Google Cloud Conversational Analytics expands across data ecosystem

Conversational Analytics in Google Cloud is now generally available for BigQuery and Looker, extending its reach to enterprise-wide deployments. Preview availability is now offered for Conversational Analytics in AlloyDB, Cloud SQL, and Spanner, enabling analysis across more data sources and surfaces.

Conversational Analytics can now query data stored in Lakehouse Managed Service tables, Apache Iceberg REST catalogs, and federated AWS S3 Unity Catalogs, alongside Google Cloud data. Agents can natively query data whether it resides solely in Google Cloud or across multiple cloud providers.

Agentic Workflows, currently in preview, enable proactive intelligence by automating multidimensional deep dives and anomaly detection. Users can schedule automated reporting routines and receive agent-driven summaries or alerts when key metrics deviate from baselines.

New controls for Conversational Analytics include Customer Managed Encryption Keys (CMEK), Private IP, and Virtual Private Cloud (VPC). The service guarantees Data Residency (DRZ) and HIPAA compliance, with role-based access controls enforced down to row- and column-level permissions for data access.

Conversational Analytics agents are co-designed with data platforms and leverage Knowledge Catalog for data discovery and context enrichment. They utilize BigQuery and Spanner Graphs for multi-hop relationships and Looker's semantic layer for deterministic metric definitions, minimizing AI hallucinations.

Conversational Analytics is accessible through APIs with native SDKs for multiple languages, and can be embedded into custom applications, Slack bots, or multi-agent systems using the Agent Development Kit (ADK) and Model Context Protocol (MCP).