Skip to content

Course

AI Product Builder build products with AI agents

From idea to a launched product in 8 weeks. Taught by Nazar Mazur — a Senior Technical Product Manager with 10+ years of experience who, in a few months and with no engineering team, built the marketplace svio.com.ua with Claude Code.

  • $299 $199
  • Duration: 8 weeks
  • Format: online, live sessions + hands-on practice
Register
Claude Code
Anthropic's agentic CLI
OpenAI Codex
OpenAI's agentic coding assistant
Google Antigravity
Gemini-based agentic development environment

Program goal

Teach a systematic approach to building digital products with AI agents as active members of your dev team — from idea to requirements, requirements to architecture, architecture to a launched product.

After this course, you'll be able to:

What you'll learn

  • LLM & Agentic AI Fundamentals

    How Claude, GPT, and Gemini actually work: tokens, context windows, tool use, reasoning. When to use a chat interface vs. an agent.

  • Claude Code, OpenAI Codex, Google Antigravity

    A deep dive into each tool with real examples: Claude Code with MCP and Git integration, Codex for agentic tasks, Antigravity — Google's agentic development environment. A clear comparison matrix.

  • Prompt Engineering & Context Design

    How to structure prompts and context for predictable results. Few-shot, chain-of-thought, instruction templates for real product work.

  • Product Architecture & Spec Writing

    From idea to a technical spec AI understands. User flows, data models, API contracts — so the agent doesn't go off track on the first iteration.

  • Verification & Quality Assurance

    How to verify AI-written code: linting, tests, code review. When it's production-ready, and when it needs rework.

  • Ship a Real Product

    From idea to a product with real users: a Supabase database and auth, a Vercel deploy, Sentry monitoring, Resend email. Your capstone is a real product, not a class exercise.

What results will you get?

  • ⭐Launch your first digital product (or internal tool for your business) — from idea to real first users
  • ⭐Cut development time from months to weeks by working effectively with AI agents
  • ⭐Learn to write specs and tasks that give AI a clear goal without unnecessary iterations
8

weeks of intensive training

16

live sessions (2 per week)

1

production-ready product on graduation

Nazar Mazur

Instructor

Nazar Mazur

Senior Technical Product Manager

10+ years in product management across digital marketing, big data and analytics. He's gone from Product Owner at N-iX (web and big data projects) and US HealthConnect to Virtuozzo/OnApp, BrandShelter (Team Internet, brand protection) and Upday (1.5M+ traffic). He ships real products with agentic AI — Claude Code, Codex, Antigravity — every day, and in this course he shares that exact process, not theoretical best practices.

  • ✓10+ years in product management
  • ✓Experience: N-iX, US HealthConnect, Virtuozzo, BrandShelter, Upday
  • ✓Stack: Claude Code · Codex · Antigravity · Supabase · Vercel
  • ✓Domains: AI, e-commerce, big data, cloud, real estate
Nazar on LinkedIn →

Proof, not a promise

Taught by someone who actually did it

The best proof that a method works is a real product. In a few months, solo, with no engineering team, Nazar built svio.com.ua — a trust marketplace, entirely with agentic development. Not a landing page, but a working platform with payments, verification and ratings.

  • Escrow-protected deals

    Safe settlement between strangers.

  • Diia seller verification

    Sellers confirmed through Diia, Ukraine's government e-service.

  • Trust & rating system

    Reputation as the backbone of the marketplace.

  • Multiple verticals

    Goods, services, jobs, real estate, volunteering.

  • Time-banking

    Exchanging services and time within the community.

  • Charity built into purchases

    A share of transactions funds good causes.

See svio.com.ua →

Curriculum

8 weeks · online format

Module 1. LLMs, Agentic AI & First Tools (Week 1)
  • ·How large language models work: tokens, context windows, fine-tuning vs prompting
  • ·The difference between a chat, an agent, and a multi-agent system
  • ·When to use which model: cost / quality tradeoffs
  • ·First hands-on session: prompt → result → error analysis
  • ·Overview of agentic tools: Claude Code, OpenAI Codex, Google Antigravity
Module 2. Claude Code + GitHub — Agentic Development (Week 1-2)
  • ·Claude Code as a local tool: install, setup, MCP (Model Context Protocol)
  • ·GitHub from scratch: repos, branches, commits, pull requests — even if you've never touched git
  • ·How Claude Code reads and writes code within a versioned project
  • ·Reviewing AI-generated diffs before you merge: what to actually check
  • ·Hands-on: your first webpage, committed to your own GitHub repo
Module 3. OpenAI Codex & Google Antigravity — Other Agentic Tools (Week 2)
  • ·OpenAI Codex: an agentic CLI and cloud agent for writing, refactoring, and reviewing code
  • ·Google Antigravity: Google's agentic development environment built on Gemini — when to pick it over Claude Code
  • ·Comparison matrix: Claude Code vs Codex vs Antigravity — strengths and weaknesses of each
  • ·Structured output: JSON schemas, function calling, result reproducibility
  • ·Hands-on: the same task solved with all three tools — comparing the results
Module 4. Context, md Files & Prompt Engineering (Week 2-3)
  • ·Managing the context window: what the agent actually "sees" — and why the result depends on it
  • ·CLAUDE.md / AGENTS.md: instructions for the agent as the project's "constitution"
  • ·Breaking work into md files: specs, task lists, plans, project memory
  • ·Few-shot, chain-of-thought and instruction templates for predictable results
  • ·Hands-on: set up project context so the agent doesn't get lost in a large codebase
Module 5. Product Spec, Requirements & UI Through an AI Lens (Week 3)
  • ·From idea to requirements: getting clear requirements without a business analyst
  • ·User flows, wireframes, data models: what AI needs to write correct code
  • ·Design and UI with AI: Tailwind, shadcn/ui, v0.dev — a professional look without a designer
  • ·A technical spec an agent understands: API contracts, error cases, edge cases
  • ·Documentation as source of truth: README, API docs, architecture docs AI can read
  • ·Hands-on: writing a spec for a complete web application
Module 6. Backend, Database & Auth — Supabase / Firebase (Week 4)
  • ·Supabase vs Firebase: when to choose which, and how they differ
  • ·Designing your database schema together with an AI agent
  • ·Authentication and sign-up: email, OAuth, magic links
  • ·Row-Level Security and access control — keeping user data safe
  • ·File storage and serverless / edge functions for your logic
  • ·Hands-on: wire a database, auth and storage into your product
Module 7. Verification, Testing & QA + GitHub Actions (Week 4-5)
  • ·How to verify AI-written code: linting, unit and integration tests
  • ·GitHub Actions: automatic CI on every push and pull request
  • ·Vercel preview deployments: check changes before they hit production
  • ·A code-review checklist + verification loop: the agent fixes itself from feedback
  • ·When the agent breaks: hallucinated APIs, runaway edits, "it deleted my code" — and rolling back with git
  • ·Production readiness: when code is ready to ship vs. needs rework
Module 8. Multi-Agent Workflows & Scaling (Week 5)
  • ·Single-agent vs multi-agent: when one agent isn't enough
  • ·Specialized agents: code writer, code reviewer, architect, product manager
  • ·Synchronization: how agents exchange context and artifacts (code, specs, reports)
  • ·Orchestration patterns: sequential, parallel, conditional flows between agents
  • ·Hands-on: architecture, coding, and review split across 3 agents
Module 9. Launch & Operations: Vercel, Sentry, Resend (Week 5-6)
  • ·Deploying to Vercel: CI/CD, environment variables, secrets, your own domain
  • ·Sentry.io: real-time error and performance tracking
  • ·Resend: transactional email — confirmations, notifications, magic links
  • ·Monitoring, logs and alerts: find out about a breakage before your customer does
  • ·Iteration: user request → task for an agent → fix in production
Module 10. Payments & Monetization — Stripe and Ukrainian gateways (Week 6)
  • ·Stripe for the global market + LiqPay / Fondy / WayForPay for Ukraine: when to use which
  • ·One-time payments, subscriptions and pricing tiers — what fits your product
  • ·Checkout, webhooks and recording transactions in your database — safely and reliably
  • ·Escrow logic for safe marketplace settlement (svio.com.ua case)
  • ·Test mode, keys and payment security — without leaking secrets
  • ·Hands-on: wire payment acceptance into your product
Module 11. AI Product Management Skills (Week 6-7)
  • ·Writing specs as a non-engineer: giving engineers/agents a clear task
  • ·Tradeoffs: cost vs quality vs speed when choosing a model and architecture
  • ·Evals: measuring how well an AI agent performs, not just "the code runs"
  • ·Analytics & metrics: what matters for AI products beyond bug counts
  • ·Hands-on: write a spec for a 3-module system, feed it to 3 different agent setups
Module 12. Capstone Project & Portfolio (Week 7-8)
  • ·Project selection: your own idea or one of 5 suggested directions
  • ·Full stack: GitHub + Supabase/Firebase + Vercel + Sentry + Resend
  • ·Build: using all three tools in parallel (Claude Code, Codex, Antigravity)
  • ·Deploy: launch to production, first 50-100 users, first feedback loop
  • ·Presentation & portfolio: documentation, presenting your project

Pricing

  • Course

    $199

    or 3 payments of $69

    • ✓ 8 weeks (16 live sessions, 90 min each, Mon-Wed 7:00 PM Kyiv time)
    • ✓ Recordings of every session + materials in a private Slack channel
    • ✓ Homework + feedback from Nazar Mazur
    • ✓ 2 code-review sessions for your capstone project
    • ✓ Prompt templates, spec documents, checklists
    • ✓ Course completion certificate

    Seats left

    6 SEATS

    Register
  • Popular

    Course + Mentorship

    $349

    or 4 payments of $89

    • ✓ Everything in the Course plan +
    • ✓ 1-on-1 mentoring with Nazar: 8 sessions, 30 min each, throughout the course
    • ✓ Private consultations on your project specifics
    • ✓ Deeper code review: 6 iterations instead of 2 for your capstone
    • ✓ Launch help: landing page templates, email capture, analytics
    • ✓ Post-course: 3 months of light support for your launched product
    • ✓ 30-day money-back guarantee

    Seats left

    3 SEATS

    Register

FAQ

Do I need prior coding experience?

No. This course is built for people without a coding background — we teach you to direct AI agents, not to write code yourself. Basic HTML/CSS or JavaScript helps you move faster, but it's not required.

What if I'm already a developer?

Great — you'll jump straight to "how to work with AI effectively to move several times faster." The course gives you a system, not scattered prompting.

What is "agentic AI"? Is it just ChatGPT?

No. ChatGPT is a chat interface — you write a prompt, it replies. Agentic AI is a system that makes its own decisions, reads context, writes code, tests it, and verifies the result. Claude Code, Codex, and Antigravity are classic examples.

Will sessions be recorded?

Yes. All 16 live sessions are recorded and yours to keep, along with materials and templates in a private channel.

What are the session times?

Monday and Wednesday, 7:00–8:30 PM Kyiv time (UTC+2). If you're in a different timezone, the recording is available the next day.

Does the capstone have to be my own idea?

You can bring your own idea or pick from 5 suggested directions. The only requirement: it has to be a real, launched product — not something stuck on localhost.

How much time per week outside sessions?

Plan for 5-7 extra hours on homework and your capstone project — roughly 16 hours a week in total.

Register

Fill out the form to reserve your seat

We'll get back to you within one business day.