Prat Moghe

Super capable agents are now in your enterprise. But without access to AI-ready data these agents cannot make reliable decisions. AI-ready data means: secure access to the right data and context, and a clear understanding of user intent. It’s an architectural gap for everybody. This session introduces Mantra, a new agentic analytics stack for trusted insights. Any agent or user can plug into it to get secure access to the right data and context.

The AI nirvana: teams can self-serve by “talking” to data, getting real-time insights. The reality: a year of POCs revealed that current agents do not scale without significant context engineering efforts. This session introduces a new agentic platform, the AI Insights Fabric, that combines federated data access, context engineering, and agent personalization to radically reduce the effort to deliver accurate insights across all enterprise data.

After a year of pilots, clear patterns are emerging around what works — and what doesn't as enterprises move AI into production. Join fellow data leaders to discuss the real challenges of AI-ready data, context engineering, validation strategies that build trust, and practical approaches to accelerating time-to-value. This executive roundtable explores lessons learned from organizations as they seek to move AI use-cases into production.

AI initiatives often stall when data teams can’t keep up with business demand for ad hoc, self-service data. Whether it’s AI agents, BI tools, or business users—everyone needs data immediately, but the pipeline-centric modern data stack is not built for this scale of agility. Promethium enables the data teams to generate instant, contextual data products called Data Answers based on rapid, exploratory questions from the business. Data Answers empower data teams for AI-scale collaboration with the business. We will demo Promethium’s new agent capability to build data answers on Databricks for self-service data. The Promethium agent leverages and extends Genie with context from other enterprise data and applications to ensure accuracy and relevance.

AI initiatives stall when data teams can’t meet the demand for ad hoc, self-service data. Pipelines are not agile enough for AI agents, BI tools or business users needing data immediately. Promethium enables the data teams to generate instant, contextual data products (data answers) to meet this demand, empowering data teams for AI-scale collaboration with the business. We will demo how to build data answers on Snowflake, extending Cortex AI with additional context to ensure accuracy and relevance.