RAG fetches the facts; the context layer decides what actually reaches the prompt. Four pieces I use in production: memory with exponential decay, hybrid retrieval with re-ranking, a token budget reserved in order, and extractive compression.
The Core Dev Environment Toolkit gives contributors a one-click wordpress-develop setup. The less good news: the core privacy component has nobody maintaining it, two PRs are waiting on review, and the 7.0 release schedule still has not landed.
Nearly 800 documentation issues triaged and over 200 closed, plus the WP-Parser problem that keeps DevHub out of sync with core. Also the DocBlock format the parser expects, and the three handbooks carrying the biggest backlogs.
What the Astro MDX integration is actually good for, the two patterns I use in production, and the two places it bites: formatters mangling JSX, and the RSS package refusing to render MDX.
Retrieval can work perfectly and still hand the model two documents that contradict each other. A conflict detection layer, the two heuristics that catch most enterprise cases, and cluster-aware recency for resolving them.
Asking a chatbot for a WooCommerce snippet is a lever pull, and the losing pulls are the hard ones to spot. Where LLM generated code breaks WordPress sites, what it does to coding standards, and why per-token pricing makes it worse.
Prompting stops scaling after a few sessions. Here is how agent skills put your recurring logic into a SKILL.md file instead, with a weekly visualization example and the directory layout I use.
The 512-token split is the default in every RAG tutorial, and it quietly ruins answers on real documents. What I use instead: sentence windows, hierarchical chunking, layout-aware table parsing, and RAGAS to check whether any of it worked.
Notes from WordCamp Asia 2026 in Mumbai, written for developers: the Interactivity API replacing fragile jQuery toggles, the Tag Processor in the HTML API, and what WordCamp India 2027 and the 7.0 roadmap mean for the code you ship.
A p-value is closer to a weirdness score than a probability that you are right. Here is how to read one, why the 0.05 threshold is arbitrary, and how to sanity-check sample size before you act on an A/B test.