Google BigQuery
Query your warehouse from inside a workflow — run SQL, get rows back as JSON, hand them to an agent.
The BigQuery Reader runs your query against a dataset and returns an array of JSON objects, one per row — so the metrics you already model in the warehouse can drive analysis, narration, and downstream actions without a manual export.
What it does.
Run SQL
Execute a query against any dataset your service account can read.
Rows as JSON
Results come back as an array of JSON objects — one object per row, ready for downstream nodes.
Warehouse-scale data
Lean on the metrics and joins you already model in BigQuery instead of re-deriving them.
Analyze and narrate
Feed rows to a Data Analyzer and LLM to turn warehouse data into plain-English reporting.
Warehouse query to narrated report.
Run the query, extract the fields you care about, reason over them, and write a narrated summary to a sheet.
Connect in minutes.
Authorize
Connect with a service account — scoped to exactly the datasets you allow.
Configure
Set the query and dataset your workflows can read.
Automate
Use it in any agentic workflow, triggered or scheduled.
Show us the workflow.
We'll show you the 10x.
Bring the marketing workflow that eats your week. We'll build it live, with your data and your models, in 30 minutes.