Google Announces New AI Agents for Data Analysis & Science Google on Tuesday unveiled six new AI agents at its Cloud Next Tokyo conference designed to automate time-consuming data tasks that typically consume 80% of enterprise data teams' work . The announcement represents a significant push into agentic AI, with tools that can build entire data pipelines from simple prompts and perform end-to-end machine learning workflows without manual coding. At the forefront is the Data Engineering Agent in BigQuery, which allows users to describe complex data workflows in natural language and have the system automatically generate SQL code, build pipelines, and create unit tests . Data engineers can request tasks like "Create a pipeline to load a CSV file, cleanse these columns, and join it with another table," and the agent handles the entire process autonomously . Enterprise Focus on Reducing Data Toil The new suite addresses what Google calls the "toil problem" in data teams, the manual, repetitive tasks that prevent data professionals from focusing on strategic work . According to TechTarget, enterprise data engineers and scientists spend most of their time searching for data in repositories instead of building applications and infrastructure . The Data Science Agent, integrated into BigQuery Notebooks and powered by Gemini, can autonomously conduct exploratory data analysis, clean data, perform feature engineering, and build machine learning models . The agent creates multi-step plans, executes code, reasons about results, and presents findings while collaborating with users through natural language feedback . For business users, Google enhanced its Conversational Analytics Agent with a new Code Interpreter that translates complex natural language questions into executable Python code . This allows non-technical users to perform advanced analytics including statistical computations and predictive modeling without coding knowledge . Developer and Migration Tools The announcement also includes Gemini CLI GitHub Actions, an open-source AI agent that automates code repository management, including issue triage, pull request reviews, and direct task delegation through @mentions . Additionally, the Migration Agent for Spanner helps organizations modernize legacy database systems by simplifying migrations from platforms like MySQL . Google launched supporting infrastructure including the Conversational Analytics API for developers to embed these capabilities into custom applications, and the Agent Development Kit for creating specialized agents . According to Chirag Dekate, a Gartner analyst quoted by TechTarget, enterprises are on "a long-term journey to reimagine, essentially deconstruct, their enterprises and reconstruct them in an AI and agent native context" . The new tools are available in preview, with most features included at no additional charge within existing BigQuery and Looker pricing .
