The Dremio Blog

At a recent customer panel moderated by Maeve Donovan, Senior Product Marketing Manager at Dremio, three of Dremio's largest customers came together with Tomer Shiran, Founder of Dremio, to share their experiences implementing Dremio's intelligent lakehouse platform. Antonio Abi Saad, Group Chief Data Officer at Sodexo, Karl Smolka, Associate Vice President - Data Platform & […]

By the end, you’ll understand how MCP enables secure, modular communication between LLMs and the systems they need to work with.

What if we had a standard that let any agent talk to any data source or tool, regardless of where it lives or what it’s built with? That’s exactly what the Model Context Protocol (MCP) brings to the table.

Modern data teams are under pressure to deliver faster insights, support AI initiatives, and reduce architectural complexity. To meet these demands, more organizations are adopting active data architectures—frameworks that unify access, governance, and real-time analytics across hybrid environments. In the newly released Dresner 2025 Active Data Architecture Report, Dremio was ranked #1—recognized as a top […]

Dremio Auth Manager is intended as an alternative to Iceberg’s built-in OAuth2 manager, offering greater functionality and flexibility while complying with the OAuth2 standards. Dremio Auth Manager streamlines authentication by handling token acquisition and renewal transparently, eliminating the need for users to deal with tokens directly, and avoiding failures due to token expiration.

Enter agent frameworks — open-source libraries and developer toolkits that let you create goal-driven AI systems by wiring together models, memory, tools, and logic. These frameworks enable some of the most exciting innovations in the AI space… but they also come with trade-offs.

Now, with the introduction of format version 3, Iceberg pushes the boundaries even further. V3 is designed to support more diverse and complex data types, offer greater control over schema evolution, and deliver performance enhancements suited for large-scale, high-concurrency environments. This blog explores the key differences between V1, V2, and the new V3, highlighting what makes V3 a significant step forward in Iceberg's evolution.

We’ve explored how Large Language Models (LLMs) work, and how we can improve their performance with fine-tuning, prompt engineering, and retrieval-augmented generation (RAG). These enhancements are powerful — but they’re still fundamentally stateless and reactive.

Clustering is a data layout strategy that organizes rows based on the values of one or more columns, without physically splitting the dataset into separate partitions. Instead of creating distinct directory structures, like traditional partitioning does, clustering sorts and groups related rows together within the existing storage layout.

this post, we’ll walk through the three most popular and practical ways to boost the performance of Large Language Models (LLMs): Fine-tuning Prompt engineering Retrieval-Augmented Generation (RAG) Each approach has its strengths, trade-offs, and ideal use cases. By the end, you’ll know when to use each — and how they work under the hood.

Enterprises today face increasing pressure to extract insights from data quickly while controlling spend. Yet, as data volumes explode across cloud and on-prem environments, traditional architectures often fall short—resulting in higher costs, rigid pipelines, and slower decision-making. The Dremio Intelligent Lakehouse Platform addresses these challenges by delivering faster insights and significant total cost of ownership […]

In this post, we’ll peel back the curtain on the inner workings of LLMs. We’ll explore the fundamental concepts that make these models tick: embeddings, vector spaces, and context windows. You’ll walk away with a clearer understanding of how LLMs “understand” language — and what their limits are.

Artificial Intelligence (AI) has become essential for modern enterprises, driving innovation across industries by transforming data into actionable insights. However, AI's success depends heavily on having consistent, high-quality data readily available for experimentation and model development. It is estimated that data scientists spend 80+% of their time on data acquisition and preparation, compared to model […]

This post kicks off our 10-part series exploring how AI evolved into LLMs, how to enhance their capabilities, and how the Model Context Protocol (MCP) is shaping the future of intelligent, modular agents.

Why SQL Must Evolve in the Era of Agentic Apps and Data-Aware AI SQL has long been the universal language of data. But with the rise of Generative AI and agentic applications, a major shift is underway. We're entering an era where natural language is the interface, and agents are the client. There are two […]