Shadow AI governance and the desire paths at work
Shadow AI shows up because the official workflow is slower than the shortcut. Here is how I read that usage as a signal, and what a governed option looks like inside a WordPress stack.
Category: AI
AI coding assistants and the WordPress code they get wrong
AI coding assistants write PHP that reads fine and falls over in production. A WooCommerce audit, the naive fetch they keep producing, and the refactor I run it through.
Gemini Embeddings 2: one vector space for text, images and video
Gemini Embeddings 2 is in public preview: one vector space for text, images, audio and video. The preview limits, calling it from WordPress with the HTTP API, and why cosine similarity on its own still is not enough.
Reviewing Claude Code output is the new bottleneck
Generating a thousand lines of PHP takes seconds, so review is where the time goes. The review skill I run before opening a PR, why I ask for HTML reports, and the WooCommerce checkout bug that nearly shipped.
Prompt caching: stop paying twice for the same tokens
Prompt caching takes up to 90% off input token cost and around 80% off latency, but only when the prompt prefix never moves. Here is how the pre-fill stage works, where the 1,024-token threshold sits, and how to order a prompt so it hits the cache.
Bayesian thinking: your intuition was not the problem
A single noisy A/B test made a client drop a feature that was working. Bayesian thinking is the correction: write down what you believed before the data arrived, then update it. Includes the mammogram problem and a five-step checklist.
Building a Claude Code Skill that actually triggers
I moved a 500-line prompt into a Claude Code Skill and stopped re-pasting it every morning. This covers the three loading stages, how to write a description Claude will act on, and the three implementation patterns.
Credit scoring EDA: what to check before you train
Jumping straight to XGBoost hides the problems in the data. Notes from a 32,581-row credit dataset: a heavy class imbalance, quartile cuts on age and income, and what a missing loan date does to model stability.
The 2026 data mandate and your governance architecture
Grace periods for the EU AI Act and the Cyber Resilience Act run out in 2026, which moves data governance out of the legal team and into the server room. What that means for provenance, SBOMs and brittle pipelines.
Agentic RAG: why vector search misses exact IDs
Vector search handles synonyms well and loses exact identifiers. Notes on pairing BM25 with vector retrieval, merging both with rank fusion, and letting the agent retry when the results come back empty.