OFICIAL Google Cloud Blog

Integrating Looker and Gemini Enterprise

What happened
Based on Google Cloud Blog · Aug 11, 2026

Google Cloud integrates Looker’s governed semantic layer with Gemini Enterprise, enabling secure, natural-language queries across structured and unstructured data while preserving governance and security controls.

Integrating Looker and Gemini Enterprise
Google Cloud Blog — Google
Key points
·
For organizations deploying AI agents at scale, there’s often a critical divide between structured and unstructured data.
·
While large language models (LLMs) excel at parsing text documents, emails, and PDFs, they can struggle when presented with raw enterprise databases.
·
Meanwhile, standard natural-language-to-SQL (NL2SQL) models often guess how database schemas fit together, which can lead to unpredictable queries, inconsistent metrics, and AI hallucinations that erode user trust.
·
Gemini Enterprise adds the best of Google AI to every employee through an intuitive chat interface that acts as a single front door for AI in the workplace.

Google Cloud has integrated Looker’s governed semantic layer with Gemini Enterprise to address a persistent challenge in enterprise AI deployments: bridging the gap between unstructured text data and structured databases. Previously, AI agents struggled to accurately interpret enterprise data schemas, often producing inconsistent or incorrect results. The new integration allows Looker analysts to publish conversational agents directly into Gemini Enterprise via the Agent-to-Agent protocol, enabling users to query both structured and unstructured data in plain English without switching tools.

The integration ensures deterministic responses by routing user queries to Looker agents, which generate precise SQL based on version-controlled business logic. This eliminates the risk of AI hallucinations, as executives and employees receive consistent, governed metrics such as revenue or churn rate. Security and governance are maintained through a zero-risk pass-through architecture, where data is processed but not stored, and access controls are enforced via OAuth and Looker’s existing permission structures, including row-level and column-level restrictions.

Looker agents published in Gemini Enterprise now provide interactive data visualizations directly within the chat interface, including charts for trends like monthly sales or regional distribution. The integration also supports multi-agent orchestration, allowing Looker agents to securely share governed insights with other Google Cloud agents, such as the Deep Research Agent, to enable structured workflows. Users must provide one-time OAuth consent to bind their Gemini Enterprise session to their Looker credentials, ensuring identity-centric authentication and adherence to existing governance policies.

The integration aligns with Google Cloud’s vision of an agentic workplace, where AI-powered tools enhance productivity without compromising security. Business users can now access presentation-ready visualizations and complex insights directly in their workflows, reducing friction in data-driven decision-making. Organizations are advised to update or refresh Looker agents published prior to release 26.12 to leverage enhanced visualization capabilities and multi-agent collaboration features.

Original source → Deals on Clipraptor.com →