BigQuery integration for Rig
The easiest way to query BigQuery in Claude and other AI tools
BigQuery is Google Cloud's serverless data warehouse for running fast SQL analytics across large datasets.
What Rig sees in BigQuery
Once connected, Rig models these objects so questions resolve to the right tables and joins:
- Projects and datasets
- Tables and views
- Partitioned and clustered tables
- dbt models
- INFORMATION_SCHEMA usage
- Scheduled query results
How BigQuery connects to Rig
Rig connects to BigQuery with a read-only service account, reads your datasets through INFORMATION_SCHEMA, and builds a context layer over your tables, joins and metrics. Queries run as standard BigQuery SQL in your own project.
Turn plain-English questions into BigQuery SQL
Rig generates BigQuery standard SQL from a natural-language question using your real datasets and metric definitions. It handles partition filters and nested fields correctly, so a marketer can ask for cost per acquisition by channel without knowing how the events table is partitioned.
- What was customer acquisition cost by channel last month?
- Show daily active users from the BigQuery events dataset
- Compare conversion rate across landing pages this quarter
Keep BigQuery scan costs predictable
Rig validates every query in a sandbox and applies partition and limit guardrails before the query runs, so a casual question never turns into a full-table scan of a multi-terabyte events table. You can see which questions cost the most bytes processed and tune from there.
- Which queries processed the most bytes this week?
- Show estimated query cost by user for the last 30 days
- Add a date filter and re-run that query on BigQuery
Analyse GA4 and product events modelled in BigQuery
Many teams land Google Analytics 4 and product events in BigQuery. Rig understands the event and parameter structure, so you can ask funnel and retention questions in plain English and get answers that unnest the event arrays correctly.
- Build a signup to activation funnel from the GA4 export
- What is week-four retention by acquisition source?
- Which events precede a purchase most often?
Query BigQuery from inside your AI assistant
Rig exposes BigQuery to Claude, Cursor, ChatGPT and other MCP clients with your governed schema attached. The assistant answers from modelled metrics rather than raw tables, so numbers stay consistent across the team.
- Pull revenue by product line from BigQuery
- Find the join between orders and sessions
- Explain how lifetime value is calculated here
Ask your BigQuery data in Claude, ChatGPT or Cursor
Rig serves your BigQuery data to AI assistants over MCP. Once BigQuery is synced into your warehouse, you can ask questions in plain English from the tool you already use, and every answer is backed by validated, governed SQL.
Frequently asked questions
- What access does Rig need for BigQuery?
- A read-only service account with permission to run queries and read INFORMATION_SCHEMA on the datasets you want exposed. Queries run in your own Google Cloud project.
- Will Rig run up large BigQuery bills?
- No. Rig sandbox-validates queries and applies partition and limit guardrails before running them, and surfaces bytes processed per query so you can monitor cost.
- Can I ask BigQuery questions in ChatGPT or Claude?
- Yes. Rig serves BigQuery to AI assistants over MCP, so you can ask in plain English from Claude, ChatGPT, Cursor and others.
- Does Rig work with GA4 data in BigQuery?
- Yes. Rig understands the GA4 event and parameter structure and can build funnel, retention and attribution analyses from the export tables.
Related integrations
Connect BigQuery data to AI tools like Claude
Rig builds a governed context layer over your data so every team, and every AI tool, asks questions and gets answers they can trust.