Hello and welcome to our workshop! We are very happy to have you here.
This is the @edition edition of this workshop, organised by VIB.
We are using the interactive Open Educational Resource online/offline course infrastructure called LiaScript. It is a distributed way of creating and sharing educational content hosted on github. To see this document as an interactive LiaScript rendered version, click on the following link/badge: LiaScript
In this hands-on workshop, you'll learn how to move beyond chat-based coding and design structured, agentic coding workflows. Using GitHub Copilot, you will learn to write effective prompts, leverage LLMs for multi-file coding tasks, and design workflows that plan, act, and iterate safely. The course features a mix of explanations, live demonstrations, and hands-on exercises, giving you the opportunity to apply LLMs to real-world coding challenges. You’ll also explore how to evaluate agent outputs, implement guardrails, and address important risks and governance issues. By the end of the training, you'll be able to use LLMs for structured coding tasks, design robust agentic workflows, and enhance productivity in your own projects.
To follow along effectively with this course and do the exercises, you need to have a license for GitHub Copilot.
Tip: Students and teachers can apply for a free Pro license through GitHub Education.
If you want to learn more about how to use generative AI, optimize your prompting techniques, and get to know LLM tools that help with literature research, writing, image generation, etc., you can follow our course on Strategic Use of Generative AI.
- 09:30 - 10:30 - Chat-based coding: capabilities and limits
- 10:30 - 10:45 - Coffee break
- 10:45 - 12:30 - Essential features of GitHub Copilot
- 12:30 - 13:30 - Lunch break
- 13:30 - 14:45 - Agentic control and workflow automation
- 14:45 - 15:30 - Responsible use of GitHub Copilot
- 15:30 - 15:45 - Coffee break
- 15:45 - 17:00 - Mini-project: implement an end-to-end agentic workflow
License: Creative Commons Attribution 4.0 International License
Target Audience: Researchers, staff scientists, group leaders, industry professionals, trainers, training providers
Level: Beginner
Prerequisites
To be able to follow this course, learners should have knowledge in:
- Basic knowlegde of HTML
- Basic knowledge of ...
- Being comfortable working with ....
Description This course consist of .....
Learning Outcomes: By the end of the course, learners will be able to:
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
Time estimation: Full day (6-7 hours)
Requirements:
- Basic programming experience (Python or other)
- Familiarity with chat-based LLM tools
- Familiarity with Git is advisable
- GitHub account (and license)
Supporting Materials:
Acknowledgement:
Authors
Contributors
Please cite as:
- ...
Here are some great tips for further learning:
- GitHub Copilot official documentation (link)
- GitHub Copilot Chat cheat sheet (link)
- GitHub Copilot Customization cheat sheet (link)
- Cline official documentation (link)
About ELIXIR Training Platform
The ELIXIR Training Platform was established to develop a training community that spans all ELIXIR member states (see the list of Training Coordinators). It aims to strengthen national training programmes, grow bioinformatics training capacity and competence across Europe, and empower researchers to use ELIXIR's services and tools.
One service offered by the Training Platform is TeSS, the training registry for the ELIXIR community. Together with ELIXIR France and ELIXIR Slovenia, VIB as lead node for ELIXIR Belgium is engaged in consolidating quality and impact of the TeSS training resources (2022-23) (https://elixir-europe.org/internal-projects/commissioned-services/2022-trp3).
The Training eSupport System was developed to help trainees, trainers and their institutions to have a one-stop shop where they can share and find information about training and events, including training material. This way we can create a catalogue that can be shared within the community. How it works is what we are going to find out in this course.
About VIB and VIB Technologies
VIB is an entrepreneurial non-profit research institute, with a clear focus on groundbreaking strategic basic research in life sciences and operates in close partnership with the five universities in Flanders – Ghent University, KU Leuven, University of Antwerp, Vrije Universiteit Brussel and Hasselt University.
As part of the VIB Technologies, the 12 VIB Core Facilities, provide support in a wide array of research fields and housing specialized scientific equipment for each discipline. Science and technology go hand in hand. New technologies advance science and often accelerate breakthroughs in scientific research. VIB has a visionary approach to science and technology, founded on its ability to identify and foster new innovations in life sciences.
The goal of VIB Technology Training is to up-skill life scientists to excel in the domains of VIB Technologies, Bioinformatics & AI, Software Development, and Research Data Management.
Editorial team for this course
Authors: @orcid(Jolan Heyse)
Technical Editors: Bruna Piereck
License: 
{
"@context": "https://schema.org/",
"@type": "LearningResource",
"@id": "https://vib-training-conferences.github.io/agentic-coding-with-github-copilot/",
"http://purl.org/dc/terms/conformsTo": {
"@type": "CreativeWork",
"@id": "https://bioschemas.org/profiles/TrainingMaterial/1.0-RELEASE"
},
"description": "In this course we will go beyond chat-based interactions and explore the capabilities of coding agents with GitHub Copilot.",
"keywords": "AI, LLM, GitHub Copilot, agentic coding, software development, workflow automation",
"name": "Agentic Coding with GitHub Copilot",
"license": "https://creativecommons.org/licenses/by/4.0/",
"educationalLevel": "beginner",
"competencyRequired": "none",
"teaches": [
"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"
],
"audience": "researches, staff scientists, group leaders, industry professionals, trainers, training providers",
"inLanguage": "en-US",
"learningResourceType": [
"tutorial"
],
"author": [
{
"@type": "Person",
"name": "Jolan Heyse"
}
],
"contributor": [
{
"@type": "Person",
"name": "Jolan Heyse"
}
]
}