Scaling WordPress data to 127 million points
A security report built on 127 million data points, and what it took: raw SQL instead of WP_Query, a resumable WP-CLI batch script, and segmentation that finally gave the numbers some contrast.
A security report built on 127 million data points, and what it took: raw SQL instead of WP_Query, a resumable WP-CLI batch script, and segmentation that finally gave the numbers some contrast.
Waiting on a full JSON payload from an LLM leaves users on a spinner for 15 seconds. Streaming with server-sent events, the ReadableStream code that consumes it, and when validation means you should not stream at all.
AI writes the query now and I check it. That includes the time an elegant LLM-generated join pushed a production database to 98% CPU, plus the utility I use to export sanitized WooCommerce data for analysis.
The Bits-over-Random Metric compares your retrieval against random chance, which is how you catch the context pollution a high Success@K hides. Notes on staged tool routing and where the collapse regime starts.
WordPress 7.0 slipped a few weeks so the collaboration layer can sit on a custom table instead of transients. What that means for polling load, cache invalidation, and any plugin still using classic metaboxes.
The six-month version of this career change is a sales pitch. Coming from a software background it took closer to two years, and the money goes to people who can ship a RAG system that does not leak data, not to people who can write prompts.
A client ran her entire business through WhatsApp until the account was blocked on a Tuesday. What owned digital assets mean in practice, and why Brazil’s first Automattic partner writes WordPress.com into its contracts.
A colleague shipped a custom assistant in a couple of hours by wiring Google Calendar, Microsoft To Do and Notion together. Execution stopped being the bottleneck, and here is a Gemini API scheduler you can start from inside WordPress.
A decade of explaining why WordPress sites don’t feel like apps, and what 2026 changes: blocks described to an AI instead of scaffolded by hand, the Interactivity API handling state without page reloads, and theme.json holding the design system.
Drift usually means a scramble for labels and a multi-hour retraining job. This is the other route: a trainable ReflexiveLayer over a frozen backbone, label-free drift triggers, and async weight updates that never block inference. It recovered 27.8 points of accuracy and cost recall.