Google Cloud’s 6 New AI Agents And Gemini Innovations: Key Features

From new AI agents for data engineering and data science to Google’s new Gemini Data Agents APIs, here are the six new agentic AI technologies Google Cloud launched this week that partners need to know about.

Google Cloud has unleashed a slew of new AI agents and agentic AI innovation for many of its flagship products, including BigQuery, Spanner, Google Data Cloud and Gemini.

The $54 billion cloud leader launched new AI agents for data engineering and data science, as well as Gemini Data Agents APIs and a new migration agent for Spanner.

“The agentic era begins with a new workforce of specialized AI agents, providing an AI-native interface to turn intent into action,” said Google Cloud’s Yasmeen Ahmad, managing director of Data Cloud, in a blog post.

Mountain View, Calif.-based Google is placing its largest investments in 2025 around new and enhanced agentic AI products and Google Gemini.

CRN breaks down the six new agentic AI technologies Google Cloud launched this week that every channel partner and customer needs to know about.

Google Cloud’s New Code Interpreter Agent

In 2024, Google Cloud launched Conversational Analytics Agent to empower business and analyst users to get answers from their data using natural language.

Google Cloud is “taking that agent to the next level with Code Interpreter,” said Ahmad, powered by Gemini’s advanced reasoning capabilities and developed alongside Google DeepMind.

Code Interpreter translates complex natural language questions into executable Python code.

The chatbot-style new tool supports conversational Q&A dialogue using the context of datasets.

“This enhancement supports the many critical business questions that go beyond what simple SQL can answer, for example, ‘Perform a customer segmentation analysis to group customers into distinct cohorts,’ Ahmad said.

It delivers a complete analytical flow by generating code, providing clear natural language explanations and creating interactive visualizations—all within the Google Data Cloud.

Click through to read about Google Cloud’s five other new agentic AI technologies.

Data Science Agent For BigQuery And Vertex AI

Targeting data scientists, Google Cloud is looking to reimagine its Colab Enterprise Notebook experience inside BigQuery and Vertex AI with its new Data Science Agent powered by Gemini.

The new Data Science Agent triggers entire autonomous analytical workflows, including exploratory data analysis, data cleaning, featurization and machine learning predictions.

The new agent creates a plan, executes the code, reasons about the results and presents its findings, all while allowing users to provide feedback and collaborate in sync.

Gemini Data Agents APIs: Conversational Analytics API

Google Cloud is pushing customers to not only use existing agents but also connect them to their own intelligent systems to create a border network.

To better enable this, Google Cloud is launching Gemini Data Agents APIs, with the first being the new Conversational Analytics API.

The new Conversational Analytics API provides the building blocks to integrate Google’s Looker natural language processing and Code Interpreter capabilities directly into a customer’s own applications, products and workflows.

The goal of Google Cloud’s new API is to allow users to create unique, engaging and accessible data experiences to meet their specific business needs.

Data Engineering Agent In BigQuery

For data engineers, Google is launching its new Data Engineering Agent in BigQuery to simplify and automate complex data pipelines.

Users can use natural language prompts to streamline the entire workflow, from data ingestion from sources like Google Cloud Storage to performing transformations and maintaining data quality.

“Simply describe what you need: ‘Create a pipeline to load a CSV file, cleanse these columns, and join it with another table,’ and the agent generates and orchestrates the entire workflow,” said Ahmad.

Gemini CLI GitHub Actions Agent

Google unveiled its new Gemini CLI Actions agent, which is an autonomous agent that can handle issue triage, pull request reviews independently and collaborate on demand to write tests and implement code.

Google launched Gemini CLI in June as a free, open-source AI agent to bring Gemini into developer terminals.

The new Gemini CLI Actions agent enhances multiuser support and GitHub integration that can be run locally.

GitHub Actions can also serve as a collaborative coding agent that can work as a user’s AI teammate.

Migration Agent For Spanner

The company launched a new data modernization agent for its global database service, Spanner. Google Cloud’s new Spanner columnar engine agent brings new analytical capabilities directly to Spanner databases.

Spanner’s new columnar engine lets users analyze vast amounts of operational data in real time, all while maintaining Spanner’s global consistency, high availability and strong transactional guarantees.

It also can work in tandem with the Data Engineering Agent as it’s intended for legacy systems that still need modernization.

“As part of our unified Data Cloud, this innovation directly benefits our analytical engine, BigQuery via Data Boost, which leverages the Spanner columnar engine to close the gap between transactional and analytical workloads and make it faster for BigQuery to analyze live operational data,” said Ahmad.