A multi-agent AI workflow is a few model calls in a row, each with its own role prompt. The pattern itself is simple. What decides whether it survives on a real WordPress site is the queue behind it, and what each agent actually sees.
A llama.cpp project that prefills a shared document once and fans the KV cache out to many agents is really a lesson in prompt order. Here is how the same shape shows up when your agents are just API calls from PHP, and how to check it.
Modern AI runs on CPUs, GPUs, TPUs and NPUs, and a WordPress site only ever meets two of them. A look at where inference actually runs, how to call a model without wrecking your server, and when the visitor’s own hardware can do the work.
LLM recommendations on a store get affordable when a free query builds the shortlist and the model only reranks thirty candidates, with the result cached. This is the WooCommerce version of a restaurant recommender pattern, including the PHP and the caching most posts skip.
A fine-tuned Mistral model now classifies 15 emotions in short text, and the weights are public under Apache 2.0. I look at what it took to train, how I’d wire it into WooCommerce review triage, and the parts I would not trust on a real store.
WordCamp Europe 2026 wrapped in Kraków with 2,458 attendees, CERN’s flagship site now on WordPress, and AI plumbing landing in core with 7.0. What I’d copy from CERN’s platform, what the AI client means for client sites, and the question I left with.
The case for letting a framework generate and score your prompts, and the part nobody mentions for WordPress: the optimization runs offline, and the prompt ships into your plugin as a plain PHP constant. Notes on when that’s worth the setup and when it isn’t.
An AI assistant that can’t see your project turns every review into a copy-paste loop. What I’d build myself, what I’d leave to the official SDK, and where the sandbox boundary belongs when the root contains wp-config.php.
Most teams using AI on a WordPress site pay a hidden tax in copy, paste and rewritten prompts, and another SaaS rarely removes it. The fix, for me, is moving the prompt into your own code with wp_remote_post, WP-CLI, caching and a small model, so the workflow runs where the data already lives.
The Core AI Team runs a table at WordCamp Europe’s Contributor Day on June 4. Before you go, two decisions matter: which environment you bring and where your model lives. This is the setup order I’d use, starting with one command the night before.