AI School "Conductor": Building IT Products Without Coding Skills

• For russian-speakers (Для русскоязычных)

Intensive Course: 20 Hours (10 Sessions x 2 Hours)

This program is designed for those who want to move beyond simply "chatting" with AI and start using it as a full-scale engineering team. We teach Vibe-coding—a methodology where you act as the architect and conductor, while autonomous AI agents handle all the technical heavy lifting.

---

Tool Stack

During the course, we will deploy and configure your development "cockpit":

• Orchestrators: Antigravity, Claude Code (CLI).
• Environment: VS Code + Windsurf / Cursor.
• Optimization: jcodemunch, MCP (Model Context Protocol).
• Infrastructure: RunPod, Vast.ai (GPU rental), Docker.
• Interfaces: Bolt.new, Lovable.

---

🚀 How to Join

We are currently accepting applications for the live-mentor cohort. To participate:

1. Fill out the form: Application Form
2. Join the Telegram Group: AI School EN
3. Introduce yourself: Once you've filled out the form, drop a message in the group!

---

Curriculum

Module 1: Foundations & Direct Action Tools

Session 01: Logging into Vibe-coding and setting up the "Cockpit"

• Theory (30 min): What is Vibe-coding? Logic over syntax. Tool overview.
• Hands-on (90 min):
  • Installing VS Code, Claude Code, and Antigravity.
  • Git Baseline: Initializing your first repo. Why "Save Points" (commits) are your life insurance.
  • Creating the first project folder.
  • Command: "Make me a simple resume page with a theme toggle."
• Result: A working local page, configured environment, and your first commit.

Session 02: Generating interfaces "with words" & Architectural Choice

• Theory (30 min): Describing structure vs. "make it pretty." Choosing the "form": SPA, Multi-page, or Chrome Extension?
• Hands-on (90 min):
  • Working in Bolt.new or Lovable.
  • Creating a visual prototype.
  • Exporting code to the workspace.
• Result: A finished visual prototype and a clear technical direction.

Session 03: Claude Code — AI Hands & Iterative Refactoring

• Theory (30 min): CLI agent capabilities. Managing dependencies.
• Practice (90 min):
  • Task: "Build the core logic."
  • Refactoring: Commands for cleanup and optimization. "Dialogue with code": how to fix specific details without breaking everything.
• Result: Project gains functionality and clean, structured code.

---

Module 2: Professional Skills & Economy

Session 04: Token Economy, jcodemunch & Environment Security

• Theory: Context windows, API costs, and .env security (Don't leak your keys!).
• Practice: Using jcodemunch for compact context. Setting up .claudignore and .env.
• Result: Reducing costs by 5–10x and keeping your project secure.

Session 05: Agent Skills, MCP & Data Schemas

• Theory: MCP (Google, DBs) and Agent Skills (Expert roles). Designing "Data Schemas" for agents to follow.
• Practice: Connecting external tools. Teaching the agent to work with real-time data and structured DBs.
• Result: An agent capable of complex research and reliable data handling.

Session 06: Orchestration & Agent Teams

• Theory: Agentic engineering. Roles: "Architect," "Executor," "Tester."
• Practice: Running Antigravity to coordinate multiple AIs. Automated bug and security checks.
• Result: A functioning "mini-studio" of AI agents running on your machine.

---

Module 3: Infrastructure & Freedom

Session 07: Own Servers & Open Source (Infinite Tokens)

• Theory: When APIs become too expensive. Overview of RunPod and Vast.ai.
• Practice: Renting a GPU server for $0.30/hr. Deploying DeepSeek-V3 or Llama-3.
• Result: A personal, unlimited AI coder on a remote server.

Session 08: AI as a System Admin & CI/CD

• Theory: Managing servers via SSH. Concept of CI/CD (Automatic updates).
• Practice: "Log into my server, install Docker, set up GitHub Actions for auto-deploy."
• Result: Your project is live and updates automatically on every push.

---

Module 4: Graduation Project

Session 09: The Big Build & Feedback Loop

• Final assembly intensive.
• Feedback Loop: Implementing analytics (PostHog) and iterating based on user data.
• Resolving logic bottlenecks.
• Result: A functioning "mini-studio" of AI agents running on your machine.

Session 10: Polishing & Defense

• Bug fixing via agent "self-diagnosis."
• Final product demonstration.
• Result: Graduation with a fully functional application and the skills to build any IT project in the future.

---

Graduation Project

The requirement for completing the school is a fully functional product created independently using AI agents.

Note: Mentors support you until a successful submission. If the project isn't working, the mentor provides additional consultations until the goal is reached.

---

Why It Works

1. 0% Boring Theory: We don't teach Python or JavaScript syntax.
2. 100% Control: You learn to manage the tools that write the code for you.
3. Efficiency: You learn how to spend pennies on tokens where others spend thousands of dollars.
4. Calendar-based and group training: You'll have additional responsibility, which will prevent you from procrastinating.
5. Real results: The training won't end until you create a real product that you can sell or use yourself.

---

Built for those who want to build the future, not just watch it happen.