Supercharge data cloud workflows with agentic AI

Automate the data life cycle, empower your teams, and accelerate insights with intelligent agents.

Overview

What are AI agents?

AI agents are software systems that use AI to pursue goals and complete tasks on behalf of users. They show reasoning, planning and memory and have a level of autonomy to make decisions, learn, and adapt. Learn more about AI agents.

How can AI agents be used for data workflows?

AI agents help data teams automate repetitive tasks like data cleaning and labeling, and business users analyze data and predict outcomes using natural language. This frees up various teams from mundane work, allowing them to focus on higher-value strategic initiatives. The result is faster insights, quicker innovation, and more efficient scaling of AI across the organization.

Who can use AI agents for data workloads?

AI agents act as powerful allies across the entire data organization:

  • Data engineers: Automate pipeline creation and maintenance using natural language prompts
  • Data scientists: Streamline data wrangling, model evaluation, and feature engineering
  • Analysts and business users: Gain instant insights and generate visualizations by asking questions in plain natural language, removing the need for specialized coding
  • Data administrators: Automate database onboarding, monitoring, and observability to maintain a healthy data estate

How It Works

Google Cloud provides specialized, first-party agents designed to automate data engineering, data science, analytics and data administration workflows. Furthermore, our flexible APIs and an open developer ecosystem allow developers to extract and embed Google’s Data Cloud intelligence directly into custom applications, internal management portals, or third-party surfaces like Slack.

Agentic Data Cloud Video
Common Uses

Assistive experiences

Supercharge day-to-day workflows

AI-powered assistance across Google’s Data Cloud streamlines your operational and analytics workflows. Across BigQuery, Spanner and AlloyDB, Gemini assists you to easily generate, complete, and explain complex queries. Gemini in BigQuery also supports Python code assistance. It also provides context-aware recommendations for data preparation and customizable SQL translations, making complex data tasks highly accessible and efficient.

    Supercharge day-to-day workflows

    AI-powered assistance across Google’s Data Cloud streamlines your operational and analytics workflows. Across BigQuery, Spanner and AlloyDB, Gemini assists you to easily generate, complete, and explain complex queries. Gemini in BigQuery also supports Python code assistance. It also provides context-aware recommendations for data preparation and customizable SQL translations, making complex data tasks highly accessible and efficient.

      Out-of-the-box autonomous agents

      Automate end-to-end workflows

      Google Cloud provides first-party agents to automate data engineering, science, and analytics. The Data Engineering Agent in BigQuery autonomously manages pipeline creation and migration using Knowledge Catalog metadata for transformations. The Data Science Agent speeds up development by planning data prep and ML training with full contextual awareness and autonomous autocorrection. The Database Onboarding Agent evaluates user requirements to recommend the best Google Cloud database and guides users through the provisioning process. The Database Observability Agent proactively monitors database fleet performance, identifies anomalies, and provides intelligent recommendations and multi-turn remediation workflows for troubleshooting and optimization.

      Deep Research Agent moves beyond simple single-step lookups to conduct extensive corporate investigations. It independently structures multi-stage queries, traces cross-system data lineages, blends structured tables with unstructured data (like PDFs, contracts, and images), and synthesizes comprehensive research briefs outlining root causes and future trends.

        Automate end-to-end workflows

        Google Cloud provides first-party agents to automate data engineering, science, and analytics. The Data Engineering Agent in BigQuery autonomously manages pipeline creation and migration using Knowledge Catalog metadata for transformations. The Data Science Agent speeds up development by planning data prep and ML training with full contextual awareness and autonomous autocorrection. The Database Onboarding Agent evaluates user requirements to recommend the best Google Cloud database and guides users through the provisioning process. The Database Observability Agent proactively monitors database fleet performance, identifies anomalies, and provides intelligent recommendations and multi-turn remediation workflows for troubleshooting and optimization.

        Deep Research Agent moves beyond simple single-step lookups to conduct extensive corporate investigations. It independently structures multi-stage queries, traces cross-system data lineages, blends structured tables with unstructured data (like PDFs, contracts, and images), and synthesizes comprehensive research briefs outlining root causes and future trends.

          "The Data Science Agent has been a game-changer for our data science team. It streamlines our workflow by taking simple, natural language instructions and translating them into multi-step data science code, which it then executes. We longer have to start from scratch with the code. Features like code completion, error fixing, and natural language-based visualization have shown the team how AI can be an accelerator for data scientists.” - Lorraine Zheng, Data Scientist at Snap Inc.

          “The agent provides solutions that enable us to explore new development approaches, showing strong potential to address complex data engineering tasks. It demonstrates an impressive ability to correctly interpret our requirements, even for sophisticated data modeling tasks like creating SCD Type 2 dimensions. In its current state, it already delivers value in automating maintenance and small optimizations, and we believe it has the foundation to become a truly distinctive tool in the future.”- Fernando Calo, Lead Data Engineer at the Spanish-language news and entertainment group PRISA

          “During the migration journey to a Dataform environment, the Data Engineer Agent successfully replicated all existing data and transformations scripts with 100% automation and zero manual intervention. This achievement resulted in a 90% reduction in the time typically required for manual ETL migration, significantly accelerating the transition." - Chris Benfield, Head of Engineering, Vodafone

          “Process documentation is often a tedious task for developers, but with the Dataform Data Engineering Agent this effort is fully automated. The agent was able to accurately generate documentation directly from our Dataform project files, following the standards and styles we defined. This allowed us to keep our documentation consistently up to date as changes were introduced, enabling zero manual intervention in our documentation workflow. It proved to be a tool with significant potential.” - Maximiliano Morales, Data Engineer at a leading telco in Argentina


            Conversational Analytics agents

            Make insights available for technical and business users

            BigQuery Conversational Analytics allows data professionals to extract insights and run predictions on multimodal and multi-format lakehouse data via natural language chat with high accuracy grounded in entities, relationships and business metrics. Conversational Analytics in databases delivers real-time operational intelligence, enabling you to interact with Cloud SQL, Spanner, and AlloyDB using natural language. Looker Conversational Analytics enables business teams to use natural language and a governed semantic layer for trusted decision-making, which reduces the workload for technical teams. Looker dashboard agents further enhance this experience by adding natural language queries and automated summaries directly to dashboards. For real-time operational needs, proactive agentic workflows allow you to transition from reactive reporting to event-driven actions by automatically investigating anomalies and suggesting mitigation plans.

              Make insights available for technical and business users

              BigQuery Conversational Analytics allows data professionals to extract insights and run predictions on multimodal and multi-format lakehouse data via natural language chat with high accuracy grounded in entities, relationships and business metrics. Conversational Analytics in databases delivers real-time operational intelligence, enabling you to interact with Cloud SQL, Spanner, and AlloyDB using natural language. Looker Conversational Analytics enables business teams to use natural language and a governed semantic layer for trusted decision-making, which reduces the workload for technical teams. Looker dashboard agents further enhance this experience by adding natural language queries and automated summaries directly to dashboards. For real-time operational needs, proactive agentic workflows allow you to transition from reactive reporting to event-driven actions by automatically investigating anomalies and suggesting mitigation plans.

                "With BigQuery's Conversational Analytics, we've further accelerated how our teams interact with data at Pet Circle. By allowing our teams to ask complex data questions in natural language, we’ve drastically reduced our time-to-insight. It empowers our data teams to create agents for non-technical teams, enabling them to make faster, data-driven decisions that ultimately help us deliver a better experience for pet parents." - Alistair Venn, CEO of Pet Circle

                "Effective conversational analytics starts with a unified, audited data layer. If teams aren't speaking the same data language, AI systems can't reliably interpret queries or surface accurate insights." - John Pettit Chief Technology Officer, Promevo

                “Our vision is for customers not only to see what happened, but to have a conversation with their data and receive intelligent recommendations inside IRIS Fleet and our other products. We believe the real opportunity is just beginning.” - Gerardo Ortiz, Head of Product and Digital Transformation, Métrica Móvil.

                  Publish agents in Gemini Enterprise

                  Make agents discoverable

                  Gemini Enterprise allows practitioners and business users to gain instant insights by simply asking questions in natural language. By publishing conversational agents built in BigQuery, Looker, Lakehouses, and Databases to the centralized Gemini Enterprise Agent Gallery, you can empower users to access enterprise data systems through a single interface. This approach completely abstracts the underlying technical complexities of the data ecosystem while ensuring that data access remains secure, audited, and governed within daily productivity workspaces. From Gemini Enterprise, administrators can easily provision access, ensuring that data interaction remains secure, audited, and governed within their daily productivity workspaces.

                  Publishing agents to Gemini Enterprise
                    Make agents discoverable

                    Gemini Enterprise allows practitioners and business users to gain instant insights by simply asking questions in natural language. By publishing conversational agents built in BigQuery, Looker, Lakehouses, and Databases to the centralized Gemini Enterprise Agent Gallery, you can empower users to access enterprise data systems through a single interface. This approach completely abstracts the underlying technical complexities of the data ecosystem while ensuring that data access remains secure, audited, and governed within daily productivity workspaces. From Gemini Enterprise, administrators can easily provision access, ensuring that data interaction remains secure, audited, and governed within their daily productivity workspaces.

                    Publishing agents to Gemini Enterprise

                      Build your own custom agents

                      Leverage open source tools and frameworks

                      Developers can easily build and embed custom agents to tackle unique enterprise data challenges. The Conversational Analytics API lets you embed natural-language query functionality directly into custom applications, internal tools, or automated workflows. The BigQuery ADK integration toolset provides ready-to-use functions for schema exploration, querying, and forecasting. Querydata for databases is available for Cloud SQL, AlloyDB, and Spanner to help you build agents for operational data. The BigQuery Agent Analytics plugin for ADK allows you to stream agent activity data directly to BigQuery for real-time observability and evaluation with a single line of code. To further streamline operations, the Looker block for BigQuery Agent Analytics provides a turn-key solution for monitoring, debugging, and optimizing AI agents.

                      Building agents with Conversational Analytics API
                        Leverage open source tools and frameworks

                        Developers can easily build and embed custom agents to tackle unique enterprise data challenges. The Conversational Analytics API lets you embed natural-language query functionality directly into custom applications, internal tools, or automated workflows. The BigQuery ADK integration toolset provides ready-to-use functions for schema exploration, querying, and forecasting. Querydata for databases is available for Cloud SQL, AlloyDB, and Spanner to help you build agents for operational data. The BigQuery Agent Analytics plugin for ADK allows you to stream agent activity data directly to BigQuery for real-time observability and evaluation with a single line of code. To further streamline operations, the Looker block for BigQuery Agent Analytics provides a turn-key solution for monitoring, debugging, and optimizing AI agents.

                        Building agents with Conversational Analytics API

                          Data Agent Kit

                          Bring Data Cloud skills to your IDE or CLI

                          The Data Agent Kit streamlines your workflows by bundling secure Model Context Protocol (MCP) tools, native IDE plugins, and pre-codified data engineering and data science skills into a single, open-source package. Bringing these capabilities directly into IDEs like VS Code, Claude Code, Codex, and Antigravity CLI shifts the developer's role from manually writing pipeline code to intent-driven development across the entire data estate. Furthermore, developers can leverage the open-source MCP Toolbox to securely connect agents to AlloyDB, BigQuery, Spanner, Cloud SQL, Knowledge Catalog, and Apache Spark. Get started with the Data Agent Kit.

                          Data Agent Kit
                            Bring Data Cloud skills to your IDE or CLI

                            The Data Agent Kit streamlines your workflows by bundling secure Model Context Protocol (MCP) tools, native IDE plugins, and pre-codified data engineering and data science skills into a single, open-source package. Bringing these capabilities directly into IDEs like VS Code, Claude Code, Codex, and Antigravity CLI shifts the developer's role from manually writing pipeline code to intent-driven development across the entire data estate. Furthermore, developers can leverage the open-source MCP Toolbox to securely connect agents to AlloyDB, BigQuery, Spanner, Cloud SQL, Knowledge Catalog, and Apache Spark. Get started with the Data Agent Kit.

                            Data Agent Kit

                              Pricing

                              ServicesUsage typePrice (USD)

                              BigQuery: Data Science Agent, Data Engineering Agent, and Conversational Analytics Agents

                              Input data

                              $3

                              per million tokens

                              Output data 

                              $20

                              per million tokens

                              Find detailed pricing for BigQuery, Looker and Gemini Code Assist.

                              BigQuery: Data Science Agent, Data Engineering Agent, and Conversational Analytics Agents

                              Usage type

                              Input data

                              Price (USD)

                              $3

                              per million tokens

                              Output data 

                              Usage type

                              $20

                              per million tokens

                              Find detailed pricing for BigQuery, Looker and Gemini Code Assist.

                              Pricing calculator

                              Estimate your monthly costs, including region-specific pricing and fees.

                              Custom quote

                              Connect with our sales team to get a custom quote for your organization.

                              Start your proof of concept

                              New customers get $300 in free credits to spend on BigQuery

                              Learn more about BigQuery

                              Data analytics design patterns

                              Query data—without a credit card—with BigQuery sandbox

                              Data analytics technical guides

                              Google Cloud