Denodo unveils DeepQuery for real-time data research

Denodo has launched DeepQuery, a Deep Research capability aimed at addressing the limitations of conventional generative AI tools in data analysis.

DeepQuery explained

DeepQuery operates differently from retrieval-augmented generation approaches, which typically focus on rephrasing indexed content. This new capability conducts structured reasoning across live and governed data sources, enabling users to investigate distributed datasets and pose complex "why" questions, such as analysing the causes of changes in customer retention across various regions.

With DeepQuery, users receive multi-step analytical answers within seconds, a process that would previously require a significant amount of manual analysis and cross-referencing across multiple data sets.

Addressing business needs

DeepQuery is built to handle open-ended business questions by leveraging real-time access to enterprise data from a range of formats and departmental systems. In contrast to traditional generative AI solutions—which tend to rephrase pre-existing content—DeepQuery analyses open questions and searches multiple systems and sources to provide structured, explainable answers rooted in current information.

The capability will also be able to incorporate external data sources—such as publicly available information, applications outside the organisation, and data from trading partners—to complement and enhance the information already held within a business.

This functionality enables users to interrogate complex, cross-functional queries that would previously take days for analysts to resolve, such as understanding the underlying reasons for quarterly changes in fund outflows. Rather than manually gathering data or generating multiple reports, DeepQuery provides connections to governed data in real time and applies reasoning capabilities to respond swiftly to intricate questions.

Integration and development

DeepQuery is being developed as a fully extensible component of the Denodo Platform and will be distributed as part of the Denodo AI SDK. The SDK offers pre-built APIs intended to streamline AI application development. This integration aims to allow developers and AI teams to use, experiment with, and incorporate the DeepQuery capability into various agents, copilots, or domain-specific solutions.

"With DeepQuery, Denodo is demonstrating forward-thinking in advancing the capabilities of AI. DeepQuery, driven by deep research advances, will deliver more accurate AI responses that will also be fully explainable."

This is according to Stewart Bond, Research VP, Data Intelligence and Integration Software at IDC, who spoke on the platform's potential impact compared to other solutions currently available.

While large language models, business intelligence tools, and other applications are starting to introduce deep research capabilities utilising public web data or data-lakehouse storage, Denodo's solution is anchored in enterprise data. Data delivered and managed by DeepQuery is structured, governed, and available in real-time, made possible by the logical data management inherent to the Denodo Platform and its data virtualisation framework.

The private preview phase of Denodo DeepQuery is currently underway, with Denodo inviting selected organisations to participate in its AI Accelerator Programme. Participants receive early access to DeepQuery's features and have the opportunity to provide input that will help shape its future development.

"As a Denodo partner, we're always looking for ways to provide our clients with a competitive edge. Denodo DeepQuery gives us exactly that. Its ability to leverage real-time, governed enterprise data for deep, contextualised insights sets it apart. This means we can help our customers move beyond general AI queries to truly intelligent analysis, empowering them to make faster, more informed decisions and accelerating their AI journey," said Nagaraj Sastry, Senior Vice President, Data and Analytics at Encora.

Model Context Protocol support

Denodo also announced support for the Model Context Protocol (MCP). With the inclusion of an MCP Server in the latest version of the Denodo AI SDK, any AI agents or applications utilising the SDK can be integrated with MCP-compliant clients. This aims to establish a reliable and standardised data foundation for organisations adopting agentic AI architectures based on open standards.

"AI's true potential in the enterprise lies not just in generating responses, but in understanding the full context behind them. With DeepQuery, we're unlocking that potential by combining generative AI with real-time, governed access to the entire corporate data ecosystem, no matter where that data resides. Unlike siloed solutions tied to a single store, DeepQuery leverages enriched, unified semantics across distributed sources, allowing AI to reason, explain, and act on data with unprecedented depth and accuracy," said Angel Viña, CEO and Founder of Denodo.