PALO ALTO, Calif., May 28, 2026 (GLOBE NEWSWIRE) — DataHub, the leading context platform company, today introduced a major new release of DataHub Cloud that can ingest, structure, improve and serve trusted context to analytics agents, dramatically increasing their accuracy and reliability in production. DataHub Cloud v1 serves as a context layer that sits between analytics agents, like Databricks Genie and Snowflake Intelligence, and enterprise data from data stores, like data warehouses and data lakes, to give agents trusted context to get analytics right and smarter with every query.
DataHub will be showcasing the new release at Snowflake Summit next week, Databricks Data + AI Summit the week of June 15 and the DataHub June Town Hall on June 25 at 11 a.m. ET / 8 a.m. PT.
“Starting with Snowflake metadata alone, our analytics agent answered about half of our benchmark questions correctly,” said Ronald Angel, Product Manager, Data Platform, Miro. “After layering in DataHub Cloud as our context platform, including data product documentation, cross-source context and business meaning derived from our query history, we nearly doubled accuracy from close to 50% to around 90%.”
“Every system in the enterprise holds context, but DataHub Cloud is the platform built to unify it, and that makes it the natural foundation for AI agents,” said Björn Barrefors, Metadata Management Lead, ICA. “We have already seen it surface institutional knowledge that analysts would never have found on their own, while also flagging known data quality issues before the query ran. The next step is putting that context layer behind every data question our business asks.”
Today AI agents frequently produce confident but factually incorrect outputs often by guessing to fill in gaps in context. They do not know what metric definition or underlying data to use and could end up using outdated data. Agents need a trusted source of truth for what data means, where it comes from, how fresh it is and how the organization actually uses it to ensure accuracy.
According to Gartner®, “A robust context layer is foundational to AI success. D&A leaders must prioritize its development to empower AI agents with the knowledge necessary for consistent, reliable and cost-efficient decision automation.”1
“Context engineering at scale requires AI- and human-curated knowledge of myriad signals, including usage patterns, historical accuracy, business definitions and semantic meaning. DataHub addresses these requirements to help agents synthesize wide-ranging structured and unstructured data, generate higher-quality results and learn over time. This contributes to the next wave of innovation for data intelligence platforms,” said Kevin Petrie, VP of Research at BARC.
Unlike retrieval layers that rely on developer-defined schemas at deployment time, DataHub Cloud is a context platform that gives analytics agents a continuously refreshed, expert-enriched source of trusted context about enterprise data at scale, dramatically improving accuracy and reliability in production. Before any agent generates SQL, DataHub supplies it with the context that makes the answer trustworthy: unified metadata ingested automatically from more than 100 sources, semantic meaning extracted continuously from years of analyst query history and expert-validated definitions curated by the people who know the data best.
“We turn years of query history into a living knowledge base, fuse in real-time operational signals and compound it with every expert correction from the field,” said Shirshanka Das, co-founder and CTO of DataHub. “Every change is timestamped and versioned; agents don’t just know the right answer, they know why it changed. That’s auditable context, and it’s how agents stop hallucinating and start earning trust.”
Breakthrough new features in DataHub Cloud, designed to address the talk-to-data use case, include:
- Context Ingestion addresses context fragmentation, the issue of operational and semantic meaning of data scattered across multiple systems, tools and documents. It builds a unified context graph from structured catalog content, semantic metric definitions from tools, like dbt and Power BI, and unstructured institutional knowledge from Notion, Confluence and similar sources. All context is chunked, embedded and retrievable in real time via GraphQL, MCP or Ask DataHub.
- Context Intelligence converts enterprise query history into a structured semantic index. When an analytics agent receives a question, it retrieves not just schema but validated query patterns that have answered similar questions before, complete with proven joins, filters and aggregation logic. Unlike approaches that require developers to hand-author semantic models before agents can be trusted, Context Intelligence turns existing query history into an immediately useful knowledge base — so accuracy improves from day one without months of manual setup. Context Intelligence turns existing query history, BI dashboards and unstructured documents into an immediately useful semantic index. The result is measurably better accuracy.
- Context Hub gives domain experts a workspace to review, approve and enrich AI-proposed context, collaborate with colleagues and simulate the impact of context changes on text-to-SQL results before publishing. Every expert interaction feeds back into the system so context quality improves continuously. Context Hub gives domain experts a dedicated workspace to review AI-proposed context, resolve conflicting definitions and simulate how changes affect text-to-SQL results before publishing so context quality compounds over time rather than drifting as data and business definitions evolve.
- Context Activation lets any agent or workflow access and use DataHub context by adding prebuilt skills and an enhanced Agent Context Kit to DataHub Cloud’s full API and SDK and native user experience surfaces built for data practitioners.
In addition, because DataHub Cloud delivers precise, pre-validated context rather than raw schema, analytics agents require significantly fewer tokens to answer each question, reducing inference costs at scale.
About DataHub
DataHub transforms enterprise data into trusted context, enabling intelligent decision making by humans and AI agents. The company was founded by the creators of the popular DataHub open source product that has more than 15,000 contributors and is used by thousands of organizations. The company’s flagship product, DataHub Cloud, is the leading context management platform trusted by the Global 2000 to ensure that context is always relevant, reliable and continuously refreshed across the entire data. estate. DataHub is backed by Bessemer Venture Partners, LinkedIn and 8VC. For more information, go to: https://datahub.com/.
1 Gartner, The 3 Core Components of the Context Layer for AI Agents, Andrés García-Rodeja, Michael Gonzales, et al., 11 March 2026
GARTNER is a trademark of Gartner, Inc. and/or its affiliates.
Media and Analyst Contact:
Amber Rowland
amber@therowlandagency.com
+1-650-814-4560
An image accompanying this announcement is available at https://www.globenewswire.com/NewsRoom/AttachmentNg/1ac5b9fe-1bd0-4b5a-bf76-2b9899181fae
