Proving User Experience ROI as a WordPress developer
Ten data points on the business value of user experience, from the 1:100 rule and page speed to Hick’s law and design maturity, written from a developer’s point of view.
Tag: AI
A pragmatic agentic AI workflow for WordPress
How to move past vibe coding to a spec-driven agentic AI workflow for production WordPress: persistent specifications, guardrails against silent failures, and automated tests, using tools like CodeSpeak and the Claude API.
Why your inference architecture matters more than the LLM
Why AI performance problems usually trace back to inference architecture, not the model: retrieval quality, context compression, compute routing, and speculative decoding, with fine-tuning often a distraction.
How I write robust code with Claude Code
A practical workflow for Claude Code: use Plan Mode before it touches your code, keep a CLAUDE.md skill file so fixes stick, and keep the context lean. The goal is production-ready WordPress, not AI-generated technical debt.
WooCommerce AI workflows that go beyond static reports
The WooCommerce integration for Claude adds 18 prebuilt AI workflows that behave like a senior analyst inside your store, from revenue triage to inventory risk reviews. They run as slash commands over live data, not static charts.
Hybrid search and re-ranking for more accurate RAG
Semantic search alone misses exact technical terms. Combining BM25 with dense vectors, then re-ranking the top results with a cross-encoder, is what made our production RAG accurate. RAGAS metrics show the difference.
WordPress AI 0.9.0: comment moderation, CLI, and model controls
WordPress AI 0.9.0 adds a comment moderation experiment, bulk alt-text generation over WP-CLI, and per-feature model controls. Here is what each one does and how to test it before the 1.0.0 release.
WordPress AI Client: building an image generation plugin
WordPress 7.0 ships the WordPress AI Client, a standardized PHP API for generative AI in plugins. This guide builds a provider-agnostic image generation tool for the Media Library using the prompt builder, support checks, and a REST endpoint.
Titanic dataset analysis: finding survival patterns with Python
The Titanic dataset is the classic first project in data science. Using Python, Pandas, and Seaborn, this walkthrough shows how gender, passenger class, and family size shaped who survived, and what that teaches developers about reading data.
The AI agent evaluation framework I use in production
Most AI agent projects fail because of weak evaluation, not weak models. These are the 12 metrics I run against every response, grouped into retrieval, generation, agent behavior, and production health, with PHP and Python examples.