Skip to main content Skip to navigation

Sakshm AI: Advancing AI-Assisted Coding Education for Engineering Students in India Through Socratic Tutoring and Comprehensive Feedback

Project Overview

The document explores Sakshm AI, an innovative AI-assisted coding education platform designed to improve problem-solving skills in engineering students in India through a Socratic tutoring approach. Utilizing Large Language Models (LLMs), Sakshm AI provides personalized feedback, context-aware hints, and adaptive guidance, effectively overcoming limitations of traditional educational tools. The study evaluates the platform's impact on learning outcomes by conducting both quantitative and qualitative analyses of user engagement. Findings indicate that Sakshm AI significantly enhances critical thinking and promotes independent learning among students, demonstrating the potential of generative AI in educational contexts. Overall, the platform exemplifies how AI can transform learning experiences by tailoring educational support to individual needs and fostering deeper cognitive skills.

Key Applications

Sakshm AI

Context: Coding education for engineering students in India

Implementation: The platform employs a Socratic tutoring approach via an AI chatbot named Disha, guiding students through problem-solving without providing direct answers.

Outcomes: Improved problem-solving skills, enhanced engagement, and greater critical thinking among students.

Challenges: Limited support for advanced topics, dependency on the AI for hints rather than direct answers, and some technical issues.

Implementation Barriers

Technical barriers

Users reported issues with platform performance, such as slow response times and occasional bugs.

Proposed Solutions: Implementing autosave features and improving the overall stability of the platform.

Content barriers

A need for a wider variety of exercises and more complex, real-world problems was noted.

Proposed Solutions: Expanding the question bank to include advanced topics and real-world scenarios.

User experience barriers

Users expressed a desire for improved user interface features and navigation.

Proposed Solutions: Enhancing the user interface, including better dark mode functionality and customization options.

Project Team

Raj Gupta

Researcher

Harshita Goyal

Researcher

Dhruv Kumar

Researcher

Apurv Mehra

Researcher

Sanchit Sharma

Researcher

Kashish Mittal

Researcher

Jagat Sesh Challa

Researcher

Contact Information

For more information about this project or to discuss potential collaboration opportunities, please contact:

Raj Gupta

Source Publication: View Original PaperLink opens in a new window