Explore how Snowflake and Microsoft collaborate to transform data and AI workflows. Learn to operate on a single data copy between Microsoft Fabric OneLake and Snowflake via Apache Iceberg, eliminating duplication. Discover Real-Time RAG AI Agents that integrate Snowflake's trusted data and enterprise systems for instant Microsoft Copilot responses, without copying data. Unlock Real-Time Actions using PowerApps with live query and writeback to Snowflake, all with no code. Simplify and innovate with these powerful tools.

This session will explore why and how Snowflake's unique capabilities are crucial to enable, accelerate and implement industrial IoT use cases like root cause analysis of asset failure, predictive maintenance and quality management. The session will explain the use of specific time series capabilities (e.g. asof joins, CORR & MATCH function), built-in Cortex ML functions (like anomaly detection and forecasting) and LLMs leveraging RAG to accelerate use cases for manufacturing customers.

Are dashboards dead? For complex enterprise use cases, the answer might be yes. In this episode, I'm joined by Irina Malkova (VP Data & AI at Salesforce), to discuss her team's transformational journey from building complex dashboards to deploying AI-powered conversational agents. We dive deep into how this shift is not just a change in tooling, but a fundamental change in how users access insights and how data teams measure their impact.

Join us as we cover: The Shift from Dashboards to Agents: We discuss why dashboards can create a high cognitive load and fail users in complex scenarios , and how conversational agents in the flow of work (like Slack) provide targeted, actionable insights and boost adoption.What is Product Telemetry?: Irina explains how telemetry is evolving from a simple engineering observability use case to a critical data source for AI, machine learning, and recommendation systems.Why Standard RAG Fails in the Enterprise: Irina shares why typical RAG approaches break down on dense, entity-rich corporate data (like Salesforce's help docs) where semantic similarity isn't enough, leading to the rise of Graph RAG.The New, Measurable ROI of Data: How moving from BI to agents allows data teams to precisely measure impact, track downstream actions, and finally have a concrete answer to the ROI question that was previously impossible to justify.Data Teams as Enterprise Leaders: Why data teams are uniquely positioned to lead AI transformation, as they hold the enterprise "ontology" and have experience building products under uncertainty.

Send us a text This week, we’re rewinding one of our most talked-about episodes! Richmond Alake, Developer Advocate at MongoDB, joins us to explore how databases power the future of AI. From RAG best practices to the truth behind AGI hype, Richmond breaks down what it takes to build systems that scale — and think. Show Notes 02:05 Meet Rich Alake 03:57 A Developer Advocate at MongoDB 05:57 Passions and Fate! 08:52 AI Hype 13:14 Oh No… AGI Again 17:30 What Makes an AI Database? 20:42 Use Cases 25:41 RAG Best Practices 27:40 The Role of Databases 30:05 Why MongoDB Does It Better 32:43 What’s Next 36:13 Advice on Continuous Learning 38:44 Where to Find RichConnect with Richmond: 🔗 LinkedIn 🌐 MongoDB Website 🧠 Register for MongoDB 🤖 AI Agents Article 💾 Best Repo for AI Developers Want to be featured as a guest on Making Data Simple? Reach out to us at [email protected] and tell us why you should be next. The Making Data Simple Podcast is hosted by Al Martin, WW VP Technical Sales, IBM, where we explore trending technologies, business innovation, and leadership ... while keeping it simple & fun.

Quasiment toutes les roadmaps Gen AI incluent désormais le déploiement at scale d'assistants experts basés sur des approches RAG. Souvent, la direction prise par les équipes techniques est de considérer chaque assistant comme un projet à part entière, sans suffisamment inclure leur développement et leur maintenance dans un cadre LLMOps bien défini — or c'est ici que le principal obstacle à l'industrialisation d'applications Gen AI se situe, et non sur les capacités des modèles LLM.

Parmi ce cadre, les tests sont indispensables : Context Precision, Context Recall, Faithfulness etc. Les équipes d'Eurazeo et d'Eulidia ont donc mis en place l'automatisation des tests effectués sur les workflows Gen AI, via une intégration de la bibliothèque RAGAS au sein des services Cortex de Snowflake. Cela a permis de poser les bases essentielles pour le déploiement du RAG-as-a-Service, application permettant de créer automatiquement des RAG à destination des équipes internes, tout en garantissant leur performance et leur pertinence.

• Nous présenterons les enjeux du déploiement d’une IA générative et d’un pipeline de RAG dans un environnement industriel sensible, en garantissant la plus stricte confidentialité des données.

• Découvrez l’approche innovante choisie par Sodern : déploiement on-premise de la plateforme LightOn, vectorisation de la base documentaire et intégration des fonctionnalités via API.

• Nous expliquerons comment ces technologies sont utilisées concrètement pour la génération et la correction de code, la création de user stories et le knowledge management, avec les premiers résultats observés.

• Enfin, nous partagerons la valeur ajoutée apportée à l’organisation et les axes d’évolution envisagés pour renforcer l’usage de l’IA sécurisée dans l’industrie.

Un copilote n’est utile que s’il s’appuie sur des données fiables, contextualisées et gouvernées. Venez voir comment la solution Qlik Talend Cloud permet de bâtir un Knowledge Mart orienté métier, puis comment Qlik Answers, grâce au RAG (Retrieval-Augmented Generation), exploite ce Knowledge Mart pour fournir des réponses en langage naturel, traçables, pertinentes et actionnables.

Vous souhaitez en savoir plus ? Toute l'équipe Qlik vous donne rendez-vous sur le stand D38 pour des démos live, des cas d'usage et des conseils d'experts.

Mettre en place un RAG (Retrieval-Augmented Generation) semble simple : connecter un LLM à une base documentaire et obtenir des réponses enrichies. Mais lorsqu’il s’agit de gérer des millions de documents, comme le font certains clients de Hymalaia comme Zenchef, la réalité est tout autre : un RAG qui fonctionne vraiment demande une ingénierie avancée et une architecture robuste. Le RAG avancé couple la puissance des LLM à des moteurs de recherche intelligents pour offrir pertinence, traçabilité et fiabilité. Dans ce talk, Cédric Carbone expliquera les fondements clés : multipass d’indexation, hybridation des algorithmes, reranking et stratégies anti-biais. Il illustrera ensuite ces principes avec un cas concret : Hymalaia, la solution SaaS de création et de déploiement d’agents IA conversationnels augmentés. Vous verrez comment un RAG bien conçu transforme un LLM en véritable outil de confiance pour la décision et l’action, capable de passer à l’échelle de vos données.

RAG avancé : combiner LLM et recherche intelligente pour pertinence, traçabilité et fiabilité, avec architecture robuste à grande échelle.

Et si vos données devenaient vraiment intelligentes ?

Au croisement de l’IA générative, des agents autonomes et des graphes de connaissances, Neo4j révèle une nouvelle dimension de performance en assurant des réponses précises et contextualisées. En structurant les relations entre vos données et en intégrant RAG (Retrieval-Augmented Generation), Neo4j réduit les hallucinations des LLM, renforce la pertinence des réponses et décuple vos capacités de décision.

Venez découvrir comment cette alliance révolutionne les workflows IA, et pourquoi Neo4j devrait être le socle de votre stratégie IA.

Comment exploiter tout le potentiel de la GenAI tout en protégeant un corpus documentaire sensible et critique.

Comment exploiter tout le potentiel de la GenAI tout en protégeant un corpus documentaire sensible et critique.

Avec Infogreffe et le Conseil National des Greffiers, nous avons développé une solution de Retrieval Augmented Generation (RAG) sur AI Foundry, spécifiquement architecturée pour répondre de manière optimale aux exigences des tribunaux de commerce.

Dans cet atelier, nous montrerons comment des documents juridiques complexes peuvent être indexés et interrogés de manière sécurisée, afin de fournir aux greffiers des réponses fiables, contextualisées et vérifiables.

Les principaux objectifs visés étant de valider la conformité d’un document, d’accélérer la recherche d’informations réglementaires et d’améliorer l’accès à des références métiers critiques.

Nous partagerons également les choix technologiques et les mesures de sécurité mises en œuvre pour garantir confidentialité, traçabilité et souveraineté de la donnée.

Un retour d’expérience pragmatique qui illustre comment la GenAI peut transformer un métier dont la donnée est un actif stratégique.

Les agents basés sur les modèles standards d'IA générative simplement contextualisés via un RAG ne peuvent relever de manière pleinement efficace les enjeux d'automatisation des tâches spécifiques dans les processus coeur de métiers. 

CGI DeepContext est une solution accélératrice pour générer rapidement des agents "business" spécialisés. Découvrez lors de cette session notre approche pour accélérer la génération de valeur et accélérer leur insertion efficiente dans les chaines de valeur métier.

Explore how Snowflake and Microsoft collaborate to transform data and AI workflows. Learn to operate on a single data copy between Microsoft Fabric OneLake and Snowflake via Apache Iceberg, eliminating duplication. Discover Real-Time RAG AI Agents that integrate Snowflake's trusted data and enterprise systems for instant Microsoft Copilot responses, without copying data. Unlock Real-Time Actions using PowerApps with live query and writeback to Snowflake, all with no code. Simplify and innovate with these powerful tools.

In this episode, I sit down with Saket Saurabh (CEO of Nexla) to discuss the fundamental shift happening in the AI landscape. The conversation is moving beyond the race to build the biggest foundational models and towards a new battleground: context. We explore what it means to be a "model company" versus a "context company" and how this changes everything for data strategy and enterprise AI.

Join us as we cover: Model vs. Context Companies: The emerging divide between companies building models (like OpenAI) and those whose advantage lies in their unique data and integrations. The Limits of Current Models: Why we might be hitting an asymptote with the current transformer architecture for solving complex, reliable business processes. "Context Engineering": What this term really means, from RAG to stitching together tools, data, and memory to feed AI systems. The Resurgence of Knowledge Graphs: Why graph databases are becoming critical for providing deterministic, reliable information to probabilistic AI models, moving beyond simple vector similarity. AI's Impact on Tooling: How tools like Lovable and Cursor are changing workflows for prototyping and coding, and the risk of creating the "-10x engineer." The Future of Data Engineering: How the field is expanding as AI becomes the primary consumer of data, requiring a new focus on architecture, semantics, and managing complexity at scale.

Abstract

As a data visualization practitioner, I frequently draw inspiration from the diverse and rapidly expanding community, particularly through challenges like #TidyTuesday. However, the sheer volume of remarkable visualizations quickly overwhelmed my manual curation methods—from Pinterest boards to Notion pages. This created a significant bottleneck in my workflow, as I found myself spending more time cataloging charts than actively creating them.

In this talk, I will present a RAG (Retrieval Augmented Generation) based retrieval system that I designed specifically for data visualizations. I will detail the methodology behind this system, illustrating how I addressed my own workflow inefficiencies by transforming a dispersed collection of charts into a semantically searchable knowledge base. This project serves as a practical example of applying advanced AI techniques to enhance creative technical work, demonstrating how a specialized retrieval system can significantly improve the efficiency and quality of data visualization creation process.

Are AI code generators delivering SQL that "looks right but works wrong" for your data engineering challenges? Is your AI generating brilliant-sounding but functionally flawed results? 

The critical bottleneck isn't the AI's intelligence; it's the missing context.

In this talk, we will put thing in context and reveal how providing AI with structured, deep understanding—from data semantics and lineage to user intent and external knowledge—is the true paradigm shift. 

We'll explore how this context engineering powers the rise of dependable AI agents and leverages techniques like Retrieval-Augmented Generation (RAG) to move beyond mere text generation towards trustworthy, intelligent automation across all domains. 

This limitation highlights a broader challenge across AI applications: the need for systems to possess a deep understanding of all relevant signals, ranging from environmental cues and user history to explicit intent, to achieve reliable and meaningful operation.

Join us for real-world, practical case studies directly from data engineers that demonstrate precisely how to unlock this transformative power and achieve truly reliable AI.

Improving retrieval systems—especially in RAG pipelines—requires a clear understanding of what’s working and what isn’t. The only scalable way to do that is through meaningful metrics. In this talk, we share insights from building a platform-agnostic search and retrieval product, and how we balance performance against cost. Bigger models often give better results… but at what price? We explain how to assess what’s “good enough” and why the choice of benchmark really matters.

Grounding Large Language Models in your specific data is crucial, but notoriously challenging. Retrieval-Augmented Generation (RAG) is the common pattern, yet practical implementations are often brittle, suffering from poor retrieval, ineffective chunking, and context limitations, leading to inaccurate or irrelevant answers. The emergence of massive context windows (1M+ tokens) seems to offer a simpler path – just put all your data in the prompt! But does it truly solve the "needle in a haystack" problem, or introduce new challenges like prohibitive costs and information getting lost in the middle? This talk dives deep into the engineering realities. We'll dissect common RAG failure modes, explore techniques for building robust RAG systems (advanced retrieval, re-ranking, query transformations), and critically evaluate the practical viability, costs, and limitations of leveraging long context windows for complex data tasks in Python. Leave understanding the real trade-offs to make informed architectural decisions for building reliable, data-grounded GenAI applications.

Data is one of the most valuable assets in any organisation, but accessing and analysing it has been limited to technical experts. Business users often rely on predefined dashboards and data teams to extract insights, creating bottlenecks and slowing decision-making.

This is changing with the rise of Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG). These technologies are redefining how organisations interact with data, allowing users to ask complex questions in natural language and receive accurate, real-time insights without needing deep technical expertise.

In this session, I’ll explore how LLMs and RAG are driving true data democratisation by making analytics accessible to everyone, enabling real-time insights with AI-powered search and retrieval and overcoming traditional barriers like SQL, BI tool complexity, and rigid reporting structures.