A client’s WooCommerce store was slow because five plugins were each calling their own LLM API on every save. That is the problem the Ai_Client in WordPress 7.0 and the new Abilities layer are meant to solve.
A client wanted a sparkle button by Friday. What WordPress 6.9 actually shipped matters more: the Abilities API and the MCP adapter, which give AI agents a defined way to talk to a site.
A wrapper around a few REST endpoints wasn’t enough to keep an AI agent alive through a timeout. Version 0.3.0 of the WordPress MCP Adapter covers what I had to hand-roll: HttpTransport, WP_Error responses, prefixed hooks and one event stream.
A synchronous OpenAI call on image upload hung the admin for five seconds. The AI Experiments plugin v0.1.0 points at a different route: registered Abilities, the WP AI Client, and MCP.
Pointing an LLM at an undocumented WooCommerce extension produced hooks that never existed. Extracting the real hook list with PHP first, then prompting, is what separates a usable draft from a liability.
A client’s AI plugins each shipped their own settings screen and each asked for API keys they had already entered. The Core AI check-in from October 8th, 2025 covers both fixes: categories on the Abilities API, and one provider settings screen.
An off-the-shelf AI plugin left a client with a slow backend and alt text that had nothing to do with the images. The core AI discussions point somewhere better: content summaries, post titles and image descriptions behind one PHP AI Client.
A client wanted AI features on his WordPress site and every plugin used a different API. The new WordPress AI Client SDK gives plugins and themes one consistent, WP-native API for multiple providers.
A client spent six months stuck on API plumbing before any AI features shipped. The lesson: build WordPress AI on a proper AI Client SDK, with a standard way to register providers, before chasing features.
A client’s AI prototype broke because their site ran PHP 7.2 while our code used PHP 7.4. Here is how the WordPress Core AI team handles the same version gap, and how to build for it.