Introduction to AI Vibe Coding for Research
At a glance
- Before the course
- No AI experience needed
- Participants leave with
- Software of their own that helps in their work, built and tested on their own computer without knowing how to code
- Format
- In person, online or both; one block or several weeks; agreed with you
Course content. Your research work is full of small tasks that you feel could be automated by software, if only it existed. In this course, you learn to vibe code for your specific research: to build your own bespoke software, tailored to your work, without learning how to program. You learn the basics of using AI programming tools, and how to describe in plain language what the program should do, so that AI comes to a best-effort first attempt. More importantly, you learn how to improve that first draft, by iteration, testing, systems thinking and adaptation to the domain the program serves. This is the core competence of vibe coding, one which researchers are particularly well suited for, with their deep knowledge of their own field and strong competence in critical and experimental thinking.
The course is structured as a research lab: from the first session, you try to build things for your own research, and you share your results and experiences with others. You leave with programs and automations that you designed to help you right away in your work. But more importantly, you gain the competence and confidence to keep using AI programming tools in the coming years, be it within or outside of academia.
Goals. You learn to:
- build, run and test vibe-coded software on your own computer that helps you in your work, without knowing how to code;
- describe a research task in a way that maximises the AI's ability to come to the best possible first draft of a program that automates it;
- identify and diagnose properly what needs improvement or fixing in your program, so that a next coding attempt can do better;
- keep your files and your data safe while using AI to code for your work;
- judge which tasks are worth a vibe-coded automation and which are not, and when your domain expertise is critical in the build.
Format. Every course can take different shapes: in person, online or both, as one intensive block or spread over several weeks, shorter or longer. Length, format and all practical details are open: we agree them together, and I adapt the course to what your institution needs.
Interested for your programme? Write to me →