Presentation, Exercise

Agentic Coding with GitHub Copilot

View material

This repository contains the course material for our course on 'Agentic Coding with GitHub Copilot'. In this course we will go beyond chat-based interactions and explore the capabilities of coding agents.
Associated in-person course: https://training.vib.be/all-trainings/agentic-coding-github-copilot-0

DOI: https://doi.org/10.5281/zenodo.20344541

Licence: Creative Commons Attribution 4.0 International

Contact: [email protected]

Keywords: Artificial Intelligence, Coding

Competency level: • Beginner

Resource type: Presentation, Exercise

Status: Active

Prerequisites:

Access to GitHub Copilot license

Learning objectives:

  • Explain key concepts and terminology related to agentic coding (agents, planning loops, tools, guardrails).
  • Describe the agent loop (goal → plan → act → observe → revise) and its implications for software development.
  • Summarize common failure modes and risks of coding agents.
  • Write effective prompts and task descriptions that guide agent behavior.
  • Critically review agent-generated code for correctness, maintainability, and security.
  • Design an end-to-end agentic workflow for a realistic coding scenario.
  • Produce a reusable prompt or workflow template that can be applied in your own projects

Authors: Jolan Heyse

Contributors: Bruna Piereck

Scientific topics: Computer science

Activity log