AI-based coaching for women in STEM subjects to improve academic success

Project description

Our aim is to improve the motivation and academic success of women in STEM subjects through AI-based coaching. Due to a low numbers of women and high drop-out rates, there is an acute need for action.

Our solution is an AI coach as a personal assistant, outside of an e-learning platform and independent, not related to a specific subject area or subject field. The AI coach supports female students in their intrinsic motivation, self-reflection on their own learning model and the development of individual learning strategies.

Aspects that a chatbot could address:
- Promote individual skills development and potential
- support self-directed and personalized learning
- reflect on your own self-assessments and learning method
- maintain or even increase personal motivation for the chosen field of study

Our target group are women studying STEM subjects at TU Dresden.
Regardless of which semester, as a target group and as participants in the development. By involving the target group in the process, we can ensure that it is precisely tailored to their needs.
With female students for female students!

Project modules

Structure and procedure of our project

1. context analysis - interviews and learning diary study

How do female students learn? With what? When? Where?

To find the right approach and understand the needs, we start with a context analysis. To do this, we use methods from the DesignThinkingToolBox, starting with a series of interviews and concluding with a diary study.

We are looking for women from STEM subjects who can give us an insight into their learning during their studies.
Would you like to support us? Then please contact us at

2. development of AI coach

In the course of the project, we are developing the AI coach as a progressive web app, which supports female students in the form of a natural language chatbot in coping with study tasks, promotes self-assessment (reflective dialogs) and resource orientation.

3. formative and summative evaluation

Target group-oriented and user-oriented - that is our main focus!

We will already discuss initial concepts of the chatbot with the target groups and also evaluate many further development steps.

An AI-based tool becomes more targeted and precise through interaction and prompts.
The chatbot is interacted with and the results evaluated in several evaluation series. After a feedback loop, the chatbot is adapted and enters the next loop so that the functions can also be tested by the target group.

We are dependent on your feedback. Would you like to take part and test the chatbot? Then get in touch at