Using GitHub Copilot and spec-kit for Agentic Coding, SDD and TDD

Course Description

AI-powered coding tools such as GitHub Copilot are rapidly transforming how software is designed, implemented, and maintained. This course teaches participants how to move beyond simple prompt-based coding and adopt a systematic, agentic approach that improves productivity without sacrificing quality, governance, or maintainability. Participants will use Copilot's advanced chat and agent modes without or with spec-kit to implement “vibe coding” and Spec-Driven and Test-Driven Development (SDD and TDD) respectively.

SDD's structured methodology spans the whole software development life cycle (SDLC) and ensures that software development remains aligned with business intent, technical constraints, and long-term sustainability. Additionally, TDD makes sure that the generated code will be of high quality. The course combines conceptual foundations with extensive hands-on exercises, enabling participants to immediately apply these techniques to real-world projects.

Main Topics

• Copilot Chat modes: Ask, Edit, Plan, and Agent
• Configuring and using MCP tools and toolsets inside Copilot
• Creating and extending multi-file applications with Copilot
• Automating tests, documentation, and source control workflows
• Configuring asynchronous background and cloud-based coding agents
• Spec-driven and Test-driven Development (SDD and TDD) methodology
• Implementing SDD with spec-kit across SDLC phases
• Configuring and using TDD
• Applying SDD and TDD in greenfield and brownfield projects

Target Audience

Software developers and testers as well as their technical managers who want to understand and use GitHub Copilot and spec-kit in agentic coding and spec-driven software development.

Prerequisites

Experience with VSCode or similar IDEs, experience in using ChatGPT or similar chatbots, basic knowledge of the programming language used during lab exercises.