Skip to content

Revise skills and mentors for GSoC 2026 project #115

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
wslany merged 1 commit into from
Jan 30, 2026
Merged

Revise skills and mentors for GSoC 2026 project #115

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 8 additions & 8 deletions pages/development/google-summer-of-code/2026.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,20 +82,20 @@ The developer should have knowledge of Flutter. Develop and implement missing to
{: .label .label-blue }

{: .highlight }
> **Required Skills**: Kotlin, Python, Android AI and ML Tools, Android-Development, Agile Development, Test Driven Development, Clean Code<br>
> **Possible Mentors**: Paul Spiesberger, Patrick Ratschiller <br>
> **Required Skills**: Kotlin, Python, JavaScript, Android AI and ML Tools, Android-Development, Agile Development, Test Driven Development, Clean Code<br>
> **Possible Mentors**: Paul Spiesberger, Wolfgang Slany <br>
> **Expected Outcome**: An integrated proof of concept AI mentor within PocketCode <br>
> **Difficulty level**: Advanced
> **Difficulty level**: Advanced

AI is now capable of sophisticated programming and can automate many coding tasks. More importantly, it excels at explaining code to students, making learning more engaging and accessible. Our goal is to integrate an AI-powered mentor into PocketCode that understands a student’s programming context and offers real-time guidance to enhance learning and coding skills.
AI is now capable of sophisticated programming and can automate many coding tasks. More importantly, it excels at explaining code to students, making learning more engaging and accessible. Our goal is to integrate our AI-powered mentor, developed during GSoC 2025, into PocketCode. This mentor understands a student’s programming context and provides real-time guidance to enhance learning and coding skills. We already have an existing [AI Tutor SDK](https://github.com/Catrobat/catrobat-ai-tutor) and are now ready to integrate it into PocketCode and its derivatives to test and improve students’ experiences with PocketCode + AI.

The AI mentor could:
- Explain programming concepts, from variables and loops to software design patterns and testing strategies
- Suggest code from text prompts, help debug issues, and propose project ideas
- Assist in code architecture, naming conventions, and writing Catrobat language tests
- Explain programming concepts, ranging from variables and loops to software design patterns and testing strategies
- Suggest code from text prompts, help debug issues and propose project ideas
- Assist with code architecture, naming conventions and writing tests in the Catrobat language
- Explain and translate downloaded projects from other users

You won’t need to implement everything—just focus on a part that excites you most! The Catrobat team will provide the initial prompt and necessary API access or local LLMs for support.
You won’t need to implement everything—just focus on the part that excites you most! The Catrobat team will provide the initial prompt and the necessary API access or local LLMs for support.

<hr>

Expand Down