The Core AI team has new leadership, the Abilities API is in core, and the WP AI Client is headed for WordPress 7.0. Here’s why a shared infrastructure beats isolated AI plugins, and how to register your functions as Abilities.
A static RAG pipeline goes stale fast. Here’s why grounding LLMs with live search results works better for real-time facts, and how to wire a search API into your WordPress backend with PHP and transients.
A demo that works one time in ten is a liability, not a feature. Here is why LLMs hallucinate, why their confidence scores lie, and how I validate AI output in WordPress before it ever reaches a user.
WordPress 7.0 brings a central Connectors hub and a Connector Approval flow for AI credentials. Here’s what the May 2026 plan means in practice: custom tables for request logging, the AI Plugin 1.0.0 release, and what the approval flow does and doesn’t protect.
Chunk-and-embed RAG loses the hierarchy that gives a 200-page contract its meaning. How the Proxy-Pointer framework indexes structural breadcrumbs instead of raw text, and how the two-stage retrieval works in Python.
WooCommerce 10.9 brings variation galleries into core, retiring the paid Additional Variation Images extension. Notes on the new meta key, the Action Scheduler migration, and the theme overrides that tend to break it.
MCP servers are becoming the plugin bloat of the AI era. Why a sandboxed CLI gives an agent more capability per token than a menu of narrow tools, and how to keep shell access from being a liability.
WordPress Workspace for Mac is in beta. It puts a site-aware agent, voice dictation and screenshot uploads on the desktop instead of in another browser tab, and it previews the Guidelines feature headed for Core.
Rust-based data libraries keep shipping, but Pandas still runs most of my production pipelines. Vectorized string operations, ast.literal_eval instead of eval, and the DataFrame constructor trick that beats df.apply(pd.Series) on big datasets.
I refactored a workflow I had already optimized in Pandas over to Polars, and the runtime went from 0.31 to 0.20 seconds. The harder part was the mental shift from eager to lazy evaluation.