Skip to content
Back to feed

November 19, 2026 · Google CloudFeature

BigQuery agent observability generally available, AI indexes in Preview

You can now enable agent observability with the Data Engineering Agent to monitor the agent's token consumption, request volume, and model latency in Cloud Monitoring and inspect execution traces and tool calls in Cloud Trace. This feature is generally available (GA).

You can now create AI indexes using the CREATE AI INDEX statement to perform natural language searches across table columns with the AI.SEARCH function without manually generating embeddings or managing models. To learn how to create, monitor, and delete AI indexes, see Use AI indexes. This feature is in Preview.

You can use the validation service in the BigQuery Migration Service to verify that tables migrated from your source data warehouse match your target tables in BigQuery across schemas, aggregate metrics, and row-level data. This feature is available in Preview.

BigQuery generative AI functions now support the gemini-4-neon model. This model is generally available.

Text from the Google Cloud release notes, licensed under CC BY 4.0. Source: Google Cloud release notes.

Free. Unsubscribe any time.

All BigQuery changes