Starburst Introduces Context Studio, Extending Federation from Data to Context
Context Studio delivers business definitions alongside data at query time, so every AI agent works from the same
Press Release Disclaimer: This is a press release distributed through the XPR Media network. It has not been independently verified by our newsroom.
![]()
Starburst, the enterprise intelligence platform that unifies data and context together for AI agents, today announced Context Studio at Launch Point, its virtual event on building the data foundation for the AI-driven enterprise.
Starburst has always federated data: Context Studio now federates context. It gathers the definitions an organization already keeps, without a rebuild, and applies them alongside the data when an agent queries it. Context Studio extends Starburst Data Products into the Enterprise Context Layer, built for agents and people.
Trust holds enterprise AI back because agents answer from definitions that are missing or out of date. With Context Studio, every agent, application, and analyst gets the same definitions, traceable to their source and under the same access rules. Data without context guesses. Context without data goes stale. Together at query time, they become intelligence.
“Customers told us the agent isn’t the hard part. Context is,” said Justin Borgman, co-founder and CEO of Starburst. “And a better model won’t fix that. A smarter model working from the wrong definition gets to the wrong answer faster. Context Studio delivers business meaning together with the data, at query time, under each user’s identity and policy, so every answer is traceable to its source in any tool.”
Many semantic layers make enterprises rebuild their definitions inside one vendor’s tool. Context Studio works the other way, starting with the definitions an organization already has and managing them through their full lifecycle:
- Bring business knowledge in without a rebuild. Context Studio harvests definitions from the sources where they already live, including business catalogs, BI tools, metric stores, query history, and existing data products. Teams can also push in business rules captured in unstructured documents, such as policies, playbooks, and process guides.
- Approve and trace every definition. Each definition links to its source and goes through an approval flow before agents use it. When two sources disagree, Context Studio flags the conflict and a person decides which applies.
- Deliver one meaning to every agent. A context loop agent turns user feedback into proposed context improvements, which a person accepts or refines before the agent runs a full regression suite to confirm the change holds across every other answer. Context becomes a shared, governed asset for the whole organization, rather than an improvement that stays with one user.
- Improve context with every use. AIDA, or any agent that connects over MCP, receives the same definitions, with access policy enforced alongside data.
“I don’t want another catalog that people forget to update. Context Studio pulls what we already wrote into one place, traces every rule back to its source, and flags when two rules disagree. Our agents start from the same answer someone on my team would give,” said Zach Eckels, Staff Data Engineer, Nerdy.
“Enterprise AI is only as reliable as the business context behind it. Organizations have invested years building business definitions and governance practices, but that knowledge is often fragmented across systems and difficult for AI agents to access consistently,” said Mike Leone, VP & Principal Analyst, Moor Insights & Strategy. “Bringing those existing definitions together with federated data, without forcing organizations to rebuild them, is an important step toward making agentic AI work at enterprise scale. Starburst is addressing a fundamental gap between making enterprise data accessible and making it meaningful to AI.”
AIDA, generally available since May, now runs on Context Studio. Drawing on the same governed definitions, AIDA answers across multiple data products in a domain, not just one. A new dashboard sub-agent builds visuals inside Starburst, under the same governance.
Starburst also shared updates across the platform:
- Turn expert knowledge into data products. A data products creation agent converts a conversation with a domain expert into a draft data product, extending context harvesting from sources to people.
- See platform usage, cost, and failures in one place. Starburst Mission Control gives platform teams a single view, plus an expert agent that recommends changes.
- Run managed Starburst inside your own cloud. Runs Starburst Galaxy in a customer’s own AWS account, with Starburst managing operations, in a BYOC “bring your own cloud” deployment.
- Automate Apache Iceberg table maintenance. Starburst LakeOps handles table maintenance automatically and monitors table health across the lakehouse.
- Accelerate queries on GPUs. Starburst Torin, the GPU-native query engine announced October 21, runs queries up to 7x faster in Starburst benchmarks.
Availability
Context Studio is available for private preview now in Starburst Galaxy and Starburst Enterprise for cloud or on- premises deployment.
About Starburst
Starburst delivers enterprise intelligence at scale by giving organizations secure, governed access to all their data, wherever it lives. Built for distributed data environments across on-premises systems, multiple clouds, and hybrid architectures, Starburst helps enterprises power AI and analytics without the cost and complexity of traditional data consolidation.
By enabling federated access to complete enterprise context, Starburst helps AI platforms, applications, and teams move from pilots to production with trusted, actionable data. Built on open standards with Trino and Apache Iceberg, Starburst integrates with existing technologies while helping organizations avoid vendor lock-in. For more information, visit starburst.ai.
View source version on businesswire.com: https://www.businesswire.com/news/home/20261118214825/en/
Media gallery

