BigQuery AI Functions

BigQuery AI Functions Can Reason Over Your Rows — If the Rows Carry Content

by

BigQuery AI Functions — AI.GENERATE, AI.GENERATE_TABLE, AI.CLASSIFY — went GA in January 2026. Claude Desktop Live Artifacts shipped in April. Together they create a two-tier natural-language interface to WooCommerce data: the operator asks Claude a question, and Claude writes SQL that calls AI Functions to reason over individual rows. But AI.GENERATE classifying refund reasons needs a refund_reason column. AI.CLASSIFY categorising cart intent needs cart-level context fields. AI.FORECAST predicting revenue needs historical data at daily or hourly granularity. None of these exist in a default WooCommerce order-export schema.

Ask Your WooCommerce BigQuery Data Anything — If Three Things Are True

by

Data Studio Pro Conversational Analytics shipped with the April 11, 2026 rename, priced at $9 per user per project. A WooCommerce store owner can now type “which products lost money in April” into a BigQuery box and get a real answer back — but only if three schema decisions are already correct upstream: the GA4 events carry a stable user_id, the WooCommerce orders join on a deduplicated transaction_id, and product COGS lives somewhere the warehouse can actually reach. Get any one of them wrong and the AI confidently returns the wrong number. The AI is the last mile. The pipeline decides the answer.

Gemini Now Runs Inside Your BigQuery SQL. Three WooCommerce Recipes.

by

On January 27, 2026, Google Cloud announced that AI.GENERATE and AI.GENERATE_TABLE are generally available in BigQuery, alongside AI.EMBED, AI.SIMILARITY, AI.IF, and AI.SCORE. The Gemini call happens inside the SQL query — no Vertex AI engineering, no data egress, no separate per-token budget. For a WooCommerce store with two years of orders, products, and reviews already in BigQuery, three immediate recipes apply: AI.GENERATE on a GROUP BY to extract review themes per product, AI.IF in a WHERE clause to triage support tickets, and AI.EMBED + AI.SIMILARITY to power semantic product search and ‘customers who bought similar products’ segmentation.