Autonomous agents fail in ways that are expensive to clean up. This is how LangGraph interrupts and checkpointers let a person approve a step mid-run, plus the idempotency mistake that made my content agent publish something I never signed off on.
WordPress 7.0 ships the PHP AI Client, and the community has already built connectors for Grok, Mistral, Ollama and OpenRouter. What each one covers, how provider registration works, and the switching case worth testing first.
Core now ships a provider-agnostic PHP API for AI work. The SDK and wrapper split, the fluent builder for text and image generation, feature detection before you draw any UI, and why bundling php-ai-client yourself now fatals.
Claude Code forgets everything when the session ends. The setup I use: a post-mortem command that writes to CLAUDE.md, skill files for the quirks of the stack, and a daily pass over the logs.
Agentic loops fail quietly: the same query retried with new wording, retries with no circuit breaker, a context window full of raw JSON. Three patterns, how to measure them, and a PHP budget gatekeeper.
WordPress Playground MCP connects Claude Code or Gemini CLI to a Playground instance running in your browser. The agent reads files, runs PHP and queries the database itself, which cuts out most of the copy-paste during plugin testing and debugging.
OpenAI prompt caching takes 90% off repeated tokens, but only for prefixes over 1,024 tokens and only when the static part of your prompt comes first. Here is a Python example plus the ordering mistake that kills cache hits.
Offline evaluation for LLM agents: routing accuracy, LLM-as-judge scoring, and RAG faithfulness, plus the quality gate I use to block a deploy when the scores come in under threshold.
WordPress.org now runs an MCP server for the Plugin Directory. It lets AI editors like Cursor and Claude validate readme.txt, check submission status, and submit plugins without leaving the editor.
The @wp-playground/mcp package lets an AI client drive a Playground instance over MCP: run PHP, write files, query the database and check the front end, all inside the browser.