Your model is trained. Your pilot is live. Your data looks AI-ready. But for most teams, the toughest part of building successful AI starts after deployment. In this talk, Shane Murray and Ethan Post share lessons from the development of Monte Carlo’s Troubleshooting Agent – an AI assistant that helps users diagnose and fix data issues in production. They’ll unpack what it really takes to build and operate trustworthy AI systems in the real world, including: The Illusion of Done – Why deployment is just the beginning, and what breaks in production; Lessons from the Field – A behind-the-scenes look at the architecture, integration, and user experience of Monte Carlo’s agent; Operationalizing Reliability – How to evaluate AI performance, build the right team, and close the loop between users and model. Whether you're scaling RAG pipelines or running LLMs in production, you’ll leave with a playbook for building data and AI systems you—and your users—can trust.

This session is repeated. For most companies, building compound AI systems remains aspirational. LLMs are powerful, but imperfect, and their non-deterministic nature makes steering them to high accuracy a challenge. In this session, we’ll demonstrate how to build compound AI systems using SLMs and highly accurate mini-agents that can be integrated into agentic workflows. You'll learn about breakthrough techniques, including: memory RAG, an embedding algorithm that reduces hallucinations using embed-time compute to generate contextual embeddings, improving indexing and retrieval, and memory tuning, a finetuning algorithm that reduces hallucinations using a Mixture of Memory Experts (MoME) to specialize models with proprietary data. We’ll also share real-world examples (text-to-SQL, factual reasoning, function calling, code analysis and more) across various industries. With these building blocks, we’ll demonstrate how to create high accuracy mini-agents that can be composed into larger AI systems.

The most common RAG systems rely on a frozen RAG system — one where there’s a single embedding model and single vector index. We’ve achieved a modicum of success with that, but when it comes to increasing accuracy for production systems there is only so much this approach solves. In this session we will explore how to move from the frozen systems to adaptive RAG systems which produce more tailored outputs with higher accuracy. Databricks services: Lakehouse, Unity Catalog, Mosaic, Sweeps, Vector Search, Agent Evaluation, Managed Evaluation, Inference Tables

This course introduces learners to evaluating and governing GenAI (generative artificial intelligence) systems. First, learners will explore the meaning behind and motivation for building evaluation and governance/security systems. Next, the course will connect evaluation and governance systems to the Databricks Data Intelligence Platform. Third, learners will be introduced to a variety of evaluation techniques for specific components and types of applications. Finally, the course will conclude with an analysis of evaluating entire AI systems with respect to performance and cost. Pre-requisites: Familiarity with prompt engineering, and experience with the Databricks Data Intelligence Platform. Additionally, knowledge of retrieval-augmented generation (RAG) techniques including data preparation, embeddings, vectors, and vector databases Labs: Yes Certification Path: Databricks Certified Generative AI Engineer Associate

This course provides participants with information and practical experience in building advanced LLM (Large Language Model) applications using multi-stage reasoning LLM chains and agents. In the initial section, participants will learn how to decompose a problem into its components and select the most suitable model for each step to enhance business use cases. Following this, participants will construct a multi-stage reasoning chain utilizing LangChain and HuggingFace transformers. Finally, participants will be introduced to agents and will design an autonomous agent using generative models on Databricks. Pre-requisites: Solid understanding of natural language processing (NLP) concepts, familiarity with prompt engineering and prompt engineering best practices, experience with the Databricks Data Intelligence Platform, experience with retrieval-augmented generation (RAG) techniques including data preparation, building RAG architectures, and concepts like embeddings, vectors, and vector databases Labs: Yes Certification Path: Databricks Certified Generative AI Engineer Associate

This course is designed to introduce participants to contextual GenAI (generative artificial intelligence) solutions using the retrieval-augmented generation (RAG) method. Firstly, participants will be introduced to the RAG architecture and the significance of contextual information using Mosaic AI Playground. Next, the course will demonstrate how to prepare data for GenAI solutions and connect this process with building an RAG architecture. Finally, participants will explore concepts related to context embedding, vectors, vector databases, and the utilization of the Mosaic AI Vector Search product. Pre-requisites: Familiarity with embeddings, prompt engineering best practices, and experience with the Databricks Data Intelligence Platform Labs: Yes Certification Path: Databricks Certified Generative AI Engineer Associate

Retrieval Augmented Generation (RAG) continues to be a foundational approach in AI despite claims of its demise. While some marketing narratives suggest RAG is being replaced by fine-tuning or long context windows, these technologies are actually complementary rather than competitive. But how do you build a truly effective RAG system that delivers accurate results in high-stakes environments? What separates a basic RAG implementation from an enterprise-grade solution that can handle complex queries across disparate data sources? And with the rise of AI agents, how will RAG evolve to support more dynamic reasoning capabilities? Douwe Kiela is the CEO and co-founder of Contextual AI, a company at the forefront of next-generation language model development. He also serves as an Adjunct Professor in Symbolic Systems at Stanford University, where he contributes to advancing the theoretical and practical understanding of AI systems. Before founding Contextual AI, Douwe was the Head of Research at Hugging Face, where he led groundbreaking efforts in natural language processing and machine learning. Prior to that, he was a Research Scientist and Research Lead at Meta’s FAIR (Fundamental AI Research) team, where he played a pivotal role in developing Retrieval-Augmented Generation (RAG)—a paradigm-shifting innovation in AI that combines retrieval systems with generative models for more grounded and contextually aware responses. In the episode, Richie and Douwe explore the misconceptions around the death of Retrieval Augmented Generation (RAG), the evolution to RAG 2.0, its applications in high-stakes industries, the importance of metadata and entitlements in data governance, the potential of agentic systems in enterprise settings, and much more. Links Mentioned in the Show: Contextual AIConnect with DouweCourse: Retrieval Augmented Generation (RAG) with LangChainRelated Episode: High Performance Generative AI Applications with Ram Sriharsha, CTO at PineconeRegister for RADAR AI - June 26 New to DataCamp? Learn on the go using the DataCamp mobile appEmpower your business with world-class data and AI skills with DataCamp for business

The use of multiple Large Language Models (LLMs) working together perform complex tasks, known as multi-agent systems, has gained significant traction. While orchestration frameworks like LangGraph and Semantic Kernel can streamline orchestration and coordination among agents, developing large-scale, production-grade systems can bring a host of data challenges. Issues such as supporting multi-tenancy, preserving transactional integrity and state, and managing reliable asynchronous function calls while scaling efficiently can be difficult to navigate.

Leveraging insights from practical experiences in the Azure Cosmos DB engineering team, this talk will guide you through key considerations and best practices for storing, managing, and leveraging data in multi-agent applications at any scale. You’ll learn how to understand core multi-agent concepts and architectures, manage statefulness and conversation histories, personalize agents through retrieval-augmented generation (RAG), and effectively integrate APIs and function calls.

Aimed at developers, architects, and data scientists at all skill levels, this session will show you how to take your multi-agent systems from the lab to full-scale production deployments, ready to solve real-world problems. We’ll also walk through code implementations that can be quickly and easily put into practice, all in Python.

Explore how AI-powered Generative Agents can evolve in real time using live data streams. Inspired by Stanford's 'Generative Agents' paper, this session dives into building dynamic, AI-driven worlds with Apache Kafka, Flink, and Iceberg - plus LLMs, RAG, and Python. Demos and practical examples included!

Talk by Andreas Kollegger on GraphRAG, knowledge graphs, and retrieval-augmented generation (RAG) within the GraphRAG track.

Although retrieval augmented generation is a very popular architectural pattern for delivering Q&A over complex internal information, it is also extremely hard to build a high quality, high accuracy RAG system. Come to this session to learn the 7 gotchas of RAG systems and best practices to improve their performance.

As organizations scale GenAI from concept to production, they face challenges like ensuring accuracy, explaining responses, and connecting GenAI to unique knowledge. This session shows how GraphRAG combines knowledge graphs with retrieval-augmented generation to build GenAI apps grounded in enterprise data. Learn how companies like Klarna have deployed GenAI to build chatbots grounded in knowledge graphs, improving productivity and trust, while a major gaming company achieved 10x faster insights. We'll share real examples and practical steps for successful GenAI deployment.

AstraZeneca has implemented a "platform" approach, which serves as a centralized repository of standardized, enterprise grade, reusable services and capabilities that are accessible to AI factories. This platform includes user interfaces, APIs that integrate AI services with enterprise systems, supporting resources like data import tools and agent orchestration services. AstraZeneca will share how, starting with a few generative AI use cases, they have successfully identified common services and capabilities, subsequently standardizing these elements to maximize their applicability through the platform. These solutions leverage technologies like GPT models, Natural Language Processing and Retrieval Augmented Generation (RAG) architecture.

Getting AI/ML innovation out of the lab and into production means operationalising and scaling complex pipelines, and ensuring that the resulting signals are pushed into operational workflows where they can be actioned. We will briefly introduce Teradata’s extensive AI/ML capabilities and provide examples of how customers leverage them. We will also discuss Agentic AI, what it means for the data platform - and how Teradata’s industry-leading vector store is enabling customers to deploy scalable RAG applications.

Despite the popularity of retrieval-augmented generation, organizations are struggling to optimize large language model applications based on RAG. Attend this session to get suggestions and recommendations on improving your RAG solution, LLMOps for RAG systems, and scaling considerations.

🎙️ Future of Data and AI Podcast: Episode 06 with Robin Sutara What do Apache, Excel, Microsoft, and Databricks have in common? Robin Sutara! From being a technician for Apache helicopters to leading global data strategy at Microsoft and now Databricks, Robin Sutara’s journey is anything but ordinary. In this episode, she shares how enterprises are adopting AI in practical, secure, and responsible ways—without getting lost in the hype. We dive into how Databricks is evolving beyond the Lakehouse to power the next wave of enterprise AI—supporting custom models, Retrieval-Augmented Generation (RAG), and compound AI systems that balance innovation with governance, transparency, and risk management. Robin also breaks down the real challenges to AI adoption—not technical, but cultural. She explains why companies must invest in change management, empower non-technical teams, and embrace diverse perspectives to make AI truly work at scale. Her take on job evolution, bias in AI, and the human side of automation is both refreshing and deeply relevant. A sharp, insightful conversation for anyone building or scaling AI inside the enterprise—especially in regulated industries where trust and explainability matter as much as innovation.

RAG has transformed AI applications by grounding responses with external data. It can be better. By pairing RAG with low latency SQL analytics, you can enrich responses with instant insights, leading to a more interactive and insightful user experience with fresh, data-driven intelligence. In this talk, we’ll demo how low latency SQL combined with an AI application can deliver speed, accuracy, and trust.

Although retrieval augmented generation is a very popular architectural pattern for delivering Q&A over complex internal information, it is also extremely hard to build a high quality, high accuracy RAG system. Come to this session to learn the 7 gotchas of RAG systems and best practices to improve their performance.

There is no value from AI without a Data Strategy. AI hallucinations are a significant risk in delivering ROI across the enterprise. Stardog’s knowledge graph-powered agentic architecture delivers an AI-ready data foundation with a semantic layer that provides facts and grounding needed to eliminate hallucinations. Learn why traditional Retrieval-Augmented Generation and straight Text-to-SQL approaches can be insufficient and how you can broaden AI's access to diverse and dense data and ensure timely, secure, and, most importantly, hallucination-free answers from your own data.

Despite the popularity of retrieval-augmented generation, organizations are struggling to optimize large language model applications based on RAG. Attend this session to get suggestions and recommendations on improving your RAG solution, LLMOps for RAG systems and scaling considerations.