Vector search optimization: flatten your JSON before embedding
Raw JSON in an embedding model spends your token budget on braces and quotes. Flattening product data into plain sentences gives the model the kind of text it was trained to read.
Category: AI in WordPress
ML in production: what shipping a model actually takes
A notebook demo is not production. This is what sits between the two: an API contract, a container, infrastructure that suits the workload, and monitoring that catches drift before the predictions quietly go bad.
WordPress Studio CLI 1.7.0 brings real local dev automation
WordPress Studio 1.7.0 ships a CLI that can create, start, stop and delete local sites, and run WP-CLI inside the Studio environment. What the studio site and studio wp commands do, plus how to let a coding agent use them without losing a site.
How convolutional neural networks learn musical similarity
Metadata filters only take music discovery so far. How CNNs read audio as Mel-spectrograms, how contrastive learning with InfoNCE loss shapes the embeddings, and why the inference belongs outside WordPress.
WordPress AI core: what has to land before 7.0 Beta 1
Notes from the AI contributor meeting: AI Experiments 0.2.0 is out, the Core Post Management abilities PR is under review, PHP AI Client v0.4.0 shipped, and the MCP Adapter stays a canonical plugin. February 19 is the Beta 1 cutoff.
WordPress AI Client: what changed on the road to 7.0
The WordPress AI Client is being lined up for a core inclusion proposal. January 2026 contributor notes cover streaming leaving the PHP client, a kill switch filter for locked-down sites, and MCP for tool discovery.
WordPress AI Experiments 0.2.0: what actually changed
WordPress AI Experiments 0.2.0 adds AI-generated excerpts in the block editor and an Abilities Explorer screen under Tools. Here is what the release changes for plugin developers, plus the code for registering your own ability.
You probably don’t need a RAG vector database yet
For a docs bot or an internal MVP, a dedicated vector database is more infrastructure than the problem needs. Vector search is matrix multiplication, and NumPy handles it in milliseconds. Includes a small store class, the SciKit-Learn upgrade path, and the four signs you have outgrown both.
WP-Bench puts AI models through a real WordPress runtime
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.
LLM optimization past the perfect prompt
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.