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.
How It Works
What you want built. How it should work. What matters and what doesn't. Clear descriptions produce better software.
AI agents write the code, connect the APIs, configure the infrastructure. What used to take weeks now takes minutes.
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.
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.
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.
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.
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.
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.
Direct agents with your voice. On-device Whisper, push-to-talk hotkeys, command routing -- speak and watch agents execute. Voice in, deployed code out.
Make AI agents reliable at scale. Budget caps, context overflow prevention, guard rails -- the production engineering that keeps agents on track when it matters.
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.
See how real projects get described in prompts, configs, and agent instructions. 15-20 min focused lessons.
Direct an AI agent to build something real using the patterns you just learned. Prompts, CLAUDE.md rules, MCP tools.
Deploy what the agent built. Every lesson produces something real -- a live site, a working server, a configured pipeline.
Share your build, compare how others described the same goal, and sharpen your ability to direct agents.
Watch real descriptions become real software. See exactly how prompts, configs, and instructions produce working output. 15-20 min focused lessons.
Every lesson includes downloadable CLAUDE.md files, prompt templates, and agent configs -- proven patterns that get results.
Each lesson ends with something deployed -- a live site, a working server, a configured pipeline. Real output, not homework.
From zero to your first AI-built project. Install Claude Code, Ollama, MCP servers, and ship something real in one session.
Write your first persistent instruction file. CLAUDE.md tells agents what you expect, how to work for you, and what conventions to follow.
Real client project walkthrough. Tell an agent to build a restaurant website and watch it go from description to deployed, responsive, live site.
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.
A complete CLAUDE.md with custom rules, hooks, 3 profiles, and autonomy framework. The configuration file that shapes every AI interaction you have.
Ollama running multiple models with Qdrant RAG on your own hardware. Private, fast, no API costs.
A working MCP server you built from scratch. One instruction triggers actions across APIs, databases, and services.
A deployed, responsive website an agent built from your description. Restaurant, portfolio, or landing page -- live on Vercel.
Whisper transcription, command routing, and TTS -- all running locally. Direct agents by speaking instead of typing. Voice in, deployed code out.
Budget guards, rate limiters, context overflow prevention. The systems that keep AI agents reliable and on-task at scale.
Industry tools. You'll learn to direct all of them.
One-time purchase. Lifetime access. Free workshops to start. Pick the track that matches where you are and where you want to go.
2 tracks + 20 lessons
All 6 tracks + everything
1-on-1 + code review
4 nights/wk live builds
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.