Blog
Long-form notes on BigQuery, BigQuery ML, GA4, MCP servers, Cloud Run, and Google Ads automation. Subscribe via RSS.
-
Forecasting GA4 revenue in pure SQL with BigQuery ML — and the model-quality checks you can't skip
A pre-release SQL-only pipeline produces a 30-day GA4 revenue forecast with ad-spend regressors and seasonal sub-forecasts — no Python, no Vertex, no Cloud Functions. The architecture matters, but the bigger story is ...
-
When +35% is really −60%: a GA4 anomaly detector where the LLM only writes the report
I've been using MCP servers for about a year, like the rest of the tech industry. Plenty of impressive moments. Also plenty of cases where the LLM confidently does a calculation wrong on data the SQL clearly returned ...
-
Self-hosted vs Google's official BigQuery MCP server: a security and cost comparison
Google's official BigQuery MCP server is the right default for trusted internal analysts. For agents handling untrusted input, a self-hosted server with hard table allowlists and per-query scan ceilings is the safer c...
-
How to build a GA4 purchase propensity model with BigQuery ML (without Vertex AI)
GA4's built-in predictive audiences need ≥1,000 returning purchasers in the last 28 days. If you don't have that traffic, you can roll your own with BigQuery ML — no Vertex AI, no AutoML, no third-party SaaS. Here's t...
-
Stopping the $2,000 AI query: how to cap BigQuery scan cost from an MCP server
Every AI agent connected to BigQuery is one bad query away from a four-figure invoice. There are three layers of defense; only one of them is bulletproof. Here's where to put each.