WordPress Core AI stops being an experiment in 6.9
Six months in, WordPress Core AI has a stable shape: the Abilities API lands in 6.9, WP Client AI abstracts the LLM providers, and the MCP adapter turns a site into a server that agents can call.
Category: AI in WordPress
Applied statistics and machine learning in production WordPress
Notes on porting statistical models into WordPress: where research gets diluted instead of distilled, how real-time aggregates in user meta leak data through race conditions, the atomic SQL fix, and why a bigger LLM is the wrong answer to arithmetic.
Demand forecasting with graph neural networks in WooCommerce
Rolling-window forecasts treat every SKU as independent. This post models a WooCommerce catalog as a graph instead, with GraphSAGE over shared plants and attributes, the PHP that extracts SKU neighbors, and where heterogeneous transformers go further.
WP-Bench: measuring how well AI models know WordPress
WordPress now has WP-Bench, a benchmark that tests AI models on Core APIs, security patterns and block development. It runs the generated code in a real WordPress runtime instead of grading answers on paper.
AWS Bedrock instead of direct API calls for WordPress AI
Hardcoded API keys hold up until the first model deprecation. Here is how I use AWS Bedrock as the gateway instead: Boto3 calls, inference profiles, IAM permissions, and a triage assistant that runs on Lambda rather than inside the WordPress request cycle.
How Infini-attention keeps long context from eating memory
Longer context windows cost server memory, not just compute. Infini-attention replaces the growing KV cache with a fixed-size compressive memory matrix updated by a Delta Rule, which cut memory use by 114x in Google’s tests.
Context engineering beats writing longer prompts
Prompting stops scaling as soon as a task has real edge cases. Here is what the Stanford ACE research found about its generator, reflector and curator loop, where the gains show up, where they do not, and how to keep the same kind of playbook in WordPress.
GraphRAG for developers: high-recall retrieval that stays cheap
Vanilla vector search breaks down as soon as your data is relational. Notes on GraphRAG, enforcing a data contract on LLM output in PHP, and the production RAG lessons worth stealing from the Towards Data Science write-ups.
RAG pipeline features: which add-ons earn their cost
Query optimization and neighbor expansion can add 40 to 50% to latency and cost for marginal quality gains. What the numbers say about when each add-on is worth shipping in a RAG pipeline, and when a naive baseline is fine.
NeMo Agent Toolkit: real metrics for LLM agents
Most LLM agents ship with no visibility between the input and the answer. How the NeMo Agent Toolkit traces every tool call and scores trajectory rather than answer accuracy alone, using Arize Phoenix and W&B Weave.