BigQuery gives data teams a serverless environment for storing and querying company data at scale. The harder part is making that data useful across the business, especially when an answer depends on company terminology or information that still lives in operational tools outside the warehouse.
Supper connects directly to BigQuery so employees can ask questions, investigate the results, and work with data from other connected sources. BigQuery remains responsible for storing and processing the warehouse data. Supper uses that environment alongside the company's business definitions and other data sources to answer questions in context.
For BigQuery customers, getting started is fairly light. After the company provisions a Google Cloud service account, Supper can inspect the permitted data, build an initial semantic model, and create an evaluation corpus for testing. Users can typically begin asking questions within one or two days.
The roles of Supper and BigQuery
Companies use BigQuery to store and analyze large amounts of structured and semi-structured data within Google Cloud. Gemini in BigQuery can generate SQL and data insights, while BigQuery Conversational Analytics lets companies create data agents that answer natural-language questions over selected sources.
Supper gives a wider group of employees a way to work with BigQuery data. Users can ask questions conversationally, continue an analysis through follow-up questions, create charts, and save recurring work as reusable Skills. Supper can use SQL to query BigQuery and Python when an analysis requires calculations or additional processing.
Many business questions also depend on context that is difficult to capture in warehouse metadata alone. The meaning of a metric may depend on an internal definition, an exception to the normal calculation, or information maintained in another system. Supper keeps that context in its semantic model and applies it when answering questions.
Connecting Supper to BigQuery
A company begins by provisioning a Google Cloud service account for Supper. Supper uses that account to inspect the BigQuery resources available to it, create the initial semantic model, and generate an evaluation corpus that tests how well the model answers questions.
The customer's part of the initial connection generally takes about five minutes. Supper completes the automated setup and testing in the background, with users typically able to begin asking questions within one or two days. The exact timeline depends on the size and condition of the BigQuery environment.
Supper queries BigQuery directly. The company can keep its existing Google Cloud architecture and data pipelines, while BigQuery continues to process the warehouse queries.
The semantic model develops further after launch. Questions from real users expose missing definitions and areas where Supper needs more context. Supper can identify many of these issues automatically, while decisions involving company-specific business rules remain with the customer. During the first month, this review usually requires anywhere from a few minutes to a few hours of customer involvement.
How Supper uses BigQuery context
BigQuery provides Supper with schema metadata about the datasets, tables, views, and columns available through the service account. Google Cloud can also contain useful business context in table descriptions, Knowledge Catalog, BigQuery data agents, LookML, or models maintained through tools such as dbt.
Supper begins with the structure it can inspect and the approved context supplied during implementation. Existing definitions can be incorporated into the Supper semantic model, allowing the data team to preserve work it has already reviewed instead of starting from an undocumented warehouse.
Supper's semantic model can include company terminology, calculation instructions, known data issues, source-selection guidance, and reusable analytical processes. This knowledge is maintained at the model level so it can be applied consistently across users and questions.
This is useful for companies whose business meaning is spread across several parts of their data environment. Supper gives its analytics agents one operational model for interpreting questions, even when the underlying documentation comes from more than one system.
Analysis across BigQuery and SaaS data
Important business information often remains spread across operational applications. A company may keep historical transaction and product data in BigQuery while the latest customer activity remains in a CRM.
Take customer acquisition performance as an example. Answering the question may require historical conversion and revenue data from BigQuery, along with current pipeline activity from the CRM. Supper can determine which sources are relevant, query them according to the user's permissions, and apply the company's approved definitions throughout the analysis.
The person asking the question does not have to know where each field lives or how the systems relate. They can ask the business question directly and continue investigating the result within the same conversation.
This lets teams analyze BigQuery alongside connected SaaS applications. It also means that a useful answer does not have to wait until every relevant field has been loaded into BigQuery and modeled there.
Permissions and administrative oversight
BigQuery supports access controls at the project, dataset, and table levels. It can also enforce row-level security and column-level access controls. These controls determine what the Supper service account is permitted to query.
Because Supper connects through a service account, it does not automatically assume each employee's individual Google Cloud identity. Administrators use Supper's user-level entitlements to control which parts of the available BigQuery data and connected SaaS sources each person can access.
Administrators can review how people are using company data through Supper's Admin Control Center. They can see the questions being asked, investigate how data is being accessed, and review issues found in the semantic model. This gives the data team continued oversight after AI analytics has been made available to the wider company.
When should a BigQuery customer use Supper?
BigQuery Conversational Analytics or Looker may cover the use case when analysis remains within Google Cloud and the intended users already work comfortably in those environments.
Supper is relevant when a company wants to make BigQuery data accessible through a dedicated business analytics product or when questions regularly depend on information outside the warehouse. It also gives the data team a place to manage company-specific definitions and review how employees use AI to access data.
Supper uses seat-based pricing. The cost is tied to the number of users rather than the number of tokens consumed during an analysis, making costs easier to anticipate when questions require several analytical steps.
Frequently asked questions
Does Supper replace BigQuery?
No. BigQuery continues to provide the warehouse and query engine. Supper connects to BigQuery and gives business users another way to analyze the data stored there.
How does Supper connect to BigQuery?
The customer provisions a Google Cloud service account for Supper. Supper uses that connection to inspect the permitted datasets, build its initial semantic model, run evaluations, and query BigQuery directly.
Does Supper copy BigQuery data into another warehouse?
Supper queries BigQuery directly for warehouse analysis. Companies do not need to migrate or duplicate their BigQuery warehouse before they can begin using Supper.
How is Supper different from BigQuery Conversational Analytics?
BigQuery Conversational Analytics lets companies create Gemini-powered data agents over BigQuery sources. Supper provides a business-facing analytics experience with its own semantic model, reusable Skills, administrative controls, and support for questions that use BigQuery alongside connected SaaS sources.
Can Supper use existing BigQuery metadata and business definitions?
Yes. Supper can begin with the schema metadata available through BigQuery and incorporate approved definitions maintained in the company's existing data environment. The data team can then add or refine context within Supper as real questions reveal what the model needs.
How long does the BigQuery setup take?
Provisioning the connection generally takes about five minutes of customer work. Supper can usually prepare the initial semantic model and evaluation corpus within one or two days, after which users can begin asking questions.