Google Announces New AI Agents for Data Analysis & Science

Google has introduced a suite of six AI agents designed to automate and simplify the labor-intensive tasks faced by data teams. These new "agentic" tools can build data pipelines, debug code, and answer complex business questions—all without requiring users to write SQL.

Key Highlights

• AI agents launched in BigQuery, GitHub, and Spanner to automate data workflows
• Gemini-powered APIs enable developers to embed conversational analytics into applications
• BigQuery now supports AI-native SQL and vector search for enhanced query capabilities
At Google Cloud Next Tokyo, the company unveiled these AI agents aimed at data engineers, scientists, analysts, and developers. This initiative is part of Google's vision for an "agentic enterprise," where intelligent agents proactively assist users by understanding their needs and performing the heavy lifting.

BigQuery AI Agents

Google introduced the Data Engineering Agent that can construct entire data pipelines from simple natural language prompts. For example, a user can say, "Clean this CSV, join it with sales data, and push it into BigQuery," and the agent executes the task automatically. For more complex workflows, the Data Science Agent within BigQuery Notebooks supports end-to-end model building, including visualizations and reasoning.

Conversational Analytics Agent

The Conversational Analytics Agent has been upgraded with a Code Interpreter that runs Python code behind the scenes. This allows business teams and analysts to ask intricate questions like "Segment customers by behavior in Q2," and receive the code, charts, and insights securely within their enterprise data environment.

Developer-Focused Gemini CLI GitHub Actions

Developers benefit from the Gemini CLI GitHub Actions, an open-source AI agent integrated into repositories. It can triage issues, review pull requests, and respond to @mentions to perform specific tasks. It operates seamlessly with Google Cloud’s secure Workload Identity Federation.

Infrastructure Enhancements

BigQuery now features an AI Query Engine that supports LLM-style queries directly within SQL. It also offers hybrid semantic search, vector embedding generation, and a new columnar engine for Spanner, bridging OLTP and OLAP workloads. These tools extend beyond structured data to support unstructured data types such as images, audio, and video. The Spanner columnar engine can execute analytical queries up to 200 times faster, while BigQuery introduces multimodal tables capable of storing and querying diverse data types together. Google is also releasing APIs for developers to embed conversational analytics into their own applications and is adopting open standards like the Model Context Protocol to ensure interoperability with other AI tools. Most of these features are rolling out now and are available at no additional cost within existing BigQuery and Looker pricing plans.

---

Source: Originally published at Maginative on August 5, 2025.

---

Frequently Asked Questions (FAQ)

What are Google's new AI agents for data teams?

Google has launched six new AI agents designed to automate and simplify complex data tasks. These agents can build data pipelines, debug code, and answer business questions using natural language, eliminating the need for users to write SQL.

What is an "agentic enterprise" in Google's vision?

An "agentic enterprise" is Google's vision where intelligent AI agents proactively assist users by understanding their needs and handling demanding tasks, thereby streamlining workflows.

What are the key capabilities of the BigQuery AI agents?

The BigQuery AI agents include a Data Engineering Agent for constructing data pipelines from natural language prompts and a Data Science Agent for supporting end-to-end model building within BigQuery Notebooks.

How does the Conversational Analytics Agent work?

The upgraded Conversational Analytics Agent uses a Code Interpreter that executes Python code behind the scenes, allowing users to ask complex data questions in natural language and receive code, charts, and insights directly.

What benefits do Gemini CLI GitHub Actions offer to developers?

Gemini CLI GitHub Actions are open-source AI agents integrated into repositories that can triage issues, review pull requests, and respond to @mentions for specific tasks, improving developer workflows.

What infrastructure enhancements has BigQuery introduced?

BigQuery now features an AI Query Engine supporting LLM-style SQL queries, hybrid semantic search, and vector embedding generation. It also introduces multimodal tables for handling diverse data types.

How does the Spanner columnar engine improve performance?

The Spanner columnar engine can execute analytical queries up to 200 times faster, bridging OLTP and OLAP workloads.

Crypto Market AI's Take

Google's foray into agentic AI for data teams mirrors the broader trend of AI integration across industries, including finance and cryptocurrency. While Google's agents focus on data pipeline automation and analytics, our platform, AI Crypto Market, leverages similar AI advancements to provide sophisticated AI-powered crypto trading bots and market analysis tools. The ability to process natural language for complex tasks, as demonstrated by Google's conversational analytics, is a cornerstone of our approach, enabling users to gain insights and execute trades with greater ease and efficiency. This signifies a shift towards more intuitive and autonomous systems that can handle intricate processes, a development we closely monitor and integrate into our own services to enhance user experience and market competitiveness.

More to Read:

• Google Launches AI Agents to Revolutionize Data Analysis (External Article - Hypothetical Link)
• The Rise of AI in Enterprise Data Management (External Article - Hypothetical Link)
• How AI is Transforming Financial Markets
• Understanding AI-Powered Trading Bots