Courses

The capstone course. Design extensible abilities, run multiple MCP servers at scale, add real observability and performance tuning, migrate legacy plugins, plan an enterprise AI strategy, and ship a publishable, commercial-grade MCP plugin.

Extends the mostly read-oriented AI-Powered WooCommerce course into genuinely destructive, financial-risk action-taking, order-status changes, refunds, payment requests, cart recovery, and recommendations, with human confirmation required by default everywhere money or inventory is touched.

Build custom abilities that actually understand Elementor, Divi, WPBakery, and Beaver Builder's real stored layouts, then wrap every edit in a duplicate-and-approve workflow and a production guardrail so an AI agent never touches a live page directly.

Set up a disposable local environment, connect Claude Code, Cursor, and Claude Cowork correctly, guardrail what they're allowed to write, and build a repeatable, reviewed workflow for full-site generation instead of trusting AI-generated PHP by default.

A defensible AI content workflow built around Google's actual stated position on AI-generated content, the real E-E-A-T framework, information gain, and getting cited by AI Overviews and AI chat assistants, not just traditional search.

Ten shippable, portfolio-ready AI tools for WordPress editorial workflows, SEO optimization, bulk editing, moderation, translation, and reporting, each combining the Abilities API with the PHP AI Client SDK.

A practical, developer-facing look at what shipping AI features on WordPress actually requires beyond the code, data privacy and consent, the EU AI Act's risk tiers, content disclosure, PII handling, bias testing, and audit trails built for compliance review, not just debugging.

Bring AI directly into the content-creation experience. Build a real AI-powered block, a custom Block Bindings source, an AI sidebar panel, a toolbar action, and an inserter variation, all running as JavaScript in wp-admin rather than as backend automation.

A working AI layer for LearnDash courses and MemberPress membership sites, a tutor grounded in real course content, adaptive learning paths, auto-graded free-text answers, membership-gated AI features, deep LearnDash content-structure integration, and human-reviewed community moderation.

WooCommerce already ships real, developer-preview MCP and Abilities API support as of version 10.9. This course builds on that official foundation, custom abilities for catalog, orders, sales reporting, and customer support, to ship real store assistants and automation.

The business capstone for freelancers, agencies, and consultants delivering WordPress AI and MCP work to clients, productized offerings, pricing models, white-labeling, contracts, staging-first delivery, and scaling a service business without scaling headcount one to one.

The hands-on build. Install the official MCP Adapter, register real abilities with proper schemas and permission checks, serve them over HTTP and STDIO, and ship a secure, production-ready MCP server.

Pick an MCP server, Royal MCP, miniOrange Secure MCP Server, or WPVibe, and connect Claude or Cursor to your WordPress site with real, verified setup steps.

Wire your working MCP server up to real clients, Claude Desktop, Cursor, and ChatGPT, then build a genuinely useful conversational admin assistant with safe publishing defaults, confirmation gates, and multi-step workflows.

A troubleshooting companion for developers who've already built abilities and an MCP server and hit something that didn't work. A repeatable debugging workflow, the real GitHub issues behind wp_register_ability() returning NULL, the actual guidance on empty input_schema validation failures, and how to read the adapter's error handler and MCP Inspector to find exactly where a call is failing.

The advanced end of the AI-on-WordPress track, fine-tuning open-weight models and training custom embedding spaces on your own content, then wiring the result back into WordPress through the real provider-extension pattern and evaluating it against a genuine baseline.

Build a real, production chat widget for anonymous site visitors, a secure REST endpoint that proxies the PHP AI Client SDK, transient-backed sessions, honest streaming UX, abuse guardrails, human escalation, and a shortcode any site owner can drop into a page.

Everything you built in the Abilities API and MCP Adapter courses already works headless, with no modification. This course covers the part that's actually new when WordPress becomes an AI backend for a non-WordPress front end, the client-side calling patterns for Next.js, mobile, and edge runtimes, and the authentication, CORS, and rate-limiting decisions specific to calling WordPress from outside WordPress.

A migration course for developers whose code targets the archived, pre-core wordpress/abilities-api package. Drop the old dependency, adopt core's built-in Abilities API, and get a clear, accurate picture of what actually shipped in WordPress core versus what is still a separate plugin.

The advanced extension of Course 3. Design specialized agent roles, hand context between them, queue long-running jobs with Action Scheduler, and chain abilities into coordinated workflows, all on real WordPress primitives, no invented orchestration framework.

A production multilingual AI workflow for WordPress, WPML and Polylang integration, terminology-consistent translation prompts, locale-aware hreflang and metadata, WooCommerce catalog translation at scale, and a human review gate before anything goes live in a second language.

A hands-on course for images, audio, and video with the WordPress AI stack, what's genuinely shipped today (real image generation into the media library), and honest, working paths around what isn't (vision and audio transcription aren't first-class SDK features yet).

A full production operations course for WordPress AI features under real load. Cache responses correctly, invalidate them safely, track and control token cost, move slow calls into background jobs, rate-limit at scale, and monitor cost and latency together.

A deep, practical course on calling Claude, GPT, and Gemini from your own WordPress plugin code with the PHP AI Client SDK, covering setup, text and embeddings, error handling, provider fallback, and two complete real-world features.

A practical, honest look at running your own LLM behind WordPress with Ollama, vLLM, or llama.cpp, including a real custom provider for the PHP AI Client SDK, regex-based PII redaction, and a decision framework for when self-hosting is actually worth it.

Combine the RAG pipeline and the front-end chat widget from earlier in this track into one shippable product, indexing products and custom post types, citing real URLs, handing off to a human in real time, and keeping every byte of data in your own WordPress database.

A cross-cutting skill course on writing prompts that behave predictably instead of flaky, inconsistent ones, system instructions, few-shot examples, structured JSON output, ability tool-calling prompts, guardrails, output validation, and reusable prompt templates.

A complete, production-oriented retrieval-augmented generation pipeline for WordPress, chunking real content, generating and storing embeddings, running semantic search in PHP, and grounding an AI assistant's answers so it stops guessing and starts citing your actual site.

The final course in the track. Turn what you built in Courses 2 and 8 into a real product, pricing models, licensing systems, GPL compliance, a WordPress.org launch funnel, alternative sales channels, and support practices built for an AI product's specific failure modes.

The proactive counterpart to debugging. Set up real PHPUnit tests for permission_callback and execute_callback, design abilities so an LLM dependency is injectable in tests, write evals that catch AI-output regressions, contract-test your MCP tools, and wire it all into a CI/CD pipeline that blocks a merge before it breaks an agent.

A corrected, honestly-sourced course. There is no shipped voice-command feature for managing a WordPress site today, only a text-based AI Assistant and a text/API-driven MCP agent path. This course builds a real voice interface from scratch, browser and local speech-to-text, local neural text-to-speech, a voice-driven chat widget, voice search grounded in your content, and voice commands gated behind human confirmation before anything destructive runs.

The entry point for the whole developer track. What the WordPress AI stack actually is, how the Abilities API, MCP Adapter, MCP, and PHP AI Client SDK fit together, and a working local setup to build on.

Wire WordPress abilities and events into external automation platforms. Real n8n, Make, and Zapier patterns for webhooks in, webhooks out, CRM and email chaining, Slack notifications, and a clear framework for when orchestration belongs outside WordPress entirely.

The real security model behind WordPress AI agent access, Application Passwords instead of OAuth, permission_callback and WordPress roles instead of a made-up RBAC system, plus the audit logging and rate limiting patterns you have to build yourself because the adapter doesn't ship them.