How I get Claude Code to improve itself overnight
I stopped hand-holding Claude Code and gave it a nightly review instead: a self-reflection skill, a 2 AM cron job, and a rules file it edits itself. This is the setup I run on real WordPress work.
Tag: AI Assistants
Unified agentic memory with lifecycle hooks and Neo4j
Every AI harness keeps its own memory, so moving from Cursor to Claude Code means starting from zero context. Here is the shared layer I build instead: lifecycle hooks writing into Neo4j, plus the batch job that turns raw events into notes.
WordPress Workspace for Mac: what the beta actually does
WordPress Workspace for Mac is in beta. It puts a site-aware agent, voice dictation and screenshot uploads on the desktop instead of in another browser tab, and it previews the Guidelines feature headed for Core.
Why recursive language models beat ReAct for long context
Recursive language models get a pointer to the data instead of having the whole thing pasted into the prompt. Why that beats ReAct and CodeAct on long-context work, and what it means for auditing a large WordPress codebase.
Why your AI coding assistant drifts into the wrong language
Mixing technical English tokens like run.py can push an AI coding assistant to drift in the embedding space, sometimes replying in Korean when prompted in Chinese. How task registers shape the behavior, and how to keep your prompts grounded.
LLM evaluation for WordPress AI agents, beyond vibe checks
Vibe checks do not scale. Here is how to score a WordPress AI agent on five measurable dimensions, accuracy, reliability, latency, cost, and business impact, using golden datasets and the LLM-as-a-judge pattern to move from fragile demos to production.
Supervised fine-tuning for LLM personas: first-person wins
Instructions alone will not give a model an identity. Three ways to train one persona into a small model, and why first-person statements generalized better than chat demonstrations or factual documents.
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.
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.
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.