- Glean’s new structured query agents make it easy for both technical and non-technical users to extract real-time insights from BigQuery by enabling direct SQL queries for experts and natural language queries for everyone else, all within a single interface.
- These capabilities empower teams to automate reporting, analyze key business metrics, and drive decisions without needing deep SQL expertise or switching between multiple tools, streamlining access to business-critical data.
- The integration works seamlessly with Glean’s broader ecosystem, allowing users to pair data insights with automation, notifications, and workflow triggers, with ongoing plans to expand support for additional data sources and query types.
Although data powers modern enterprises, much of it still resides in siloes across data warehouses, documents, and applications. Although the term “Big Data” was popularized in the 1990s, for most end users, tapping into siloed structured data requires data science teams, SQL knowledge, or database schema expertise, making it difficult to access, analyze, and put data to use to inform decisions. According to Gartner, AI agents are set to change that, with 64% of respondents identifying analytics and BI among the top three domains where AI agents will have the most impact.
Today, we’re excited to announce a major expansion of Glean’s data analysis capabilities making the extraction of insights from structured data in BigQuery simple for everyone, regardless of SQL expertise. Now, with Glean structured query agents, you can now get real-time insights from BigQuery through either direct SQL or natural language using Google’s Conversational Analytics API, transforming complex data queries into simple, intuitive conversations.
These new updates help teams unlock actionable insights from their business-critical data systems and automate sophisticated workflows. Importantly, these capabilities are available directly in the tools they use most, without requiring significant time investments and technical expertise.
Leveraging insights from BigQuery data with AI
As one of the most widely used cloud data warehouses, BigQuery, stores massive volumes of business data for many industries. With so much critical business data stored in BigQuery, the ability to quickly access, understand, and act on these insights becomes essential for effective decision-making yet a lack of technical expertise or bandwidth keeps this out of reach for most teams.
Now, from a single Glean interface, users can tap into BigQuery either through a deterministic SQL action for power users or a natural-language action that translates plain-English questions into real-time insights.
.webp)
"Customers have invested heavily in building a central source of truth with BigQuery, but the final mile—getting insights into the hands of decision-makers—has always been a challenge. Glean's structured query agents are a game-changer. By leveraging Google's Conversational Analytics API, Glean has built a seamless bridge that allows users to query petabyte-scale data in natural language, right in their flow of work. It’s the perfect synergy of Glean's user-centric AI platform and BigQuery's unmatched scale and performance."
— Yasmeen Ahmed, Managing Director, Data Cloud, Google Cloud
One interface, two ways to work with BigQuery
In Glean, teams can choose the interface that fits their skills: power users can write SQL directly for exact query specification and familiarity, and non-technical users can ask questions in plain English via Google’s Conversational Analytics API—all within the same agent experience. Here’s how each structured query agent works:
Search BigQuery with SQL
This action is geared toward analysts and data engineers who want to write and execute their own SQL queries. This enables a Glean agent to execute your SQL as-is, keeping full control over CTEs, window functions, ARRAY/STRUCT handling, precise joins, and partition filters for predictable, audit-ready runs. This is ideal for parameterized reports, SLAs, and data-quality checks where the query shape matters; and for steering cost-performance via strict partition filters or materialized views. The user can either supply SQL verbatim, or have AI decide the value and pass a query in the agent instructions.
Gemini BigQuery Analytics with Context
What about users without SQL knowledge? Instead of going to your data science team for every ad-hoc request, you can ask questions like “Which campaigns drove the highest pipeline last quarter?” or “Which features have the highest weekly active usage among enterprise accounts?” and a Glean structured query agent forwards the user’s natural language query to BigQuery, where Google converts it to SQL. Glean displays this SQL in the intermediate steps and returns the final answer to the user in plain English.
Doing more with AI through Glean
With these new flexible, powerful ways to query your BigQuery data, Glean makes it easy to automate reporting, analyze key business metrics, and drive business decisions, all without the need to jump between tabs, write complex SQL, or rely on technical experts. Whether you are an experienced data scientist or have minimal SQL knowledge, users now have a single place to get answers from their Google data warehouses.
These structured data features work seamlessly alongside our connector ecosystem, search, and automation capabilities. They can be paired with actions like notifications, report generation, or custom workflow triggers in agents, turning every query into an opportunity to automate and collaborate. We’ll also continuously deliver upcoming expansions to more data sources and new query types as well.
Ready to try these new features or see them in action? Check out the demo video above or this page to learn more about how structured data can streamline your work.
