OPUS 4.6 IS HERE // NEW describe it, Opus ships it // see plans →
Courses Workshops Community Tools Directory Prompt Library Skills Library Pricing Log In
Start Building
BUILD
AI Agent Training

Ship
Software.
Not Code.

Learn to direct AI agents that write the code, connect the APIs, and deploy to production. You describe what you want. They build it.

CLAUDE.md architecture. Prompt engineering. MCP servers. Agent orchestration. Structured training in the skills that turn your ideas into shipped products.

~ % |
No Coding Required 6 Tracks 50+ Lessons Ship Real Projects Free Workshops Enrolling Now No Coding Required 6 Tracks 50+ Lessons Ship Real Projects Free Workshops Enrolling Now
6
Tracks
18
Workshops
50+
Lessons
200+
Prompt Templates
All
Skill Levels
24/7
Community

How It Works

01

You Describe It

What you want built. How it should work. What matters and what doesn't. Clear descriptions produce better software.

02

Agents Build It

AI agents write the code, connect the APIs, configure the infrastructure. What used to take weeks now takes minutes.

03

You Ship It

Review, refine, deploy. You stay in control of what gets built and how it works. The human is at both ends -- direction and judgment.

The people shipping the most software right now aren't writing code. They're directing the agents that write it.

We teach you the directing part.

01 -- Curriculum

Six Tracks.
Real Skills.

Each track teaches a different way to direct AI agents -- from writing your first CLAUDE.md to building custom MCP servers. Practical skills you can apply immediately.

01 Track 1

Claude Code Mastery

Your CLAUDE.md is the configuration file that shapes every AI interaction. Rules, profiles, hooks, autonomy frameworks. Build the document that tells agents how to work for you.

Beginner 8 Lessons
02 Track 2

Local LLM Setup

Run AI on your own hardware. Ollama setup, model routing, VRAM budgeting, RAG with Qdrant -- private, fast, no API costs, and it answers only to you.

Intermediate 10 Lessons
03 Track 3

MCP Development

Build custom MCP servers that connect AI agents to any API, database, or service. One instruction triggers actions across systems. Extend what agents can do for you.

Advanced 8 Lessons
04 Track 4

AI Web Development

Tell an agent "build a restaurant website" and get a production site in under an hour. Learn to describe projects so precisely that agents ship exactly what you want.

Beginner 12 Lessons
05 Track 5

Voice Pipeline

Direct agents with your voice. On-device Whisper, push-to-talk hotkeys, command routing -- speak and watch agents execute. Voice in, deployed code out.

Intermediate 6 Lessons
06 Track 6

Context Engineering

Make AI agents reliable at scale. Budget caps, context overflow prevention, guard rails -- the production engineering that keeps agents on track when it matters.

Advanced 6 Lessons
METHOD
02 -- How You'll Learn

Learn By
Building.

No lectures. No theory dumps. Every lesson starts with something you want to build. You describe it, an agent builds it, you study what worked and what didn't.

01

Watch

See how real projects get described in prompts, configs, and agent instructions. 15-20 min focused lessons.

02

Build

Direct an AI agent to build something real using the patterns you just learned. Prompts, CLAUDE.md rules, MCP tools.

03

Ship

Deploy what the agent built. Every lesson produces something real -- a live site, a working server, a configured pipeline.

04

Refine

Share your build, compare how others described the same goal, and sharpen your ability to direct agents.

WATCH

Video Walkthroughs

Watch real descriptions become real software. See exactly how prompts, configs, and instructions produce working output. 15-20 min focused lessons.

TEMPLATES

Config Blueprints

Every lesson includes downloadable CLAUDE.md files, prompt templates, and agent configs -- proven patterns that get results.

SHIPPED

Real Output

Each lesson ends with something deployed -- a live site, a working server, a configured pipeline. Real output, not homework.

track-1 -- agent setup
# Tell the agent what to build
$ claude "scaffold a portfolio site"
Loading project config...
Connecting 8 MCP tools...
Created responsive portfolio (3 pages)
Contact form, dark mode, animations
$ vercel --prod
Live at portfolio.vercel.app
# Description to production in under 30 min
track-2 -- local AI
# Run AI on your own hardware
$ ollama run deepseek-r1:14b
Loading 8GB model into VRAM...
Ready. Private. No API costs.
# Your hardware, your data, no API costs
BEGIN
03 -- Start Here

Free Workshops.

SHIP
04 -- What You'll Build

What You'll
Build.

Every track ends with a capstone -- something you described and agents built. Portfolio-ready projects that prove you can direct AI to ship real things.

Track 1 Project

Your Agent Configuration

A complete CLAUDE.md with custom rules, hooks, 3 profiles, and autonomy framework. The configuration file that shapes every AI interaction you have.

Track 2 Project

Private AI Server

Ollama running multiple models with Qdrant RAG on your own hardware. Private, fast, no API costs.

Track 3 Project

Custom MCP Server

A working MCP server you built from scratch. One instruction triggers actions across APIs, databases, and services.

Track 4 Project

Production Website

A deployed, responsive website an agent built from your description. Restaurant, portfolio, or landing page -- live on Vercel.

Track 5 Project

Voice Command Pipeline

Whisper transcription, command routing, and TTS -- all running locally. Direct agents by speaking instead of typing. Voice in, deployed code out.

Track 6 Project

Production Guard Rails

Budget guards, rate limiters, context overflow prevention. The systems that keep AI agents reliable and on-task at scale.

Tools you'll direct agents through
Claude Code Ollama MCP Protocol Qdrant TypeScript Next.js Tailwind CSS Vercel Whisper ElevenLabs GitHub Actions Docker

Industry tools. You'll learn to direct all of them.

05 -- Tools You'll Direct

The Stack.

AI Agents
  • Claude Code
  • CLAUDE.md architecture
  • Multi-agent teams
  • Hooks and guard rails
Local AI
  • Ollama
  • Qdrant vector DB
  • RAG pipelines
  • Model routing
MCP Ecosystem
  • MCP SDK (TypeScript)
  • Browser automation
  • API integrations
  • Custom tool servers
Deployment
  • Vercel / Next.js
  • Tailwind CSS
  • Git workflows
  • CI/CD with agents
$
06 -- Pricing

Choose
Your Path.

One-time purchase. Lifetime access. Free workshops to start. Pick the track that matches where you are and where you want to go.

Foundations $150

2 tracks + 20 lessons

Builder $500

All 6 tracks + everything

Mentored $1000

1-on-1 + code review

Watch & Build $2500

4 nights/wk live builds

07 -- FAQ

Questions.

Who is this training for?

+
Anyone with something to build. Developers, designers, freelancers, founders, operators -- if you understand your field, you can direct AI agents to build working solutions without waiting for a dev team. We teach you the practical skills to make that happen.

Do I need coding experience?

+
No. AI agents write the code. We teach you to direct them: what to build, how to structure it, and how to make them reliable. You bring the ideas and domain knowledge. Track 1 and Track 4 start from zero.

Do I need a Mac?

+
No. Claude Code, Ollama, MCP servers, and the core tools run on Mac, Linux, and Windows. Some lessons show Mac-specific setups (Apple Silicon optimization, Thunderbolt networking), but every concept includes cross-platform alternatives.

How is this different from YouTube tutorials?

+
YouTube shows you what AI can do. We teach you how to use it. Every lesson comes with the exact files that make agents work -- CLAUDE.md configs, prompt templates, orchestration patterns. The instructor ships production software daily using these same tools and methods.

What's in the Mentored tier?

+
Limited to 10 students. Monthly 1-on-1 calls, direct message access, project reviews, and a custom learning path. We review your actual work and help you get better results from agents.

Is this a subscription?

+
No. All tiers are one-time purchases with lifetime access to the content available at purchase. Builder and Mentored tiers include future content drops as they're released.
NOW

Stop
Watching
Tutorials.

Start Shipping Software.

Every lesson produces something real. A live site, a working server, a deployed pipeline. You describe what you want and agents build it.