Google Cloud and Anthropic Launch Claude Apps Gateway for Secure Enterprise AI Deployment
14.07.2026 
Conversational Analytics in BigQuery Brings Trusted Agentic Reasoning to Everyone
Google Cloud just moved Conversational Analytics in BigQuery to general availability. Now business and technical teams can query data, run multi-step analyses, and build reports in natural language, right inside BigQuery. It’s built on Google’s Gemini models, and it works right out of the box, no setup needed.
What’s Actually New
- Agents Grounded in Your Own Data. Data professionals can build specialized agents tied to specific projects, datasets, tables, views, graphs, and user-defined functions. From there, they can publish those agents to Gemini Enterprise, Looker Studio, or a custom app through the Conversational Analytics API.
- Reach Beyond BigQuery. Queries now stretch across Lakehouse-managed Apache Iceberg tables and cross-cloud sources like Databricks Unity, AWS Glue, SAP, and Salesforce. So a single conversation can pull from data sitting in completely different clouds.
- Answers You Can Actually Check. Every response shows the agent’s reasoning steps and the exact SQL behind it. It cites the tables and glossary terms it pulled from, and if a prompt is vague, it asks a clarifying question instead of taking a shot in the dark.
- Governance That’s Already Built In. The feature inherits BigQuery’s existing access controls and logs every query for audit purposes. On top of that, it supports Access Transparency, Customer-Managed Encryption Keys, Private IP, VPC Service Controls, and data residency guarantees across EU and US multi-region endpoints.
- From Answers to Investigations. Deep-dive mode plans out a full multi-step investigation when you ask why a metric moved. Scheduled agentic workflows go further still, running recurring checks like a Monday-morning business report or daily anomaly detection. Nobody has to kick them off by hand.
“Most of our clients already have the data. What they don’t have is enough analysts to answer every question fast enough. Now a sales or ops lead can ask BigQuery directly why a number moved and get a straight, sourced answer instead of waiting in a queue. And the governance carries over from BigQuery too, so it’s safe to roll out past a pilot.” 
Co-Founder and Google Cloud & Data Analytics Expert at Cloudfresh
How Cloudfresh Helps
As a Google Cloud Premier Partner, Cloudfresh helps teams set up BigQuery’s data foundation and build the specialized agents this feature runs on. We connect them to Gemini Enterprise or your existing BI workflows without data ever leaving BigQuery’s governance boundaries.
