WP-Bench is the official WordPress AI benchmark. It runs model-written code inside a real WordPress runtime instead of asking a human whether the code looks right. How to run it, and what it still gets wrong.
Prompt engineering has stopped being the interesting part of LLM work. This is about context engineering, caching structured context in transients, and checking that the model’s reasoning holds up.
Zero-shot prompts make the model guess your coding standards. Feeding it two or three working examples from your own code gets output that matches your prefixes, namespaces and security patterns.
Anthropic’s January 2026 report puts the correlation between prompt sophistication and response sophistication at 0.925. Prompt engineering did not die, it moved from magic phrases to knowing your domain well enough to frame the problem.
WordPress.com switched its MCP server to OAuth 2.1 with PKCE, so AI agents no longer need long-lived tokens pasted into a config file. What the code verifier protects against, and what an authorized agent can do on your site.
Most WordPress sites keep their data as loose post meta rows. Healthcare got further by agreeing on shared ontologies before writing any code, and the same approach works in a WordPress codebase, from CPT design through JSON-LD output.
The WordPress Abilities API landed in 6.9 Beta 2, minus the JavaScript registration, which moved to a standalone NPM package in the Gutenberg repo. Notes on that split, the AI Experiments plugin, the WP AI Client 0.1.0 plan and the MCP Adapter refactor.
Low-tech logistics companies do not need AGI, they need to stop counting stock with a pen. Voice-driven inventory counts in n8n, damage reports generated from a photo, and a WordPress REST endpoint that takes the data in without breaking WooCommerce stock.
Perplexity and BLEU tell you nothing about whether an automated customer journey actually goes anywhere. The CDP framework scores continuity, deepening and progression against a taxonomy of journey stages instead.
LLM-as-judge asks a model that hallucinates to catch hallucinations. Displacement Consistency scores the vector between a question and its answer against grounded neighbors instead, with no source document and no second model call at inference time.