AI Genius Episode 1 - Attendee Companion

AI Genius Episode 1 workshop hero image showing the event title and branding

This guide is your complete, self-contained attendee companion. Everything you need, prerequisites, setup, and every exercise, step by step, lives on this site. You only need the repository for one thing: cloning the starter code.

What You Will Learn

What "AI-native" actually means for developers
How to write issues that give Copilot the context it needs
How to assign work to Copilot and observe it in action
How to review Copilot-generated PRs like a senior developer
How to iterate via PR comments instead of starting from scratch
Best practices for collaborating with AI throughout the coding process

The AI-Native Workflow Loop

IDEA
  └─► GitHub Issue  (describe the work)
        └─► Assign to Copilot  (Copilot agent picks it up)
              └─► Code is generated in a secure sandbox
                    └─► Draft PR is opened  (with session log)
                          └─► Human reviews and iterates via PR comments
                                └─► Merge and ship

You are the tech lead in this workflow. Copilot handles the how. You define the what and why.

Prerequisites

Before you start Chapter 1, make sure you have:

A GitHub account with access to GitHub Copilot
The GitHub Copilot App installed on your desktop
Python 3.10 or later installed locally
Git installed locally

Setup: Get the Starter App Running

Fork the repository to your own GitHub account: go to codess-aus/AIGenius-GHCP-AINative and click Fork in the top-right corner.

Clone your fork locally:

git clone https://github.com/YOUR-USERNAME/AIGenius-GHCP-AINative.git
cd AIGenius-GHCP-AINative

Install dependencies and run the starter app to confirm it works:

cd starter-app
pip install -r requirements.txt
python app.py add "Deploy the API" --priority high --due 2025-12-31 --tag work
python app.py add "Buy coffee" --priority low --tag personal
python app.py list
python app.py stats

You should see a formatted table of two tasks and a stats summary. If that works, you are ready.

Open the GitHub Copilot App on your desktop and connect it to your forked repository.
Head to Chapter 1 below and work through the chapters in order. Each one tells you exactly what to do, no need to jump back to the repo's README or exercises/ folder.

The 5 Golden Rules of AI-Native Coding

Write better issues - your issue IS your prompt. Be specific.
Review like a senior dev - AI generates fast, humans verify smart.
Use copilot-instructions.md - give Copilot standing context about your project.
Iterate, don't regenerate - guide via comments rather than starting from scratch.
Stay in the loop - check the session log, understand what Copilot did and why.

Chapter 1

Write a Well-Formed Issue

Learn the anatomy of a great issue, work through a fully worked example, and write your own issue using one of four feature options.

Read chapter →
Chapter 2

Assign to Copilot

Assign your issue, open the Copilot App, and observe the agent clone, explore, implement, and open a draft PR in real time.

Read chapter →
Chapter 3

Review a Draft PR

Use a practical review framework to validate correctness, quality, security, and test coverage, then leave a real review comment.

Read chapter →
Chapter 4

Iterate via PR Comments

Watch Copilot respond to your feedback, re-review the update, and complete the loop by merging the PR yourself.

Read chapter →
Chapter 5

Azure + AI Extension

Tackle a harder, cloud-flavoured challenge: Azure Table Storage persistence or Azure OpenAI-powered smart tagging.

Read chapter →
Chapter 6

Resources and Next Steps

Keep learning with curated links covering Copilot agents, fleet workflows, community projects, and certifications.

Read chapter →