How we automated task generation for learning
Universal task generator for an educational platform
About product
The universal LLM-based solution reduces the time methodologists spend preparing educational materials for students.
){kind=icon}
6 people
){kind=icon}
3 weeks
What was the task
The client’s product is an international educational platform for self-learning in mathematics and physics. Previously, methodologists manually created training and assessment tasks in their admin panel, which was time-consuming and sometimes lacked a creative approach.
Our task was to implement AI that would simplify the methodologists’ work by automatically generating various types of tasks based on a request, as well as being able to shorten, simplify, and translate them into other languages.
We conducted research and compared popular AI models to identify the most effective one, to assess differences in generation using the same approach, as well as to gather information on possible limitations. The Gemini 2.0 model yielded the best results; we even asked the AI to write its own prompt based on the specified requirements and conditions.
In the end, we produced a universal and endless turnkey task generator. It creates task scenarios and outlines the entire solution algorithm with step-by-step explanations. Now the methodologist only needs to log into the admin panel, navigate to the LLM interface, paste the prepared prompt, then download and import the generated result into the admin system.
What the client got:
- A working MVP integrated into the client’s infrastructure.
- The methodologists’ workflow has been automated and the company’s expenses have been reduced.
- The tasks for students have become more engaging and creative.
Main functionality:
- Creation of various types of tasks (scenarios), including those with images – graphs, diagrams, blueprints
- Integration with the client's admin panel and backend
- Integration with textbook materials
- Localization of the interface and content
- Task generation validator
Interface
