for Know Your Customer (KYC) and compliance due diligence during customer onboarding. This system aims to minimize false positives, significantly reducing human review time and costs. Beyond typical Retrieval-Augmented Generation (RAG) applications like summarization and chat-with-your-data (CWYD), the AI Screening Agent employs a ReAct architecture with intelligent tools, enabling it to perform complex compliance decision-making with human-like accuracy and greater consistency. In this talk, I will explore the screening agent architecture, demonstrating its ability to meet evolving client policies. I will discuss evaluation and configuration management using MLflow LLM-as-judge and Unity Catalog, and discuss challenges, such as, data fidelity and customization. This session underscores the transformative potential of AI agents in compliance workflows, emphasizing their adaptability, accuracy, and consistency.

Unlock the hidden potential in your image data without specialized computer vision expertise! This session explores how to leverage Databricks' multi-modal Foundation Model APIs to analyze, classify and extract insights from visual content. Learn how Databricks provides a unified API to understand images using powerful foundation models within your data workflows. Key takeaways: Implementing efficient workflows for image data processing within your Databricks lakehouse Understanding multi-modal foundation models for image understanding Integrating image analysis with other data types for business insights Using OpenAI-compatible APIs to query multi-modal models Building end-to-end pipelines from image ingestion to model deployment Whether analyzing product images, processing visual documents or building content moderation systems, you'll discover how to extract valuable insights from your image data within the Databricks ecosystem.

Scaling large language models (LLMs) and multimodal architectures requires efficient data management and computational power. NVIDIA NeMo Framework Megatron-LM on Databricks is an open source solution that integrates GPU acceleration and advanced parallelism with Databricks Delta Lakehouse, streamlining workflows for pre-training and fine-tuning models at scale. This session highlights context parallelism, a unique NeMo capability for parallelizing over sequence lengths, making it ideal for video datasets with large embeddings. Through the case study of TwelveLabs’ Pegasus-1 model, learn how NeMo empowers scalable multimodal AI development, from text to video processing, setting a new standard for LLM workflows.

At Zillow, we have accelerated the volume and quality of our dashboards by leveraging a modern SDLC with version control and CI/CD. In the past three months, we have released 32 production-grade dashboards and shared them securely across the organization while cutting error rates in half over that span. In this session, we will provide an overview of how we utilize Databricks asset bundles and GitLab CI/CD to create performant dashboards that can be confidently used for mission-critical operations. As a concrete example, we'll then explore how Zillow's Data Platform team used this approach to automate our on-call support analysis, leveraging our dashboard development strategy alongside Databricks LLM offerings to create a comprehensive view that provides actionable performance metrics alongside AI-generated insights and action items from the hundreds of requests that make up our support workload.

LLM agents aren’t just answering questions — they’re running entire workflows. In this talk, we’ll show how agents can autonomously ingest, process and structure unstructured data using Unstructured, with outputs flowing directly into Databricks. Powered by the Model Context Protocol (MCP), agents can interface with Unstructured’s full suite of capabilities — discovering documents across sources, building ephemeral workflows and exporting structured insights into Delta tables. We’ll walk through a demo where an agent responds to a natural language request, dynamically pulls relevant documents, transforms them into usable data and surfaces insights — fast. Join us for a sneak peek into the future of AI-native data workflows, where LLMs don’t just assist — they operate.

We present AT&T AutoClassify, built jointly between AT&T's Chief Data Office (CDO) and Databricks professional services, a novel end-to-end system for automatic multi-head binary classifications from unlabeled text data. Our approach automates the challenge of creating labeled datasets and training multi-head binary classifiers with minimal human intervention. Starting only from a corpus of unlabeled text and a list of desired labels, AT&T AutoClassify leverages advanced natural language processing techniques to automatically mine relevant examples from raw text, fine-tune embedding models and train individual classifier heads for multiple true/false labels. This solution can reduce LLM classification costs by 1,000x, making it an efficient solution in operational costs. The end result is a highly optimized and low-cost model servable in Databricks capable of taking raw text and producing multiple binary classifications. An example use case using call transcripts will be examined.

Genie Rooms have played an integral role in democratizing important datasets like Cell Tower and Lease Information. However, in order to ensure that this exciting new release from Databricks was configured as optimally as possible from development to deployment, we needed additional scaffolding around governance. In this talk we will describe the four main components we used in conjunction with the Genie Room to build a successful product and will provide generalizable lessons to help others get the most out of this object. At the core are a declarative, metadata approach to creating UC tables deployed on a robust framework. Second, a platform that efficiently crowdsourced targeted feedback from different user groups. Third, a tool that balances the LLM’s creativity with human wisdom. And finally, a platform that enforces our principle of separating Storage from Compute to manage access to the room at a fine-grained level and enables a whole host of interesting use-cases.

This research introduces a groundbreaking method for healthcare time-series forecasting using a Large Language Model (LLM) foundation model. By leveraging a comprehensive dataset of over 50 million IQVIA time-series trends, which includes data on procedure demands, sales and prescriptions (TRx), alongside publicly available data spanning two decades, the model aims to significantly enhance predictive accuracy in various healthcare applications. The model's transformer-based architecture incorporates self-attention mechanisms to effectively capture complex temporal dependencies within historical time-series trends, offering a sophisticated approach to understanding patterns, trends and cyclical variations.

At OpenAI, Kafka fuels real-time data streaming at massive scale, but traditional consumers struggle under the burden of partition management, offset tracking, error handling, retries, Dead Letter Queues (DLQ), and dynamic scaling — all while racing to maintain ultra-high throughput. As deployments scale, complexity multiplies. Enter Kafka Forwarder — a game-changing Kafka Consumer Proxy that flips the script on traditional Kafka consumption. By offloading client-side complexity and pushing messages to consumers, it ensures at-least-once delivery, automated retries, and seamless DLQ management via Databricks. The result? Scalable, reliable and effortless Kafka consumption that lets teams focus on what truly matters. Curious how OpenAI simplified self-service, high-scale Kafka consumption? Join us as we walk through the motivation, architecture and challenges behind Kafka Forwarder, and share how we structured the pipeline to seamlessly route DLQ data into Databricks for analysis.