A hands-on workshop where participants build a project prototype entirely through an agentic workflow — using GitHub Copilot's Ask, Plan, and Agent modes together with specialist agents, reusable skills, and a strict TDD loop. No implementation code is provided; everything is produced through structured AI collaboration.
- Use the Right Mode: Know when to reach for Ask (sparring partner), Plan (review before execution), or Agent (direct execution), and why the distinction matters
- Blueprint Before Building: Use AI to produce
BLUEPRINT.mdanddeveloper_todo.mdbefore writing a single line of implementation code - Author Specialist Agents: Create focused agents with clearly defined responsibilities, minimal tool sets, and explicit domain boundaries
- Replace Guesswork with Skills: Build reusable skills that give agents deterministic capabilities — consistent backlog item structure, correct test execution, reliable project state
- Implement End-to-End with TDD: Drive one backlog item from data layer through to a tested UI component using the strict test-first loop
Build something from scratch with the help of GitHub Copilot.
💡 Tip: Not sure what to build? Use Plan Mode in GitHub Copilot (press
Shift+Tabin the CLI or select "Plan" in VS Code Copilot Chat) to brainstorm and spar with Copilot. Describe your interests or problem domain and let Copilot help you shape an idea, outline an architecture, and break it down into actionable steps — before writing a single line of code!
Want to start from the basics? Follow a guided, hands-on workshop to learn GitHub Copilot from the ground up using the CLI:
Note: The techniques and patterns you learn in this workshop apply equally to VS Code with GitHub Copilot — completions, chat, and agent mode all work the same way. Feel free to follow along in whichever tool you prefer!
- Choose your project
- Follow the guide or make your own:
- Use AGENTIC_WORKFLOW.md as your step-by-step guide through blueprinting, instruction authoring, specialist agent creation, and feature implementation.