The Dremio Blog

The investment in the semantic layer pays off not just in agent accuracy but in the reliability of every downstream workflow that depends on agent output.

For data engineers building the foundation for agentic analytics, this open-standards approach also means less lock-in risk. The investment in modeling data as Iceberg tables is portable. The catalog is accessible to any Iceberg-compatible engine.

If agentic analytics is on your roadmap, or if you're already building AI applications that need to connect to enterprise data, it's worth auditing where your current platform sits across these three pillars. Most gaps show up fastest when agents start hitting data quality issues, permission errors, or ambiguous schema definitions that a human analyst would have talked their way around.

Apache Iceberg, the open and interoperable table format that has become the industry standard for the Apache Iceberg, the open and interoperable table format that has become the industry standard for the modern data lakehouse, adds meaningful new capabilities in Iceberg version 3 (V3). With the March release of Dremio Cloud, those capabilities are now […]

Learn how to build a customer 360 dashboard that unifies customer data and see how Dremio powers scalable, AI-ready analytics for enterprises.

Explore the nine best agentic analytics tools for data analysis in 2026, and learn why Dremio is the top solution for enterprise users.

Discover how analytics AI agents drive faster decisions when powered by a governed, scalable lakehouse foundation built for enterprise data.

The safest data architecture is one where data doesn't move, policies are unified in a central catalog, and every query is authenticated, authorized, and encrypted. By abstracting the complexity of data access and enforcing fine-grained controls at the catalog level, Dremio secures the data foundation so your teams—and your AI agents—can explore insights freely.

Dremio's Agentic Lakehouse provides an alternative for the workloads that drive the highest Databricks spend: interactive analytics, BI dashboards, and ad-hoc queries. By offloading these queries to Dremio's engine with Autonomous Reflections, you eliminate the DBU consumption and the underlying cloud compute for 60-80% of your analytical workload. Meanwhile, Databricks stays in place for the heavy processing it does well: ETL pipelines, ML training, and Spark-based transformations.

Dremio provides an alternative: keep Redshift for the workloads that need it, but offload the repetitive, expensive dashboard and reporting queries to Dremio's engine. Dremio's Autonomous Reflections serve those queries from Apache Iceberg tables on your own S3 storage, bypassing Redshift compute entirely. The result is a 40-60% reduction in Redshift compute costs in the first month, without migrating a single table.

Dremio provides a different approach. Instead of replacing Snowflake entirely, you can layer Dremio on top of it, offloading the expensive, repetitive queries to Dremio's engine while keeping Snowflake for the workloads it handles best. Dremio's Autonomous Reflections, AI-powered analytics, and federated query engine reduce the compute Snowflake needs to process, often cutting the bill by 40-60% in the first month.

If your team manages both a warehouse and a lake, give Claude the context it needs to actually help you. Using a dedicated MCP server bridges the gap between powerful language models and your complex data architecture.

This tutorial shows you how to build a supply chain analytics pipeline on Dremio Cloud that unifies procurement, warehouse, and sensor data. You'll seed sample datasets, model them through Bronze, Silver, and Gold views, and use the AI Agent to evaluate supplier performance and inventory risk through natural language questions.

This tutorial shows you how to build a healthcare analytics pipeline on Dremio Cloud that unifies patient, claims, and prescription data in real time. You'll create sample datasets, model them into Bronze, Silver, and Gold views, and use the AI Agent to analyze readmission risk and cost patterns through natural language questions.

This tutorial shows you how to build a financial analytics pipeline on Dremio Cloud in 30 minutes. You'll seed sample banking, market, and compliance data, model it into a medallion architecture, and use the AI Agent to detect transaction anomalies and assess account risk through natural language questions.