Live demo
Marketing Warehouse. Five platforms in one place a model can read.
A BigQuery warehouse that pulls five ad and CRM platforms into one place every morning and joins ad spend all the way through to booked patients, with a self-documenting catalog that lets an LLM answer marketing questions in plain English, and weekly graded evals to prove it keeps doing so.
Walk through it, six steps
Five connectors, one morning sync
Cloud Scheduler fires the connector jobs at 6 AM: search ads, social ads, call tracking, and the CRM, with one platform arriving via BigQuery Data Transfer. All connectors share retry, load, and secret code, packaged as a single container image run as serverless jobs.
| Source | Rows | Status | Finished |
|---|---|---|---|
| Search ads (Platform A) | 1,204 | ok | 06:04 |
| Social ads (Platform B) | 912 | ok | 06:06 |
| Call tracking | 388 | ok | 06:07 |
| CRM boards | 2,730 | ok | 06:11 |
| Search ads (transfer) | · | managed transfer | 06:15 |
The problem.
Marketing questions like which channel actually produces patients, not clicks, required manually exporting from five platforms and stitching spreadsheets. And once an LLM was allowed to answer questions over the data, a harder problem appeared: how do you know its answers stay right as the schema evolves?
- 5 search ads, social ads, call tracking, CRM, and more
- 98.5% patients joined to leads; 99.5% agreement vs exports
- 22 golden Qs weekly graded run, fails under 80%
- $5 to 15/mo serverless jobs + BigQuery
How it fits together.
Ingest
- 5 connectors, one Docker image, Cloud Run jobs
- Shared retry, load and secret modules
- 6 AM schedule + managed transfer
Warehouse
- BigQuery: raw → staging → marts (+ evals dataset)
- Inline descriptions on every view and column
- data_guide catalog written for LLM readers
Consume
- LLM access via MCP Toolbox
- Looker Studio dashboards
- Plain-English answers with mart citations
Trust
- 6:45 freshness check + z-score drift sentinel
- 22 golden questions graded weekly, 80% gate
- Glass monitoring app with per-node health
Where it landed.
Marketing spend, calls, leads, and booked patients live in one queryable place with 98.5% linkage, validated at 99.5% agreement against the manual exports it replaced, for five to fifteen dollars a month. The part worth stealing: treating the LLM's access as a product surface with its own weekly, graded, gated eval suite instead of assuming yesterday's good answers persist. All dollar figures shown are synthetic.