GEMDUCK · AI PROJECT LAB

Go from “I can use AI”
to “I built something that works.”

This is not another theory course. Download the course folder and open it in Codex or Claude Cowork. The AI shows you the finished result first, then guides one step at a time until your project runs and passes acceptance.

16 complete project foldersEvery project has a reference + starterEvery step has passing evidence
See exactly how Project 01 works ↓
Pay once · no subscriptionInstant access after payment7-day refund period under the terms
Stripe shows the payment methods available for your device and country. Your course email is used only to deliver access.

WHY THIS COMES AFTER THE FREE COURSE

The free course teaches the method.
Project Lab turns it into working projects.

NOW · FREE FOUNDATION COURSE

Understand AI and use it well

  • Understand models, prompts and workflows
  • Complete browser-based exercises
  • Know where AI can help
You never need Project Lab to continue the free course
→
NEXT · PROJECT LAB

Open a folder and complete a real deliverable

  • Run the finished reference first
  • Rebuild it with the AI from starter
  • Test, repair and keep a local working project
You are buying a prepared path to a result—not more disconnected information

PREVIEW BEFORE YOU BUY

What happens in the first project?

Every beginner starts with Project 01, the AI Personal Brand Website. You do not choose between 16 projects or write code on the first screen.
Project 01 · reference/index.html

AI WORKFLOW SPECIALIST

Hello, I’m Alex.

I turn repetitive work into simple AI-assisted systems.
The finished reference opens directly in your browser
  1. 01

    AI checks first

    Confirm that you opened the course root folder and that the required tools are available.

  2. 02

    See the finished result

    Open the reference so you know exactly what you are building.

  3. 03

    Do only the first step

    The AI explains starter and helps change your name and positioning—without dumping ten commands on you.

  4. 04

    Make it yours

    The AI interviews you about experience, skills and contact details, then writes approved content into the page.

  5. 05

    Run and repair

    Open the page locally. If something fails, diagnose it from the files and actual output.

  6. 06

    Keep passing evidence

    Check mobile layout, links and content, then record the evidence in PROJECT-REPORT.

You keep:A personal website folder you can open on your computer, continue editing and optionally publish.Once your AI tool is installed, you can view the reference before writing code. Completion time varies by tool, computer and level of customisation.

NOT A FOLDER OF PROMPTS

Each folder already contains a complete hands-on path.

01Runnable finished reference
02Safe starter to customise
03AI tutor instructions
047 guided checkpoints
055+ acceptance checks
06Sample data and safety boundaries

WHAT YOU WILL ACTUALLY BUILD

See the result first. Then build it once.

Projects 01–04 preview in a browser. Later projects let the AI check your local environment and explain missing tools instead of pretending a command worked.
Project 12 · dashboard.html

WEEKLY ACQUISITION REPORT

78 leads

Source: metrics.csv · original unchanged

16 COMPLETE PROJECTS

From your first published page to a demo-ready micro-SaaS.

Publish Your Work

PROJECT 01Beginner

AI Personal Brand Website

Build a mobile-friendly personal brand website with safe course samples, pass local checks, then decide whether to publish.

60–90 minutesBrowser
PROJECT 02Beginner

AI Lead-Generation Website

Create a lead-generation page for a real service with pricing, FAQs and an enquiry form.

90–120 minutesBrowser
PROJECT 03Beginner

AI Practical Mini Tool

Turn a repeated calculation into a browser tool with inputs, rules, results and a copy button.

90–120 minutesBrowser
PROJECT 04Beginner

AI Browser Game

Build a browser game with start, scoring, increasing difficulty and replay.

120–180 minutesBrowser

Work Automation

PROJECT 05Intermediate

AI Email Triage and Reply Assistant

Read test emails, classify and prioritise them, then create reply drafts that wait for human approval.

2–3 hoursNode.js
PROJECT 06Beginner

AI Meeting Notes to Action Items

Turn messy meeting notes into decisions, owners, deadlines and questions that still need confirmation.

90–120 minutesNode.js
PROJECT 07Intermediate

AI Invoice and Form Extractor

Extract a batch of text invoices into an auditable CSV and flag missing or duplicate records.

2–3 hoursPython 3

AI Applications

PROJECT 08Intermediate

AI PDF Knowledge Assistant

Answer questions about a set of local documents with filenames and line-number citations.

3–4 hoursPython 3
PROJECT 14Intermediate

AI Customer Support Knowledge Bot

Answer from approved FAQs with citations and escalate low-confidence questions to a person.

3–4 hoursPython 3

Marketing and Sales

PROJECT 09Beginner

AI Multi-Platform Content Repurposer

Turn one original long-form article into email, LinkedIn and short-video drafts with human review.

90–120 minutesNode.js
PROJECT 10Intermediate

AI Lead Scoring System

Score and rank form leads with visible rules, then recommend a next step.

2–3 hoursNode.js

Research and Data

PROJECT 11Intermediate

AI Competitor and Market Intelligence Assistant

Build a dated competitor report from saved primary material with links, evidence levels and explicit unknowns.

2–3 hoursNode.js
PROJECT 12Intermediate

AI Data Analysis Dashboard

Turn a CSV into auditable KPIs, trend charts, an anomaly list and a standalone HTML report.

2–3 hoursPython 3
PROJECT 13Intermediate

AI Daily Intelligence Agent

Fetch, deduplicate and rank RSS items, then create a daily brief with original links.

2–3 hoursPython 3

Advanced Projects

PROJECT 15Advanced

AI Quant Strategy Backtesting Lab

Turn a precise trading hypothesis into a historical backtest and compare it with buy and hold.

4–6 hoursPython 3
PROJECT 16Advanced

AI Micro-SaaS

Start with one narrow problem and build a SaaS prototype with demo login, core value, usage limits and a pricing page.

6–10 hoursNode.js

HOW IT WORKS

Start in four steps. No programming experience required.

01

Download and extract

After purchase, get the complete ZIP from your private download centre.

02

Open it in your AI tool

Codex Desktop or Claude Cowork works best. Other folder-aware AI coding tools may also work.

03

Say “Start the course”

The AI reads START-HERE, the tutor protocol and your progress, then advances one checkpoint.

04

Keep a verifiable project

Every project must run, pass tests and record evidence in PROJECT-REPORT.

PROJECT LAB IS FOR YOU IF

You finished the foundations but still have not built something real.

  • You want to build a website, automation, data tool or AI application but do not know where to begin
  • You are willing to open a folder and follow one AI-guided step at a time
  • You need a finished reference, starter and acceptance standard—not more random prompts

IT IS NOT THE RIGHT FIT IF

You only want passive videos or expect AI to make money automatically.

  • You are unwilling to install any local AI tool
  • You expect a promise of income, employment or investment returns
  • You want one button to complete every project without making decisions or checking results

Tool compatibility

Best: Codex Desktop, Claude Cowork.
Works: Claude Code and folder-aware AI coding tools.
Limited: web chats that accept only single-file uploads.

Transparent costs

The course pack itself calls no paid model API. Your cost depends on the subscription or usage allowance of the AI tool you choose. Every reference starts with local sample data.

Safety boundaries

Email stays in draft; quant projects use historical backtests only; research keeps sources; support, finance and high-impact decisions require human review.

QUESTIONS BEFORE YOU BUY

Know exactly what happens next.

Is this another 16-lesson video course?

No. It is 16 local project folders. Each includes a finished reference, starter, AI tutor instructions, checkpoints, tests and an acceptance report. Your AI tool reads those files and guides the hands-on work.

Why not just ask ChatGPT to build it?

You can, but beginners usually lack a precise goal, runnable reference, correct order and acceptance standard. Project Lab fixes those inside the course files so the AI cannot start by generating a pile of work you cannot judge.

Can I start if I cannot code?

Yes. The first projects begin with finished HTML files that open in a browser, and the AI advances one step at a time. You still need Codex Desktop or Claude Cowork; the private download page guides installation, extraction and your first message.

Where do I go after purchase?

You enter a private download centre: download the ZIP, choose the Codex or Claude Cowork setup guide, open the course root folder and copy “Start the course”. You will not be left guessing after download.

Are there additional model costs?

The folder itself calls no paid API. Model cost depends on the AI tool and plan you choose. Every project starts with local sample data and clearly labels any external service.

What if it is not right for me?

The digital course has a seven-day refund period under the terms. It does not promise income, employment or investment results.

V1.0 · ONE-TIME PURCHASE

Do not collect another course.
Complete the first project you can open and run.

Pay once · no subscriptionInstant access after payment7-day refund period under the terms
Stripe shows the payment methods available for your device and country. Your course email is used only to deliver access.
This digital course does not promise income or employment. If it is not useful, you may request a refund within seven days under the terms.