Prukalpa Sankar

Everyone's talking about context layers. Nobody agrees on what one is — a semantic layer with a better name? A knowledge graph in a trench coat? AI is moving from pilot to production — and it made data teams into janitors: cleaning up hallucinations, debugging agents. But the context agents need most is what data teams already own. The definitions, the lineage, the institutional knowledge. That's not a cost center. It's your most strategic AI asset. You already have Databricks — maybe Unity Catalog too. But your agents still don't know which "revenue" definition to use, which tables to trust, or what the business actually means. The gap between pilot and production isn't a model problem. It's a context problem. Join Prukalpa Sankar and Varun Banka to see it live: dark Databricks tables become AI-ready — automated lineage mapped, AI-bootstrapped definitions added, Context Quality Score green — and a Genie query returns a governed response via MCP. All live. All on stage.

Context layer. Semantic layer. Ontology. Knowledge graph. Context graph. GraphRAG. If you've been in an architecture meeting, you've heard all of these terms. If you've tried to figure out which one you need, you've probably given up. Are these different things? Buzzwords? A semantic layer in a trench coat? Or genuinely different approaches to the same problem: making AI understand your business? Join Atlan and industry experts who actually disagree with each other for the spiciest 20 minutes at Snowflake Summit. No slides. No consensus. Just strong opinions, real arguments and a chance to finally understand where these terms diverge — and whether any of them matter for your AI strategy.

Most enterprise AI projects stall before production — not because Snowflake CoWork or Cortex Agents aren't powerful, but because agents don't know which "revenue" definition to use, which tables to trust, or what the business actually means. The gap between pilot and production isn't a model problem. It's a context problem. Workday is closing it and they're here to show you how. Join Prukalpa Sankar of Atlan and Joe DosSantos, CDO at Workday, to learn what the Enterprise Context Layer is and why production AI needs it, how Workday's shared language — built for people — is now being leveraged for AI via Atlan's MCP, and what it takes to go from cool demo to AI trusted at scale.

Everyone's talking about context layers. Nobody agrees on what one is: A semantic layer with a better name? A knowledge graph in a trench coat? AI made data teams into janitors, cleaning up hallucinations and debugging agents. But the context agents need most is what data teams already own: The definitions. The lineage. The governance. The institutional knowledge. That's not a cost center; it's your most strategic asset. Join Prukalpa Sankar and Varun Banka to learn how the four levels of context map the gap. Then watch live as a dark Snowflake database becomes AI ready, with automated lineage, AI-bootstrapped definitions, a green Context Quality Score and a governed Cortex Agent response via MCP.

With hundreds of millions viewing broadcasts from news to sports, Fox relies on a sophisticated and trusted architecture ingesting 100+ data sources, carefully governed to improve UX across products, drive sales and marketing, and ensure KPI tracking. Join Oliver Gomes, VP of Enterprise and Data Platform at Fox, and Prukalpa Sankar of Atlan to learn how true partnership helps their team navigate opportunities from Governance to AI. To govern and democratize their multi-cloud data platform, Fox chose Atlan to make data accessible and understandable for more users than ever before. Their team then used a data product approach to create a shared language using context from sources like Unity Catalog at a single point of access, no matter the underlying technology. Now, Fox is defining an ambitious future for Metadata. With Atlan and Iceberg driving interoperability, their team prepares to build a “control plane”, creating a common system of trust and governance.

While nearly 90% of leaders expect AI investments to drive revenue growth in the next three years, as little as 12% of AI pilot projects transition into production. The consequences of this chasm between pilot and production are existential, and enterprises that bridge this gap to become AI-native will have their data team to thank. Join Varun Banka and Prukalpa Sankar, Co-Founders of Atlan, to learn how governance and metadata management are evolving to help leading enterprise data teams to become AI-native, fast-becoming the most critical part of the modern data stack by offering the context and trust needed to finally make AI production-ready.

Workday helps more than 11,000 organizations, including 60% of the Fortune 500, manage their most important assets — their people and their money. The key to Workday’s success lies in ensuring their more than 20,000 global employees are comfortable with and capable of using data to inform their decisions and work. Join Joe DosSantos, Chief Data Officer at Workday, and Prukalpa Sankar, Co-Founder of Atlan, to learn what it takes to build AI companions and marketplaces that expand the definition of who can use data, carefully governing and building data products with Snowflake and Atlan, and delivering the rich context necessary for accurate, trustworthy insights with AI.

Data-driven teams will be behind the most amazing human achievements in the next decade, from curing cancer to developing self-driving cars to putting people on Mars.