AI GamingGPT & Claude

CyberTech33

CodeGame’s primary target audience consists of school students, university students, and beginners who want to learn programming. Traditional teaching methods, an excessive focus on theoretical knowledge, and limited opportunities for hands-on practice can make learning programming difficult and reduce users’ motivation. CodeGame aims to address these challenges through gamification, interactive tasks, and artificial intelligence (AI) support. By making programming more engaging, accessible, and practical, the platform helps users develop their coding skills and logical thinking abilities.

Open the demo Video Code

Preliminary score

30.0/ 100Earlyaverage of 2 judges

Value for the user12.0 / 25
A specific problem and a clear outcome from solving it.
Prototype and use of AI6.0 / 30
A working core scenario, and what AI actually contributes to the result.
Quality testing4.0 / 20
Tests, examples of failures, and comparison with the current approach.
Feasibility6.0 / 15
Data requirements, running costs and a clear next step.
Originality2.0 / 10
A meaningful difference from common solutions.

What the judges wrote

Claude Opus 5.5Preliminary27/100
Strengths
Your submission is candid: it states plainly that the MVP has no live AI model, uses rule-based feedback and simulated execution, and that earlier versions existed. Your frontend appears to cover a full learning loop of missions, editor, simulated terminal, hints, XP, achievements and certificates. Making it open instantly with no login or setup lowers the barrier for beginners to try it.
To improve
The card rewards what AI contributes, and your MVP contains none, so the core scenario cannot score as an AI prototype. Even one live AI feature would change that, such as an LLM that explains a learner's specific error or generates a personalised next mission. Your testing section lists known limitations rather than tests. Run a few real learners or scripted code submissions through the hints and report where the feedback was wrong, compared with a standard tutorial. Add running costs per user, a specific target group (for example, Azerbaijani secondary schools), and a concrete next step, and explain how you differ from CodeCombat, Codecademy or Scratch.
GPT-6 AstraPreliminary33/100
Strengths
Your described MVP offers a coherent beginner learning loop through coding missions, mentor hints, XP, and achievements. Your disclosure clearly distinguishes simulated execution and rule-based feedback from live AI functionality. You also identify relevant limitations around secure code execution, API dependencies, and cross-device progress.
To improve
Your next prototype should demonstrate actual code execution and a live AI mentor responding to learners’ errors; development-only AI does not establish AI’s contribution to the submitted experience. Your testing should document correct and incorrect solutions, misleading feedback, and a comparison against static hints with beginner learners. Your feasibility plan should specify execution and API costs, exercise-validation requirements, and a concrete integration milestone.

The team

Fərid Paşazadə
business
Elgün Sadıqzadə QalibLead
developer

Disclosure

Required by the rules. Judges verify it against the repository.

Models: GPT-6 (development assistance only); no live AI model in the MVP.
Data: Synthetic educational exercises and manually created Python challenges. No personal datasets.
Components: HTML5, CSS3, vanilla JavaScript, localStorage, browser-based terminal simulation. No backend.
Built during the event: Confirmed

Quality testing

CodeGame Academy has been developed through multiple iterations, including frontend prototypes and a backend-enabled architecture with AI API integration. For the hackathon MVP, our priority was accessibility, usability, and demonstrating the complete learning journey without requiring external services. We implemented and checked the core frontend components, including interactive missions, terminal simulation, mentor hints, XP progression, achievement tracking, and certificate functionality. **Technical challenges identified:** - External AI API connectivity and configuration can introduce dependencies and availability issues. - Full Python execution requires a secure execution environment. - Browser-based progress storage does not provide cross-device synchronization. - The frontend demo uses rule-based feedback instead of the live AI functionality intended for the full platform. To reduce setup complexity, we separated the interactive frontend demonstration from the backend-dependent functionality. Our goal is to demonstrate the educational value and user experience of CodeGame while maintaining a clear technical path toward a fully integrated AI-powered learning system.

Worth 20 of the 100 points.

Running it

CodeGame Academy is an AI-powered, gamified programming education platform designed for school and university students. The project has also been developed in a full-stack version with a Node.js backend, database integration, API key configuration, and AI-assisted coding features. For this hackathon submission, we have provided a lightweight, frontend-only MVP to allow judges to explore the core experience immediately, without installing dependencies, configuring servers, or obtaining API credentials. **How to run the MVP:** 1. Open the provided Netlify deployment link. 2. Select a programming mission. 3. Write code in the interactive editor. 4. Test the code using the terminal simulation. 5. Explore mentor hints, XP rewards, levels, achievements, and learning progression. No installation or login is required for the submitted MVP. **Technical clarification:** The submitted frontend version uses simulated execution and rule-based educational feedback. The separate backend-enabled version supports AI API integration but is not part of this public demo. **Development disclosure:** Earlier versions of CodeGame existed before this submission. The frontend MVP represents a simplified demonstration of the broader product concept.

Project ownership

The team keeps the rights to this project. Judges were given access for verification only.